DESC:TECHNICAL FIELD
[0001] The present invention generally relates to the field of anti-tank guided missiles (ATGMs) and particularly relates to the system and method for operating a seeker of an anti-tank guided missile (ATGM).
BACKGROUND
[0002] A seeker in an Anti-Tank Guided Missile (ATGM) is a significant component responsible for tracking and homing in on a target. The seeker is typically an electro-optical device consisting of various sensors such as imaging sensors, inertial sensors, angle sensors, etc. The data of such sensors are utilized by a seeker-embedded controller to compute target information such as tracking error, line of sight (LoS) rates, etc. for missile navigation purposes. Within an ATGM, multiple interfaces are provided. For example, in addition to interfaces for the aforementioned sensors, interfaces for other major weapon sub-systems such as onboard computers, telemetry, data loggers, and command launch unit are also present. Further, the protective cover or enclosure that houses the seeker of the ATGM, referred to as the ‘dome’, acts as an impact switch to detonate a warhead of the ATGM upon impact with the target.
[0003] Existing approaches for improving the hit rate of an ATGM utilize embedded platforms such as microcontrollers, field-programmable gate arrays (FPGAs), and digital signal processors (DSPs) for sensor signal processing to extract target information for navigation of the ATGM towards the target. However, due to the limited computing power of such platforms, conventional signal processing techniques are employed which limit the deployment scenarios of the seekers and ultimately leads to reduced capabilities of the seekers.
[0004] Accordingly, there lies a need to address the above-mentioned limitations and provide an improved method for operating a seeker of anti-tank guided missiles (ATGMs).
SUMMARY
[0005] This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention. This summary is neither intended to identify essential inventive concepts of the invention nor is it intended for determining the scope of the invention.
[0006] According to one embodiment of the present disclosure, disclosed herein is a method for operating a seeker of an anti-tank guided missile (ATGM). The method includes identifying one or more targets within a field of view (FOV) of the seeker from an infrared (IR) based image data associated with the one or more targets within the FOV of the seeker. The method further includes highlighting the one or more identified targets with one or more visual cues, and a probability score corresponding to each of the highlighted one or more targets. The method further includes activating a mid-course tracking operation to maintain an ATGM on a specific trajectory towards a locked target when a count of a number of pixels in an IR-based image data corresponding to the locked target is greater than a first threshold. Further, the method includes identifying an aim point on a body of the locked target when the count of a number of pixels in the IR-based image data of the locked target is greater than a second threshold and the launched ATGM is maintained on the specific trajectory, the second threshold being greater than the first threshold. Finally, the method includes navigating the launched ATGM to strike the locked target at the identified aim point.
[0007] According to another embodiment of the present disclosure, disclosed is a video tracking engine (VTE) for operating a seeker of an anti-tank guided missile (ATGM). The VTE comprises a target locking unit configured to identify one or more targets within a field of view (FOV) of the seeker from an infrared (IR) based image data associated with the one or more targets within the FOV of the seeker, highlight the one or more detected targets with one or more visual cues, and a probability score corresponding to each of the highlighted one or more targets, and lock a target based on a selection from the one or more detected targets. The VTE further comprises a tracking unit configured to determine whether a target has been locked by the target locking unit and perform a mid-course tracking operation to maintain the launched ATGM on a specific trajectory towards the locked target when a count of a number of pixels in an IR-based image data corresponding to the locked target is greater than a first threshold. Furthermore, the VTE comprises an aim point selection unit configured to identify an aim point on a body of the locked target when the count of a number of pixels in the IR-based image data of the locked target is greater than a second threshold and the launched ATGM is maintained on the specific trajectory, the second threshold being greater than the first threshold.
[0008] According to another embodiment of the present disclosure, disclosed is an anti-tank guided missile (ATGM) for striking a target, the ATGM comprising a seeker configured to identify one or more targets within a field of view (FOV) of the seeker from an infrared (IR) based image data associated with the one or more targets within the FOV of the seeker. Further, the seeker is configured to highlight the one or more detected targets with one or more visual cues, and a probability score corresponding to each of the highlighted one or more targets and activate a mid-course tracking operation to maintain an ATGM, launched toward a locked target selected from the one or more highlighted targets, on a specific trajectory towards the locked target when a count of a number of pixels in an IR-based image data corresponding to the locked target is greater than a first threshold. The seeker is further configured to identify an aim point on a body of the locked target when the count of the number of pixels in the IR-based image data of the locked target is greater than a second threshold and the launched ATGM is maintained on the specific trajectory, the second threshold being greater than the first threshold, and navigate the launched ATGM to strike the locked target at the identified aim point.
[0009] To further clarify the advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which are illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail in the accompanying drawings.
