Description:TECHNICAL FIELD
[0001] The present disclosure relates, in general, to surveillance networks, and more specifically, relates to the system and methods for automatic multi-mode tracking of land-based targets.

BACKGROUND
[0002] Due to the rapid growth of sensing and communication technologies, multi-layer sensor-based security systems are becoming a promising factor for getting accurate detections of targets or events. Generally, security systems are equipped with a variety of sensors such as radar, underground sensors (point & optical fibre cables (OFC) based sensors), electro-optic sensors (fix and pan, tilt, zoom cameras), and electric & laser fences. These sensors form multi-level sensing of various targets or events like animals, vehicles, and humans coming towards the target surveillance area. Detection sense by the sensors is transferred to a centralized PTZ-tracking application (PTA) for fusion analysis of sensed information for effective surveillance & decision-making. PTA also involves automated & real-time analysis of incoming information for detection of anomalies, identification of suspicious behaviour, and generation of alerts & commands to surveillance electro-optic devices particularly PTZ-cameras for better and precise monitoring.
[0003] In the case of a security system, the surveillance area is divided into different zones, categorized as risk & normal zones. Each zone is covered by various sensor layers. PTZ-camera is one of the critical elements among multiple sensor layers where the PTZ-camera tracks the target near the periphery of the surveillance area in the range i.e., max up to 300 meters.
[0004] An example of a system and method for tracking moving objects in a scene is described in EP3419284A1. This technique suggests tracking camera-monitored events that could be any objects or specific types of objects. The proposed approach extracts coordinate from images either from a single camera or various views of cameras that can be done manually or automatically in the system. Another example is recited in a patent USOO5434617A, a moving object is tracked within the field of view of an electronic camera system, which is illustratively composed of a fixed spotting camera and a movable tracking camera. In the methodology, images are sequentially generated by the electronic camera system and then stored as pixel representations during each of the scan intervals of the camera system.
[0005] Yet another example is recited in a patent USOO8929603B1 that explains the method of autonomous lock-on target tracking with a geospatial aware PTZ camera that works on the frame-differencing operation to detect the object or target. The invention focuses to lock on target tracking without compromising desired resolution. However, the existing arts suffer from limitations that include are as follows:
• PTZ-camera tracking is generally done on single sensor-based inputs. Lack of object detection by a variety of sensors.
• Lack of tracking multiple objects by PTZ-camera.
• Lack to manage if multiple objects are arrived for tracking by a single PTZ camera at a time.
• Lack of manual overriding condition for any specific object among multiple tracked objects by a single PTZ camera.
• Lack to support for geo-location-based tracking without image analysis. Discussed prior arts consider all the data generated by the camera without filtering that may lead to inefficient object tracking and unnecessary engagement to PTZ camera.
• Lack of mentioning any capability of handing-taking over feature between PTZ-cameras.
• Lack to maintain PTZ-camera bore sight view for co-located targets.
[0006] There are various challenges with land-based detected targets or events tracking such as short life span, inaccuracy in the received geo-position information, false alarms, and the large volume of targets or events detections in multi-layer sensor deployments. Therefore, it is desired to overcome the drawbacks, shortcomings, and limitations associated with existing solutions, and develop a tracking system and method for land-based detected targets and events through PTZ-cameras for sensed information by multiple layers of sensors.

OBJECTS OF THE PRESENT DISCLOSURE
[0007] An object of the present disclosure relates, in general, to surveillance networks, and more specifically, relates to systems and methods for automatic multi-mode tracking of land-based targets.
[0008] Another object of the present disclosure is to provide a system for automatic multi-mode PTZ-camera tracking of targets/events detected by multi-sensors detection i.e., radar detections, unattended ground sensors (UGS) events, fixed camera events, and smart fences events, for PTZ-camera tracking.
[0009] Another object of the present disclosure is to provide a system having a PTZ-camera tracking mechanism that covers scenarios for tracking multiple objects by the PTZ-camera at a time by assigning priority values. Each detected target/event is weighted to calculated priority values from an algorithm.
[0010] Another object of the present disclosure is to provide a system of manual overriding conditions to track specific objects among multiple tracked objects by a single PTZ camera.
[0011] Another object of the present disclosure is to provide a system that enables the PTZ-camera tracking method in an automatic multi-mode tracking that manages image analysis and geo-position, where the system manages the tracking of every type of target detected by multiple types of sensors.