BRIEF DESCRIPTION OF THE DRAWINGS
[0010] These and other features, aspects, and advantages of the present invention will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:
[0011] Figure 1 is a block diagram depicting an anti-tank guided missile including an AI-enabled seeker, according to an embodiment of the present disclosure;
[0012] Figure 2 is a block diagram depicting the seeker and components thereof, according to an embodiment of the present disclosure;
[0013] Figure 3 is a block diagram depicting the modules of the VTE, according to an embodiment of the present disclosure;
[0014] Figure 4 is a flow diagram depicting a workflow of the ATLF, according to an embodiment of the present disclosure;
[0015] Figures 5a and 5b are pictorial representations of highlighted targets by the ATLF, according to an embodiment of the present disclosure;
[0016] Figure 6 is a flow diagram depicting a workflow of the MCT, according to an embodiment of the present disclosure;
[0017] Figures 7a and 7b are pictorial representations of the FOV of the seeker when MCT 303 is triggered, according to an embodiment of the present disclosure;
[0018] Figure 8 is a flow diagram depicting vulnerable aim point selection by the VAPS, according to an embodiment of the present disclosure;
[0019] Figures 9a and 9b are pictorial representations of the vulnerable aim point selection by the VAPS, according to an embodiment of the present disclosure; and
[0020] Figure 10 is a block diagram depicting the method for operating a seeker of an anti-tank guided missile (ATGM), according to an embodiment of the present disclosure.
[0021] Further, skilled artisans will appreciate those elements in the drawings are illustrated for simplicity and may not have necessarily been drawn to scale. For example, the flow charts illustrate the method in terms of the most prominent steps involved to help to improve understanding of aspects of the present invention. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present invention so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.
DETAILED DESCRIPTION
[0022] For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the embodiment illustrated in the drawings and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the invention is thereby intended, such alterations and further modifications in the illustrated system, and such further applications of the principles of the invention as illustrated therein being contemplated as would normally occur to one skilled in the art to which the invention relates.
[0023] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are explanatory of the invention and are not intended to be restrictive thereof.
[0024] Reference throughout this specification to “an aspect”, “another aspect” or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, appearances of the phrase “in an embodiment”, “in one embodiment”, “in another embodiment”, and similar language throughout this specification may but do not necessarily, all refer to the same embodiment.
[0025] The terms “comprise”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such process or method. Similarly, one or more devices or sub-systems or elements or structures or components proceeded by “comprises... a” does not, without more constraints, preclude the existence of other devices or other sub-systems or other elements or other structures or other components or additional devices or additional sub-systems or additional elements or additional structures or additional components.
[0026] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. Also, the various embodiments described herein are not necessarily mutually exclusive, as some embodiments can be combined with one or more other embodiments to form new embodiments. The term “or” as used herein, refers to a non-exclusive or unless otherwise indicated. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein can be practiced and to further enable those skilled in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
[0027] As is traditional in the field, embodiments may be described and illustrated in terms of blocks that carry out a described function or functions. These blocks, which may be referred to herein as units or modules or the like, are physically implemented by analog or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware and software. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like. The circuits constituting a block may be implemented by dedicated hardware, by a processor (e.g., one or more programmed microprocessors and associated circuitry), or by a combination of dedicated hardware to perform some functions of the block and a processor to perform other functions of the block. Each block of the embodiments may be physically separated into two or more interacting and discrete blocks without departing from the scope of the invention. Likewise, the blocks of the embodiments may be physically combined into more complex blocks without departing from the scope of the invention.
[0028] The accompanying drawings are used to help easily understand various technical features and it should be understood that the embodiments presented herein are not limited by the accompanying drawings. As such, the present disclosure should be construed to extend to any alterations, equivalents, and substitutes in addition to those which are particularly set out in the accompanying drawings. Although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are generally only used to distinguish one element from another.
[0029] An object of the present disclosure is to provide an artificial intelligence (AI) enabled seeker application for anti-tank guided missiles (ATGMs). Another object of the present disclosure is to provide an AI-enabled video tracking engine (VTE) for target tracking purposes. The VTE may utilize low-latency memory-mapped interfaces for connecting with both visual and infrared (IR) imaging devices.
[0030] Figure 1 is a block diagram 100 depicting an ATGM 101 including an AI-enabled seeker 103, according to an embodiment of the present disclosure. The AI-enabled seeker 103 may be installed towards a front portion of the ATGM 101. Other components of the ATGM 101, such as but not limited to on board processor (OBP) 105, telemetry 107, and actuator control unit (ACU) 109 may be positioned in the ATGM 101 adjacent to the AI-enabled seeker 103. For the sake of brevity, the term ‘AI-enabled seeker’ may be used interchangeably with the term ‘seeker’. Further, the term ‘ATGM’ 101 may be used interchangeably with the term ‘missile’. The seeker 103 may operate with the aid of various components, as described in conjunction with Figure 2. The seeker output may comprise line of sights rates which serve as input to OBP which in turn directs the ACU to provide fin deflections that maneuver missile towards target. The telemetry section is utilised to provide in-flight data parameters for monitoring.