[0012] Another object of the present disclosure is to provide an interface for manual overriding to hook specific targets or events among a list of multiple tracking objects.
[0013] Yet another object of the present disclosure is to provide a PTZ-camera tracking application that applies specific algorithms to maintain PTZ-camera bore sight view for co-located targets.

SUMMARY
[0014] The present disclosure relates in general, to surveillance networks, and more specifically, relates to the system and methods for automatic multi-mode tracking of land-based targets. The main objective of the present disclosure is to overcome the drawback, limitations, and shortcomings of the existing system and solution, by providing a system for automatic multi-mode tracking of land-based targets in a multi-sensor network.
[0015] The present disclosure provides the set of sensors deployed across the surveillance area to detect a set of target data. The set of sensors selected from radars, underground sensors, fix cameras, electric and laser fences, and any combination thereof. The tracker device of an image-capturing unit is coupled to the set of sensors. The tracker device of the image-capturing unit, on receipt of the set of target data, is configured to operate in manual mode and auto mode. In an exemplary embodiment, the image-capturing unit is the PTZ camera.
[0016] The processor operatively coupled to the tracker device of the image capturing unit, the processor configured to receive, from the set of sensors, the set of target data, assign priority to each detected target data to determine the highest priority. Further, the processor can determine the geo-position information of the received target data, wherein geo-position information of the received target data is converted into the pan, tilt and zoom (PTZ) values. The processor can operate, upon receipt of the pan, tilt and zoom values, the image capturing unit in the manual mode to track the intrusion target position. The processor can capture, upon the absence of the geo-position information of the received target, video-based information of the received target data; and operate, upon receipt of the video-based information, the image capturing unit in the auto mode to track intrusion target position.
[0017] Various objects, features, aspects, and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent like components.

BRIEF DESCRIPTION OF THE DRAWINGS
[0018] The following drawings form part of the present specification and are included to further illustrate aspects of the present disclosure. The disclosure may be better understood by reference to the drawings in combination with the detailed description of the specific embodiments presented herein.
[0019] FIG. 1 illustrates an exemplary view of a multi-sensors security surveillance network, in accordance with an embodiment of the present disclosure.
[0020] FIG. 2 illustrates a top-level system architecture of PTZ-tracking for land-based targets or events, in accordance with an embodiment of the present disclosure.
[0021] FIG. 3 illustrates a flowchart of a method of PTZ-tracking in the multi-sensor network, in accordance with an embodiment of the present disclosure.
[0022] FIG. 4 illustrates an exemplary view of the geo-position-based PTZ tracking approach, in accordance with an embodiment of the present disclosure.
[0023] FIG. 5 illustrates an exemplary view of the flow chart of a method for automatic multi-mode tracking of land-based targets in the multi-sensor network, in accordance with an embodiment of the present disclosure.

DETAILED DESCRIPTION
[0024] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such detail as to clearly communicate the disclosure. If the specification states a component or feature “may”, “can”, “could”, or “might” be included or have a characteristic, that particular component or feature is not required to be included or have the characteristic.
[0025] As used in the description herein and throughout the claims that follow, the meaning of “a,” “an,” and “the” includes plural reference unless the context clearly dictates otherwise. Also, as used in the description herein, the meaning of “in” includes “in” and “on” unless the context clearly dictates otherwise.
[0026] The present disclosure relates, to the surveillance network, and more specifically, relates to the system and method for automatic multi-mode tracking of land-based targets. The system and method proposed in the given invention relate to the system involving the automatic multi-mode tracking method for land-based targets and events in the context of intrusions, attacks, or any type of suspicious activities across the surveillance area based on the received inputs from various types of deployed sensors such as radars, unattended ground sensors (UGS), electric and laser fences and fixed cameras. Surveillance security systems generally use only one mode tracking method and that is a video analytic-based PTZ-camera tracking.
[0027] The proposed disclosure discusses multi-mode tracking methods by a PTZ camera i.e., geo-position-based tracking and video analytic-based tracking. The geo-position-based tracking algorithm mathematically maps tracked object position (lat, long) into pan, tilt & zoom value and further pass directly this value to PTZ-tracker hardware. On receiving this input, the PTZ camera moves to track the intrusion target position. This method is entirely different from the image analytic tracking mechanism. However, the tracking method is also capable to switch on another tracking mode as per received inputs from multiple–sensors that are purely based on video analytic mechanism. The PTZ camera works in two ways i.e., arm mode and disarm mode. Geo-position based tracking method works when the PTZ camera is in disarm mode and the video analytic-based tracking mechanism works in the arm mode of the PTZ camera.
[0028] The geo-position-based tracking method creates various virtual tracking polygon areas across the PTZ camera within the tracking limit range. The value of pan and tilt may remain the same for an object till the object’s position within a virtual polygon area. That helps the system to avoid unnecessary PTZ-tracker movement for every position change of tracked object and only the PTZ-camera zoom value is adjusted on need. Also, this method is capable to cover multiple objects together with maintained bore sight of the PTZ camera.
[0029] The proposed tracking method also adds toggling sequence capability for a PTZ camera with a pre-defined time period to manage concurrent multiple threats or events. As well as manual override feature is provided to break toggling sequence to lock the PTZ camera for a single tracking. As well as PTZ-camera handing taking over capability is also provided to make continuity in the tracking mechanism in both tracking modes. This way proposed invention is able to manage all scopes of tracking scenarios and definitely it is a recommended solution for any perimeter security system.
[0030] The advantages achieved by the system of the present disclosure can be clear from the embodiments provided herein. The proposed disclosure discusses the system and methods for automatic multi-mode PTZ-camera tracking of targets/events detected by multi-sensors detection i.e., radar detections, UGS events, fixed camera events, and smart fences events, for PTZ-camera tracking. The proposed PTZ-camera tracking mechanism covers the scenario for tracking multiple objects by the PTZ-camera at a time by assigning priority values. Each detected target/event is weighted to calculated priority values from an algorithm. The system provides a method of manually overriding conditions to track specific objects among multiple tracked objects by a single PTZ camera. The PTZ-camera tracking method is an automatic multi-mode tracking that manages image analysis and geo-position based. Thereby, the system is able to manage to track every type of target detected by multiple types of sensors. The method provides an interface for manual overriding to hook specific targets or events among a list of multiple tracking objects. The PTZ-camera tracking application applies specific algorithms to maintain PTZ-camera bore sight view for co-located targets. The description of terms and features related to the present disclosure shall be clear from the embodiments that are illustrated and described; however, the invention is not limited to these embodiments only. Numerous modifications, changes, variations, substitutions, and equivalents of the embodiments are possible within the scope of the present disclosure. Additionally, the invention can include other embodiments that are within the scope of the claims but are not described in detail with respect to the following description.
[0031] FIG. 1 illustrates an exemplary view of a multi-sensors security surveillance network, in accordance with an embodiment of the present disclosure.
[0032] Referring to FIG. 1, system 100 and the method for tracking targets and events in the multi-sensor network using PTZ-camera and its tracker device. Based on open and flexible architecture where the targets and events as detected by a variety of networked sensors like radars, underground sensors, fix cameras, and electric & laser fences deployed across the surveillance area.
[0033] The system 100 performs an automatic multi-mode tracking mechanism, multiple objects tracking at a time and maintains a PTZ-camera view for co-located targets.
[0034] Automatic Multi-Mode Tracking Mechanism:
a) geo-position-based tracking / manual mode: If the target or event has information about the detected geo-position, then the system does track on the basis of the received geo-position of the target. The image analytic concept is not required in tracking. Target Lat/Long is converted into pan, tilt & zoom values by a mathematical algorithm, that is passed to the PTZ-tracker device & PTZ-camera moves accordingly. At this time, the PTZ camera runs in the disarm mode that is known as the manual mode of the PTZ-camera.
b) Image analytic-based tracking/auto mode: If the received input from the sensor has no geo-location, the system starts a video-based tracking mechanism and PTZ-camera operates in arm mode which is known as the auto mode of the PTZ-camera.
[0035] Multiple Objects Tracking at a Time:
If the alert generation is from two or more sensors from different zone for a common PTZ camera 106 then a default sequence of toggling between the targets is performed by the PTZ with configurable time on the target, default 5 sec on each target to track multiple objects at a time. A manual override feature is also associated with this to break toggling and the operator can continue with desired target/event tracking only.
[0036] Maintain PTZ-camera view for co-located targets:
If alert generation from two or more sensors for the same area, then bore sight of the PTZ-camera 106 may be maintained as the centre of the endpoints without unnecessary toggling of the PTZ-camera. That means PTZ camera 106 may not change its pan & tilt value for covering more than one object if they are near around to each other.