[0031] Figure 2 is a block diagram depicting the seeker 103 and components thereof, according to an embodiment of the present disclosure. The seeker 103 may be an embedded system consisting of a video tracker engine (VTE) 201, one or a plurality of processors 209, an infra-red (IR) imager 211, an inertial measurement unit (IMU) 213, control systems 215, memory 217, encoders 221, and power supply system 223.
[0032] The VTE 201 comprises a pre-processing unit 203, modules 205, and post-processing unit 207. The pre-processing unit 203 may be configured to improve the quality of IR-based images captured from the IR imager 211 using methods such as contrast enhancement, noise adjustment, intensity transformations, smoothening, sharpening, and resizing images. The pre-processing unit 203 may also be configured to improve variance in a dataset associated with a trained AI-based model 219 to develop a robust model using predefined augmentation techniques like random scaling, cropping, flipping, rotation, random erase, cutout, mosaic, hide-and-seek, and grid mask. The modules 205 of the VTE perform the crucial operation of the seeker 103, i.e., to track a target and efficiently navigate the ATGM 101 towards the target. The post-processing unit 207 may be configured to improve the quality of the AI-based model 219 predictions by applying techniques like non-maximal suppression to the output of the AI-based model 219.
[0033] The one or a plurality of processors 209 may be a general-purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, a graphics-only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), and/or an AI-dedicated processor such as a neural processing unit (NPU). The GPU may be configured to process IR-based image data captured from the IR imager 211. The plurality of processors 209 may control the processing of the input IR-based image data in accordance with a predefined operating rule or artificial intelligence (AI) based model 219 stored in the non-volatile memory and the volatile memory, i.e., memory 217. The predefined operating rule or AI-based model 219 is provided through training or learning. In an embodiment of the present disclosure, the AI based model 219 may be trained using pre-defined neural network architectures such as but not limited to, darknet, visual geometry group (VGG), Res-Net, Google Net, spatial pyramid pooling (SPP), feature pyramid network (FPN), Pan-sharpening framework (PAN), radial basis function (RFB), you only look once (YOLO), single-shot detector (SSD ), region-based convolutional neural network (RCNN), and Retina Net. The pre-processing operations of the pre-processing unit 203 may be performed before training the AI-based model 219.
[0034] The memory 217 may include any non-transitory computer-readable medium known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read-only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. The memory 217 may also comprise the AI-based model 219.
[0035] The IMU 213 may be configured to track and locate a target or object of interest. The IMU 213 within the seeker 103 may include a plurality of sensors for measuring various aspects of motion and orientation of the ATGM 101. The various aspects of motion and orientation may include but are not limited to, acceleration, angular velocity, and magnetic field strength. The plurality of sensors may include but are not limited to, accelerometers, gyroscopes, and magnetometers. The control system 215 may include a digital signal controller (DSC) for providing necessary articulation to an electro-optical (EO) payload on the gimbal. The DSC may be a part of control system and the EO payload may refer to the onboard thermal and visual camera. The encoder 221, may be configured to provide angle information on the gimbal system of AI enabled seeker. In an exemplary embodiment of the present disclosure, the VTE may utilize a hardware-accelerated H.264 encoders for transmitting compressed telemetry stream The telemetry stream is sent by AI enabled seeker comprising of video stream as acquired by visual/infrared camera of AI enabled seeker The outgoing stream is sent post compression of H.264 algorithm on an interface circuitry including serial interfaces using Universal asynchronous receiver-transmitter (UART) protocol. Besides the components described herein, the AI seeker 103 may also comprise other components that perform functions that are known to a person skilled in the art. Hence, a description of such components is not provided for the sake of brevity. The modules 205 are now described in conjunction with Figure 3 below.
[0036] Figure 3 is a block diagram 300 depicting the modules 205 of the VTE 201, according to an embodiment of the present disclosure. The modules 205 perform the functions that enable the AI features of the VTE 201. The modules 205 may include an AI-assisted target lock feature (ATLF) module 301, a mid-course tracking (MCT) module 303, and a vulnerable aim point selection (VAPS) module 305. The ATLF 301 may be configured to highlight one or more probable targets within the field of view (FOV) of the seeker 103 and is described in detail in conjunction with Figures 4, 5a, and 5b. The MCT 303 may be configured to maintain the seeker 103 on a trajectory towards a locked target out of the one or more highlighted targets and is described in detail in conjunction with Figures 6, 7a, and 7b. The VAPS 305 may be configured to identify one or more suitable aim points on the locked target and is described in detail in conjunction with Figures 8, 9a, and 9b. Each of the ATLF 301, MCT 303, and VAPS 305 address and provide solutions to individual problems in the existing techniques as described in detail below.
[0037] Conventional seeker applications require an operator’s input for acquiring a target for engaging the ATGM 101. Further, such seeker applications have rudimentary signal processing software wherein fluctuations in target, background signatures, occlusions, countermeasures, and evasive tactics are not accounted for due to the unavailability of sufficient computing power. Furthermore, difficult terrain, adverse atmospheric conditions, and limitations of an optical system often lead to unsuccessful target interception due to errors in acquiring correct targets. Hence, according to an embodiment, the present disclosure discloses the ATLF 301 for the seeker 103 wherein probable targets within the FOV of the seeker 103 are highlighted.
[0038] Figure 4 is a flow diagram 400 depicting a workflow of the ATLF 301, according to an embodiment of the present disclosure. Firstly, at step 401, IR-based image data may be obtained from the memory of the seeker 103, wherein the IR-based image data may comprise images, videos, or both. The IR-based image data may correspond to the FOV of the seeker 103, wherein the FOV may include one or more targets to be attacked by the ATGM 101. Thereafter, at step 403, frame-by-frame segmentation may be performed on the obtained IR-based image data resulting in a set of segmented frames. The frame-by-frame segmentation may be performed based on one or more segmentation techniques, as would be apparent to a skilled person in view of the present disclosure, and therefore, is not described herein for the sake of brevity. Thereafter, at step 405, visual cues may be overlaid on the set of segmented frames to highlight one or more targets in the FOV of the seeker 103. In an embodiment, color-coded visual cues may be overlaid. The highlighted portions of the segmented frames may be accompanied by a bounding box that depicts a probability score of the ATLF 301 in ascertaining the target. In an embodiment, the probability score can be expressed in either probabilistic or percentage terms. For example, a higher probability score than a predefined threshold probability score indicates a high probability of the highlighted target in the FOV being a correct target. The segmented IR-based image data frames with highlighted targets may correspond to encoded IR-based image data. Thereafter, encoded IR-based image data may be written to a memory, as depicted at step 407. Such visual cues may assist an operator of the ATGM 101 in selecting a target. In an embodiment, the ATLF 301 may assist the operator in acquiring correct targets of size, for example, 2.5 x 2.3 m2 at ranges of 200 m to 2500 m irrespective of battlefield conditions. Based on the operator’s selection, a target may be identified from the one or more highlighted targets, as depicted at step 409. Thereafter, at step 411, a centroid may be extracted on the identified target and written to the memory at step 413.
[0039] Further, the ATLF 301 may utilize a light-weight detector integrated with optimized image processing techniques, i.e., custom object detector, adaptive template matching (ATM), and histogram of gradients (HOG) for low-latency tracking framework to account for rapid modifications in the size of the identified target due to continuous ATGM progression towards the identified target. In an embodiment, ATLF 301 may be optimized to run at 60 frames per second (FPS) and a satisfactory mean average precision (MAP) scores. Exemplary scenarios depicting the operation of the ATLF 301 are described in conjunction with Figures 5a and 5b.
[0040] Figures 5a and 5b are pictorial representations of highlighted targets by the ATLF, according to an embodiment of the present disclosure. As shown in Figures 5a and 5b, one or more targets may be identified with different probability scores. For example, as shown in Figure 5a, a target is identified and highlighted with a visual cue indicating a probability score of the identified target. For example, the target may be identified with a probability score of 0.23 in Figure 5a. In an embodiment, the visual cue may be color-coded, for example, blue. Similarly, as shown in Figure 5b, a target may be identified and highlighted with a visual cue indicating a probability score of 0.10. In an embodiment, visual cues with higher probability scores may be color-coded with a different color from the color of the visual cues with lower probability scores. For example, the identified target shown in Figure 5b has a higher probability score than that of the target identified in Figure 5a and may be color-coded with a different color than the color of the visual cue indicated in Figure 5a. For example, the visual cue shown in Figure 5b may be color-coded as pink. Color-coded visual cues may provide visual indications of the probability score of the highlighted targets to the operator, thereby assisting the operator in making prompt decisions in selecting a suitable target. Therefore, the ATLF 301 may provide the capability to identify and highlight probable targets within the FOV of the seeker 103 with color-coded visual cues. Based on the operator’s selection, one of the highlighted targets may be identified and engaged by the ATGM 101. However, the launched ATGM 101 progressing toward the locked (i.e., identified) target may be required to maintain a trajectory toward the locked target. Therefore, as the ATGM 101 attains a height where the locked target is more clearly visible as compared to the visibility of the locked target at the time of launch of the ATGM 101, the MCT 303 may be triggered as described in detail in conjunction with Figure 6 below.