[0037] There are various challenges with land-based detected targets or events tracking like it is short life span, inaccuracy in the received geo-position information, false alarms, and the large volume of targets or events detections in multi-layer sensor deployments. To overcome these mentioned challenges, the presented disclosure explains about tracking system and method for land-based detected targets and events.
[0038] The proposed method includes workflow of land-based target tracking through PTZ-cameras 106 for sensed information by multiple layers of sensors with the following concepts:
• To handle the in-accuracy of the received geo-position information, one of the segments of proposed method includes the division of the entire FOV into circular arcs of pre-defined configurable angular value where the geographical area covered by the arc is termed as sectors. Each sector is further categorized into smaller geographical areas that are further analysed to confirm the position of the detected target or event accurately.
• A sensor priority-based filtering mechanism is used for suppressing the false alarms from PTZ tracking because PTZ camera 106 tracks only the highest priority alarm in the system.
• The automated alarms suppression mechanism has the following filtering criteria to find out the critical threat in the system:
a) Target course-based filtering is based on the direction of the target coming towards or going away or moving in parallel with the target surveillance area.
b) Target severity-based filtering is decided on the basis of its distance from the target surveillance area boundary.
c) Event suppression based on the inner and outer periphery of the surveillance area
[0039] Real-time & automated tracking of detected targets or events in the system are done by PTZ-camera 106 that includes the following tracking methods and the system does context switching at run time on a demand basis:
[0040] Geo-position based tracking: PTZ camera 106 direction is moved towards the polygon area rather than focusing only on a single point location. PTZ slew-to-cue mechanism is applied for tracking if the target is detected by multiple sensors. In case alerts are detected in different zones then PTZ-camera 106 may toggle between both zones to focus detected events or targets with default toggling time periodicity. During the PTZ-camera 106 toggling, system 100 provides the manual interface to break toggling sequence and focus only on single object tracking. PTZ-tracker device 104 also plays an important role to move PTZ-camera 106 on its calculated pan, tilt & zoom value for detected targets or events.
[0041] Video analysis-based tracking: To start image analysis-based object tracking, PTZ tracking module gives “goto preset” command to PTZ-camera 106. PTZ-camera 106 goes to as per received “preset” number position. In this mode, automatically PTZ-camera 106 goes into video analysis-based tracking. This “preset” number must be pre-configured into the system as per detailed analysis of surveillance area environment.
[0042] Intelligent and centralized analysis of the incoming sensor input is done for the detection of anomalies, identification of suspicious behaviours and generation of alarms/alerts. As well as initiation of supportive commands to direct surveillance PTZ-camera 106 at the target location is given for précised & effective surveillance. This feature of the system helps the operator to take the right decision at right time.
[0043] The proposed disclosure discusses system and methods for automatic multi-mode PTZ-camera tracking of targets/events detected by multi-sensors detection i.e., radar detections, UGS events, fixed camera events, and smart fences events, for PTZ-camera tracking. The proposed PTZ-camera tracking mechanism covers the scenario for tracking multiple objects by the PTZ-camera 106 at a time by assigning priority values. Each detected target/event are weighted to calculated priority values from an algorithm.
[0044] The system provides a method of manually overriding conditions to track specific objects among multiple tracked objects by a single PTZ camera 106. The PTZ-camera 106 tracking method is an automatic multi-mode tracking that manages image analysis and geo-position based. Thereby, the system is able to manage to track of every type of target detected by multiple types of sensors. The method provides an interface for manual overriding to hook specific targets or events among list of multiple tracking objects. The PTZ-camera tracking application applies specific algorithms to maintain PTZ-camera bore sight view for co-located targets.
[0045] FIG. 2 illustrates top-level system architecture 200 of PTZ-tracking for land-based targets or events, in accordance with an embodiment of the present disclosure.
[0046] The deployed sensors 102 usually generate alerts at a very faster pace, flooding the intrusion detection system with a mixture of actual alerts and false alerts. To suppress false alerts in real-time, a technique based on the combination of accurate weight of multiple sensor contributions and severity of detected zone is used. The validity of a true threat is decided on the basis of the assigned highest priority value to the detected target and event.
[0047] In an embodiment, the set of sensors 102 deployed across the surveillance area to detect a set of target data. The set of sensors 102 selected from radars, underground sensors, fix cameras, electric and laser fences and any combination thereof. The tracker device 104 of an image-capturing unit 106 is coupled to the set of sensors 102, and the tracker device 104 of the image capturing unit, on receipt of the set of target data, is configured to operate in manual mode and auto mode. In an exemplary embodiment, the image capturing unit is the PTZ-camera 106.