[0041] A majority of the existing missile systems include electro-optical (EO) seekers and require the operator's input for target lock for tracking purposes before the missile launch. These systems are often referred to as Lock on before Launch (LOBL) weapon systems. As the missile guides itself towards the locked target, based on the velocity profile and trajectory, the available scenery in the FOV of the seeker changes dynamically at a high rate. Further, due to the motion of the missile and its approach toward the locked target, the geometry and aspect ratio of the locked target also changes at a high rate. Furthermore, targets generally employ evasive maneuvers as countermeasures to prevent themselves from being attacked or destroyed. Therefore, seekers must have effective mid-course tracking capabilities that are invariant to such changes in the target behavior. In addition to being invariant to target behavior, the mid-course tracking application may also be robust enough to prevent target switch in the case of identical or false targets presenting themselves within the FOV of the seeker after the initial lock and missile launch. Hence, in an embodiment, the present disclosure provides an AI-based MCT application for the seeker 103 of an ATGM 101.
[0042] Figure 6 is a flow diagram 600 depicting a workflow of the MCT 303, according to an embodiment of the present disclosure. Firstly, at step 601, IR-based image data may be read from the memory of the seeker 103, and simultaneously a target lock status may be determined, i.e., whether a target is locked or engaged. If the target is determined to be engaged at step 603, a number of pixels in IR-based image data of the locked target, as viewed from the ATGM 101 in progression and obtained from the IR imager 211, may be determined at step 605. However, if the target is not locked the workflow of the MCT 303 goes back to the step 601. When the determined number of pixels is greater than the first predefined threshold, the MCT 303 may be triggered. For example, as shown at step 607, the first predefined threshold may be 100. Therefore, if the number of pixels determined at step 605 is greater than 100, the MCT 303 may be triggered at step 609. If the number of pixels are less than the first predefined threshold, the MCT workflow goes back to step 605. In an embodiment, the MCT 303 may be triggered once the seeker 103 detects a growth of the locked target from 20% to 70% of the image frame.
[0043] In an embodiment, the present disclosure discloses the MCT 303 which enables robust tracking that is invariant to one or more target evasive maneuvers including switching with false targets, and/or occlusion factors during the ATGM 101 motion towards the target and comes into effect from a mid-course stage of ATGM 101 flight towards the target. The robustness feature may be developed utilizing the AI-based model 219 training for the desired functionality. In an embodiment, like the ATLF 301, MCT 303 may also be optimized to run at 60 FPS and a satisfactory MAP score. Therefore, as shown in Figure 6, a robust target lock may be maintained at step 611, a centroid may be located on the locked target with an increased image frame at step 613, and the centroid may be written to the memory of the seeker at step 615. Exemplary scenarios depicting the operation of the MCT 303 is described in conjunction with Figures 7a and 7b.
[0044] Figures 7a and 7b are a pictorial representation of the FOV of the seeker 103 when MCT 303 is triggered, according to an embodiment of the present disclosure. As shown in Figures 7a and 7b, the locked targets are more clearly visible as compared to the locked targets visible at the time of the launch of the ATGM 101, as shown in Figures 5a and 5b. In other words, a greater number of pixels of the locked target are visible than the number of pixels of the locked target in Figures 5a and 5b. Therefore, the MCT 303 enables the seeker 103 to continue approaching the locked target despite any evasive maneuvers. In other words, the MCT 303 provides the capability to maintain a robust target lock despite target evasive maneuvers, occlusion factors, and/or false targets. As the ATGM 101, while maintaining the robust lock with MCT 303, closes in on the locked target, one or more vulnerable points may be selected on the locked target to aim and ensure the destruction of the locked target.
[0045] Selection of such vulnerable aim points is necessary to ensure high kill probability as many protection techniques may have been deployed on the targets such as steel armour plates, composite armor, and active protection systems for the protection of target vehicles and crew. Despite such protective measures, the targets still offer general vulnerable points. Some of the general vulnerable points offered by the targets may be:
- Suspension parts: the mobility of targets such as tanks depends upon the proper functioning of the suspension parts. The suspension parts may include a sprocket, an idler, wheels, and tracks. Such suspension parts may prove to be the most vulnerable.
- Rear part: rear parts of the target containing engine and gasoline tanks may be considered vulnerable points as penetrating such parts may disable and explode the target easily.
- The turret: the turret of a target is of particular importance as a vulnerable aim point as destruction of the same may effectively neutralize the target.
[0046] Accordingly, in an embodiment, the present disclosure discloses VAPS 305 for the seeker 103 application wherein a suitable aim point may be selected during a terminal phase of the missile flight. Such vulnerable aim points may be selected using the VAPS 305, as described in conjunction with Figure 8 below.
[0047] Figure 8 is a flow diagram 800 depicting vulnerable aim point selection by the VAPS 305, according to an embodiment of the present disclosure. When the ATGM 101 closes in, the range of the locked target from the sensors of the ATGM 101 becomes smaller. At such shorter distances, a full image of the locked target may be available, and the most vulnerable or damage-inflicting point on the locked target can be selected as a hit point for the ATGM 101. The VAPS 305 application of the seeker 103 enables the selection of a suitable aim point during the terminal phase of the missile flight based on prior AI-based training associated with general vulnerable points offered by the targets. In an embodiment, VAPS 305 may identify a suitable aim point in a target by distinguishing the explosive reactive armour (ERA) panels, turret, wheel tracks, and engine of the target during the terminal phase of ATGM flight. In an embodiment, the features of the VAPS 305 may be developed utilizing a combination of contrast limited adaptive histogram equalization (CLAHE) and a predefined neural network trained for performing real-time segmentation of the target. In an embodiment, like ATLF 301 and MCT 303, the VAPS 305 may also be optimized to run at 60 FPS and a satisfactory MAP score.
[0048] As shown in Figure 8, at step 801, the IR-based image data may be obtained from the memory of the seeker 103 and simultaneously whether a target is locked or engaged may be determined. Thereafter, at step 803, whether the MCT 303 is engaged is determined. If the MCT 303 is determined to be engaged, then at step 805, pixels in the current target frames as viewed from the seeker 103 may be counted. However, if the MCT 303 is not engaged, the VAPS 305 workflow goes back to step 801. The number of pixels must be greater than a second predefined threshold for the operation of the VAPS 305. For example, as shown in Figure 8, if the number of pixels is greater than 250 at step 807, the VAPS 305 may perform frame-by-frame segmentation at step 809. However, if the number of pixels are less than the second predefined threshold, the VAPS 305 workflow goes back to step 805. Thereafter, at step 811, geometric details may be extracted from the segmented frames. At step 813, the extracted geometrical details may be compared against target vulnerability information such as a vulnerability matrix. Thereafter, at step 815, based on the comparison, an aim point and a centroid on the locked target may be located. Finally, at step 817, the located centroid data may be written to the memory. Exemplary scenarios depicting the vulnerable aim point selection are described in conjunction with Figures 9a and 9b.
[0049] Figures 9a and 9b are pictorial representations of the vulnerable aim point selection by the VAPS 305, according to an embodiment of the present disclosure. As shown in Figures 10a and 10b, vulnerable points may be determined based on the portion of the locked target visible to the seeker 103. For example, in Figure 9a, wheel tracks visible from the side view of the locked target may be targeted, while in Figure 9b, when the front of the target is visible, one or more suspension parts such as front wheels may be targeted. Thus, the VAPS 305 module provides the capability to identify suitable vulnerable aim points on a locked target while distinguishing different parts of the locked target. The ATGM 101 may hit the locked target at the identified aim points, thereby ensuring a high kill probability. Hence, the present disclosure provides techniques for operating the seeker 103 of the ATGM 101 for achieving efficient and robust navigation of the ATGM 101 by the seeker 103. The method for operating the seeker 103 is described in detail in conjunction with Figure 10.
[0050] Figure 10 is a block diagram depicting the method 1000 for operating a seeker of an anti-tank guided missile (ATGM), according to an embodiment of the present disclosure. The method, at step 1001, may include identifying one or more targets within a field of view (FOV) of the seeker 103 from an infrared (IR) based image data associated with the one or more targets within the FOV of the seeker 103. According to an embodiment of the present disclosure, for identifying the one or more targets, IR signals associated with the FOV of the seeker 103 may be received and one or more optics corresponding to the received IR signals may be stabilized. Further, the IR-based image data associated with the FOV of the seeker based on a processing of the received IR signals and the one or more stabilized optics may be obtained and the one or more targets within the FOV of the seeker from the obtained IR-based image associated with the FOV of the seeker may be identified.
[0051] Thereafter, at step 1003, the method 1000 may include highlighting the one or more identified targets with one or more visual cues, and a probability score corresponding to each of the highlighted one or more targets. Thereafter, at step 1005, the method 1000 may include activating a mid-course tracking operation to maintain an ATGM, launched towards a locked target selected from the one or more highlighted targets, on a specific trajectory towards the locked target when a count of a number of pixels in an IR based image data corresponding to the locked target is greater than a first threshold. According to an embodiment of the present disclosure, for activating the mid-course tracking operation, a target to be locked may be identified based on a selection from the one or more highlighted targets for a launch of the ATGM towards the locked target, and the mid-course tracking operation may be activated for keeping the launched ATGM on its trajectory toward the locked target. According to an embodiment of the present disclosure, activating the mid-course tracking operation may comprise identifying an event associated with one or more evasive maneuvers performed by the locked target and steering, by the seeker, the launched ATGM towards the locked target in response to the identified event.