[0048] The processor operatively coupled to the tracker device 104 of the image capturing unit, the processor 108 configured to receive, from the set of sensors 102, the set of target data, assign priority to each detected target data to determine the highest priority. Further, the processor 108 can determine the geo-position information of the received target data, wherein geo-position information of the received target data is converted into pan, tilt and zoom (PTZ) values. The processor can operate, upon receipt of the pan, tilt and zoom values, the image capturing unit in the manual mode to track the intrusion target position. The processor 108 can capture, upon the absence of the geo-position information of the received target, video-based information of the received target data; and operate, upon receipt of the video-based information, the image capturing unit in the auto mode to track intrusion target position.
[0049] The image-capturing unit 106 switches tracking mode based on received inputs from the set of sensors 102, wherein geo-position-based tracking is operated when the image-capturing unit is in manual mode and video analytic-based tracking is operated when the image-capturing unit is in auto mode. The PTZ-camera 106 tracks the target by using the computed pan, tilt and zoom value applied as input to the tracker device 104, where the computed PTZ values work on co-located multiple targets and the bore sight view of the PTZ-camera for co-located targets is maintained, wherein the PTZ is not changed for the tracked target till its position remains in same bore-sight.
[0050] The system provides system configurability for sensor priority, camera toggling span, and division of surveillance area into risk and normal zone, wherein interface configuration of the PTZ-camera is provided for its associated tracker device. The system is featured with the automated selection of operational PTZ cameras for day/night mode, wherein the IR-equipped camera is selected automatically for target tracking at night and vice-versa.
[0051] The PTZ-camera 106 track multiple objects having the same priority in the respective surveillance area using toggling sequence and is capable to break toggling sequence through a manual override feature by operator intervention. The system automatically selects the next suitable PTZ camera, if the object goes beyond the current PTZ camera range during tracking to maintain continuity in tracking.
[0052] FIG. 3 illustrates flowchart 300 of a method of PTZ-tracking in the multi-sensor network, in accordance with an embodiment of the present disclosure.
[0053] At block 302, the methodology constitutes the reception of sensor inputs in form of detected targets or events in the target surveillance environment from the deployed sensors. At block 304, the priority is assigned to each detected target or event on the basis of contribution from the sensors as per eq. (1).
Priority Value =𝑍𝑓∗Σ𝑆𝐶∗𝑃𝑖𝑁𝑖=1 ……………….. eq. (1)
where
Sc : Sensor contribution flag {1=Contribution & 0= No Contribution},
Pi : Priority Factor of detected sensor
Zf : Detection in SVL Zone factor
[0054] In this way, maximum sensor contribution shows confirmation of its true presence. A novel mechanism of assigning priorities to the detected targets in a multi-target environment is utilized in the proposed invention. In this mechanism, the surveillance zones of the system are divided into risk & normal zone with the associated weight factor as defined in Table-1.
S.No SVL Zone Type (Z) Weight Factor (f)
1 Normal SVL Zone 1
2 Risk SVL Zone 2
Table 1: SVL Zone Priority Table
[0055] At block 306, the configured sensors and surveillance zones in the system play a major role in priority assignment to tracked objects or events. Each configured sensors have its own priority factor in the system which is configured by the system administrator.
S.No Sensor type (S) Priority factor (P)
1 Radar 0.1
2 Camera 0.2
3 UVDS_Walking 0.3
4 UVDS_Digging 0.4
5 Drain 0.5
6 Electric Fence 0.6
Table 2: Sensor Priority Table
[0056] The system 100 i.e., the PTZ-target tracking model proposed to check the final priority value of the target/ event that is set in descending priority order of tracked object list. The system 100 also chooses a suitable day/night PTZ camera 106 on the basis of timestamping of the detected event or target. At block 308, the tracking methodology of the proposed invention constitutes a novel method for tracking land-based targets and/or events by best suited PTZ-camera 106. FIG. 3 shows the complete workflow of tracking methodology using PTZ-camera in dual mode i.e., auto and manual.
[0057] At block 312, in auto mode, the system sets the PTZ-camera tracking using video-based analytic mode that is done if the detected event or target has no information about its location. At block 316, the video management system (VMS) interface helps for tracking of target/event when PTZ camera is in auto mode.
[0058] At block 310, in manual mode, the system sets the PTZ-camera tracking using geo-position information, if the detected event has information about its geo-location exact point or area with +/- 20 meter proximity as shown in FIG. 4. At block 314, the PTZ-camera tracks the targets and/events by passing computed pan, tilt & zoom (PTZ) value to tracker device. These calculated values are able to work on co-located multiple targets. At block 318, the PTZ slew-to-cue mechanism is applied for tracking if the target is detected by multiple sensors.
[0059] FIG. 4 illustrates an exemplary view of the geo-position based PTZ tracking approach, in accordance with an embodiment of the present disclosure.
[0060] As depicted in FIG. 4, in manual mode, the system 100 sets the PTZ-camera tracking using geo position information, if the detected event has information about its geo-location exact point or area with +/- 20 meter proximity as shown in FIG. 4. PTZ-camera 106 tracks the targets and/events by passing computed pan, tilt & zoom value to tracker device 104. These calculated values are able to work on co-located multiple targets.
[0061] PTZ tracking is managed and controlled by the PTZ-tracker device 104. Mapping of the PTZ-tracker device 104 for each PTZ is utilised by the tracking application module. PTZ-tracker device 104 is responsible for rotating PTZ-camera 106 on computed pan, tilt & zoom values. PTZ-camera focuses target/event on the polygon area where the target or event is detected. In the proposed method, the PTZ-camera location is the centre of the circle and again divided into multiple co-centric circles in diameter. Multiple polygon areas across the PTZ-camera Field of View (FOV) have been obtained for tracking the targets or events like zone-1, zone-2 and zone-3. PTZ-camera 106 zoom level is managed separately for day and night cameras.
[0062] The computed PTZ values are sent to tracker device 104 of the designate PTZ-camera for the tracked object using the tracker interface module. The PTZ value shall not be changed for the tracked target till its position remains in the same sub-polygon. If the object goes beyond the PTZ-camera range during tracking, the system pick-up automatically the next suitable PTZ-camera 106 to maintain continuity in tracking.
[0063] If multiple objects are in the same priority in the tracking-queue, PTZ-camera 106 handles this scenario via toggling. The default toggling periodicity is kept as 5 Sec, i.e., the PTZ camera 106 can track one object or target for an interval of 5 sec before switching over to another. If the camera operator is interested to track only one of them, then the manual overriding feature is also provisioned in the proposed method to support this.
[0064] FIG. 5 illustrates an exemplary view of a flow chart of a method for automatic multi-mode tracking of land-based targets in the multi-sensor network, in accordance with an embodiment of the present disclosure.
[0065] Referring to FIG. 5, the method 500 includes at block 502, the set of sensors deployed across the surveillance area to detect a set of target data. At block 504, the tracker device of an image-capturing unit is coupled to the set of sensors, the tracker device of the image-capturing unit, on receipt of the set of target data, is configured to operate in manual mode and auto mode. At block 506, the processor can receive from the set of sensors the set of target data. At block 508, the processor assigns priority to each detected target data to determine the highest priority.
[0066] At block 510, the processor can determine the geo-position information of the received target data, wherein geo-position information of the received target data is converted into pan, tilt and zoom values. At block 512, the processor can operate, upon receipt of the pan, tilt and zoom (PTZ) values, the image capturing unit in the manual mode to track the intrusion target position.
[0067] At block 514, the processor can capture, upon the absence of the geo-position information of the received target, video-based information of the received target data and at block 516, the processor can operate, upon receipt of the video-based information, the image capturing unit in the auto mode to track intrusion target position.
[0068] It will be apparent to those skilled in the art that the system 100 of the disclosure may be provided using some or all of the mentioned features and components without departing from the scope of the present disclosure. While various embodiments of the present disclosure have been illustrated and described herein, it will be clear that the disclosure is not limited to these embodiments only. Numerous modifications, changes, variations, substitutions, and equivalents will be apparent to those skilled in the art, without departing from the spirit and scope of the disclosure, as described in the claims.

ADVANTAGES OF THE PRESENT INVENTION
[0069] The present invention provides a method to manage automatic multi-mode PTZ-tracking on the basis of received inputs from multiple sensors across the surveillance area.
[0070] The present invention provides a method that supports the automatic selection of suitable PTZ cameras for day and night vision as per demand.
[0071] The present invention provides a geo-position-based tracking method that is capable to avoid undue engagement of the tracker device, to prevent the PTZ camera from failure and abrupt behaviour in tracking.