[0052] Thereafter, at step 1007, the method 1000 may include identifying an aim point on a body of the locked target when the count of a number of pixels in the IR-based image data of the locked target is greater than a second threshold and the launched ATGM is maintained on the specific trajectory, the second threshold being greater than the first threshold. According to an embodiment of the present disclosure, identifying the aim point on the body of the locked target may comprise performing a frame-by-frame segmentation of the IR-based image data associated with the locked target, extracting, from each frame of the segmented IR-based image data, geometrical details corresponding to different parts of the body of the locked target, comparing the extracted geometrical details with a target vulnerability information associated with one or more vulnerable points on the body of the locked target, and identifying the aim point on the body of the locked target based on a result of the comparison.
[0053] Thereafter, at step 1009, the method 1000 may include determining a centroid of the identified aim point on the body of the locked target. Thereafter, at step 1011, the method 1000 may include navigating the launched ATGM to strike the locked target at the determined centroid of the aim point on the body of the locked target. According to an embodiment of the present disclosure, the method 1000 may include processing the IR-based image data, by the seeker of the ATGM, at a frame rate of at least 60ps and a mean average precision (MAP) being greater than a predefined threshold.
[0054] At least by virtue of the aforesaid, the present subject matter at least provides the following advantages:
[0055] Firstly, targets on a battlefield are correctly identified through the IR imager 211 of the seeker, which can lead to smaller aperture optics in future variants. Secondly, the robust tracking capability of the seeker during flight is enabled by providing a capability of regaining target lock if lost due to occlusions, invariance to target evasive maneuvers such as crisscrossing and smoke grenades, and invariance to false targets such as already destroyed main battle tanks (MBTs). Besides providing greater lethality and single shot kill probability (SSKP), the method disclosed in the present subject matter provide better chances of incapacitating maneuverable armoured personnel carriers (APV) targets. Finally, the VTE 201 may be optimized to complete the processing within a short span of time. For example, the VTE 201 may complete the target identification and ATGM navigation within 20ms.
[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one ordinary skilled in the art to which this invention belongs. The system, methods, and examples provided herein are illustrative only and not intended to be limiting.
[0057] While specific language has been used to describe the present subject matter, any limitations arising on account thereto, are not intended. As would be apparent to a person in the art, various working modifications may be made to the method to implement the inventive concept as taught herein. The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment.
[0058] The embodiments disclosed herein can be implemented using at least one hardware device and performing network management functions to control the elements.
[0059] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the scope of the embodiments as described herein.
,CLAIMS:1. A method for operating a seeker (101) of an anti-tank guided missile (ATGM) (101), the method comprising:
identifying one or more targets within a field of view (FOV) of the seeker (103) from an infrared (IR) based image data associated with the one or more targets within the FOV of the seeker (103);
highlighting the one or more identified targets with one or more visual cues and a probability score corresponding to each of the highlighted one or more targets;
activating a mid-course tracking operation to maintain an ATGM (101), launched towards a locked target selected from the one or more highlighted targets, on a specific trajectory towards the locked target when a count of a number of pixels in the IR-based image data corresponding to the locked target is greater than a first threshold;
identifying an aim point on a body of the locked target when the count of a number of pixels in the IR-based image data of the locked target is greater than a second threshold and the launched ATGM (101) is maintained on the specific trajectory, the second threshold being greater than the first threshold; and
navigating the launched ATGM (101) to strike the locked target at the identified aim point.
2. The method as claimed in claim 1, wherein for identifying the one or more targets, the method comprises:
receiving IR signals associated with the FOV of the seeker (103);
stabilizing one or more optics corresponding to the received IR signals;
obtaining the IR-based image data associated with the FOV of the seeker (103) based on a processing of the received IR signals and the one or more stabilized optics; and
identifying the one or more targets within the FOV of the seeker (103) from the obtained IR-based image associated with the FOV of the seeker (103).
3. The method as claimed in claim 1, wherein for activating the mid-course tracking operation, the method comprises:
identifying a target to be locked based on a selection from the one or more highlighted targets for a launch of the ATGM (101) towards the locked target; and
activating the mid-course tracking operation for keeping the launched ATGM (101) on its trajectory toward the locked target.
4. The method as claimed in claim 1, wherein activating the mid-course tracking operation further comprises:
identifying an event associated with one or more evasive maneuvers performed by the locked target; and
steering, by the seeker (103), the launched ATGM (101) towards the locked target in response to the identified event.
5. The method as claimed in claim 1, wherein identifying the aim point on the body of the locked target comprises:
performing a frame-by-frame segmentation of the IR-based image data associated with the locked target;
extracting, from each frame of the segmented IR-based image data, geometrical details corresponding to different parts of the body of the locked target;
comparing the extracted geometrical details with a target vulnerability information associated with one or more vulnerable points on the body of the locked target; and
identifying the aim point on the body of the locked target based on a result of the comparison.