[0072] The present invention provides a method in which the surveillance areas are divided into high-risk and normal zones which makes PTZ-camera allocation and reallocation tasks easier.
[0073] The present invention provides a system that performs efficiently in terms of handling multiple tracks concurrently with the same priority by toggling the sequence of the PTZ-camera.
[0074] The present invention provides the manual overriding feature to break toggling sequence of a PTZ camera that empowers the operator to select the most suitable target or event to track smoothly.
[0075] The present invention provides a system that is completely configurable in every sense like sensor priority configuration, surveillance zone priority configuration, PTZ-camera & its tracker configuration.
[0076] The present invention provides a system that is designed to avoid false tracks/events that help to avoid unnecessary engagement of the PTZ-camera using priority assignment techniques.
, Claims:1. A system (100) for automatic multi-mode tracking of land-based targets in a multi-sensor network, the system comprising:
a set of sensors (102) deployed across the surveillance area to detect a set of target data;
a tracker device (104) of an image capturing unit (106) is coupled to the set of sensors, the tracker device of the image capturing unit, on receipt of the set of target data, is configured to operate in manual mode and auto mode; and
a processor (108) operatively coupled to the tracker device of the image capturing unit, the processor configured to:
receive, from the set of sensors, the set of target data;
assign priority to each detected target data to determine the highest priority;
determine geo-position information of the received target data, wherein geo-position information of the received target data is converted into pan, tilt and zoom (PTZ) values;
operate, upon receipt of the pan, tilt and zoom values, the image capturing unit in the manual mode to track intrusion target position;
capture, upon the absence of the geo-position information of the received target, video-based information of the received target data; and
operate, upon receipt of the video-based information, the image capturing unit in the auto mode to track the intrusion target position.
2. The system as claimed in claim 1, wherein the set of sensors (102) selected from radars, underground sensors, fix cameras, electric and laser fences and any combination thereof.
3. The system as claimed in claim 1, wherein the image capturing unit (106) is PTZ-camera.
4. The system as claimed in claim 1, wherein the image capturing unit (106) switches tracking mode based on received inputs from the set of sensors, wherein the geo-position based tracking is operated when the image capturing unit is in manual mode and video analytic based tracking is operated when the image capturing unit is in auto mode.
5. The system as claimed in claim 1, wherein the PTZ-camera (106) tracks the target by using the computed pan, tilt and zoom values applied as input to the tracker device, wherein the computed PTZ values work on co-located multiple targets and the bore sight view of the PTZ-camera for co-located targets is maintained, wherein the PTZ is not changed for the tracked target till its position remains in same bore-sight.
6. The system as claimed in claim 1, wherein the system (100) provides system configurability for sensor priority, camera toggling span, and division of surveillance area into risk and normal zone, wherein interface configuration of the PTZ-camera is provided for its associated tracker device.
7. The system as claimed in claim 1, wherein the system is featured with an automated selection of operational PTZ cameras for day/night mode, wherein the IR-equipped camera is selected automatically for target tracking at night and vice-versa.
8. The system as claimed in claim 1, wherein the PTZ-camera (106) track multiple objects having the same priority in the respective surveillance area using toggling sequence and is capable to break toggling sequence through a manual override feature by operator intervention.
9. The system as claimed in claim 1, wherein the system automatically selects the next suitable PTZ camera, if the object goes beyond the current PTZ camera range during tracking to maintain continuity in tracking.
10. A method (500) for automatic multi-mode tracking of land-based targets in a multi-sensor network, the method comprising:
deploying (502) a set of sensors across the surveillance area to detect a set of target data;
operating (504) a tracker device of an image capturing unit, on receipt of the set of target data, in manual mode and auto mode, wherein the tracker device of the image capturing unit is coupled to the set of sensors;
receiving (506), at a processor, from the set of sensors, the set of target data;
assigning (508), at the processor, priority to each detected target data to determine the highest priority;
determining (510) geo-position information of the received target data, wherein the geo-position information of the received target data is converted into pan, tilt and zoom (PTZ) values;
operating (512), upon receipt of the pan tilt and zoom values, the image capturing unit in the manual mode to track intrusion target position;
capturing (514), upon the absence of the geo-position information of the received target, video-based information of the received target data; and
operating (516), upon receipt of the video-based information, the image capturing unit in the auto mode to track the intrusion target position.