6. The method as claimed in claim 1, wherein prior to navigating the launched ATGM (101) to strike the locked target, the method comprises:
determining a centroid of the identified aim point on the body of the locked target; and
navigating the launched ATGM (101) to strike the locked target at the determined centroid of the aim point on the body of the locked target.
7. The method as claimed in claim 1, further comprising processing the IR-based image data, by the seeker (103) of the ATGM (101), at a frame rate of at least 60fps and a mean average precision (MAP) being greater than a predefined threshold.
8. A video tracking engine (VTE) (201) for operating a seeker (103) of an anti-tank guided missile (ATGM) (101), the VTE (201) comprising:
a target locking unit configured to:
identify one or more targets within a field of view (FOV) of the seeker (103) from an infrared (IR) based image data associated with the one or more targets within the FOV of the seeker (103);
highlight the one or more detected targets with one or more visual cues, and a probability score corresponding to each of the highlighted one or more targets; and
locking a target based on a selection from the one or more detected targets;
a tracking unit configured to:
determine whether a target has been locked by the target locking unit; and
perform, upon determining that a target has been locked by the target locking unit, a mid-course tracking operation to maintain the launched ATGM (101) on a specific trajectory towards the locked target when a count of a number of pixels in an IR-based image data corresponding to the locked target is greater than a first threshold; and
an aim point selection unit configured to:
identify an aim point on a body of the locked target when the count of a number of pixels in the IR-based image data of the locked target is greater than a second threshold and the launched ATGM (101) is maintained on the specific trajectory, the second threshold being greater than the first threshold.
9. The video tracking engine (201) as claimed in claim 8, wherein for identifying the one or more targets, the target locking unit is configured to:
receive IR signals associated with the FOV of the seeker (103);
stabilize one or more optics corresponding to the received IR signals;
obtain the IR-based image data associated with the FOV of the seeker (103) based on a processing of the received IR signals and the one or more stabilized optics; and
identify the one or more targets within the FOV of the seeker (103) from the obtained IR-based image data associated with the FOV of the seeker (103).
10. The video tracking engine (201) as claimed in claim 8, wherein for performing the mid-course tracking operation, the tracking unit is configured to:
identify a target to be locked based on a selection from the one or more highlighted targets for a launch of the ATGM (101) towards the locked target; and
perform the mid-course tracking operation for keeping the launched ATGM (101) on its trajectory toward the locked target.
11. The video tracking engine (201) as claimed in claim 8, wherein the tracking unit is further configured to:
identify an event associated with one or more evasive maneuvers performed by the locked target; and
steer by the seeker (103), the launched ATGM (101) towards the locked target in response to the identified event.
12. The video tracking engine (201) as claimed in claim 8, wherein to identify the aim point on the body of the locked target, aim point selection unit is configured to:
perform a frame-by-frame segmentation of the IR-based image data associated with the locked target;
extract, from each frame of the segmented IR-based image data, geometrical details corresponding to different parts of the body of the locked target;
compare the extracted geometrical details with a target vulnerability information associated with one or more vulnerable points on the body of the locked target; and
identify the aim point on the body of the locked target based on a result of the comparison.
13. The video tracking engine (201) as claimed in claim 8, wherein the aim point selection unit is further configured to:
determine a centroid of the identified aim point on the body of the locked target; and
navigate the launched ATGM (101) to strike the locked target at the determined centroid of the aim point on the body of the locked target.
14. The video tracking engine (201) as claimed in claim 8, wherein each of the target locking unit, tracking unit, and aim point selection unit is configured to process the IR-based image data, at a frame rate of at least 60fps and a mean average precision (MAP) being greater than a predefined threshold.
15. An anti-tank guided missile (ATGM) (101) for striking a target, the ATGM (101) comprising:
a seeker (103) configured to:
identify one or more targets within a field of view (FOV) of the seeker (103) from an infrared (IR) based image data associated with the one or more targets within the FOV of the seeker (103);
highlight the one or more detected targets with one or more visual cues, and a probability score corresponding to each of the highlighted one or more targets;
activate a mid-course tracking operation to maintain an ATGM (101), launched towards a locked target selected from the one or more highlighted targets, on a specific trajectory towards the locked target when a count of a number of pixels in an IR-based image data corresponding to the locked target is greater than a first threshold;
identify an aim point on a body of the locked target when the count of the number of pixels in the IR-based image data of the locked target is greater than a second threshold and the launched ATGM (101) is maintained on the specific trajectory, the second threshold being greater than the first threshold; and
navigate the launched ATGM (101) to strike the locked target at the identified aim point.