Description:FIELD OF THE INVENTION
This invention relates to Computer vision based Face Recognition Drone System.
BACKGROUND OF THE INVENTION
Safety and effective crowd control are critical to extensive public functions and events. The traditional physical approaches to crowd surveillance and control are pretty inadequate, error-prone, and unable to give responses to emergencies or unusual crowd behavioral patterns. This could result in disorder, injuries, and possibly even deaths because the delay in detecting and responding to the threat would guide the individual to safe areas in an emergency. There is an essential need for a real-time behavior analysis automatic intelligent system that could guide and alert for better safety and management of the crowd.
The utilization of a real-time behavior analysis intelligent system that is automatic could bring about a complete change in crowd management at large events. This system makes use of advanced technology such as machine learning and computer vision to constantly check for the unusual behaviors among the crowds, predict any possible dangers that might occur in future. Such proactive measures will enable event organizers and the security personnel to promptly respond to threats by adopting appropriate safety measures so as to avert accidents and maintain lawfulness. The user interface could thereby enhance how people manage big crowds in terms of efficiency and safety.
Merging this smart system with the established security infrastructure can establish an all-inclusive plan towards crowd control. The ability of the system to analyze huge amounts of data within fractions of seconds enables rapid identification of potential threats and coordinated response. For example, when there is a sudden increase in number of people or panic attack among people; it can signal the securities instantly who will then guide them through designated areas that are safe from harm thus reducing chances of injury amongst them. Consequently, this not only improves general public event security but also creates trust within attendees who know very well that there exists robust mechanisms for their protection.
CN110008919A The present invention devises a kind of quadrotor drone face identification system of view-based access control model, mainly includes flight control system, face recognition module, wireless image transmission module, earth station's information display module. The present invention utilizes the camera collection image being mounted on quadrotor drone holder, and embedded board to is sent video image by CSI interface, embedded board carries out image preprocessing, Face detection and recognition of face processing to it after receiving image, judge whether this person is target face by designed classifier, if target face, then send facial image on earth station's display interface of computer end by wireless image transmission. Meanwhile earth station carries out information library searching to target face, shows the information of target person.
RESEARCH GAP: Autonomous Navigation: A system that uses LiDAR, ultrasonic, and infrared sensors to ensure safe and efficient movement in crowded environments.
KR102254491B1 Disclosed is an autonomous flight drone equipped with an intelligent image analysis function. The autonomous flight drone equipped with an intelligent image analysis function has a camera (thermal imaging camera, general camera). The drone itself provides intelligent image analysis of camera images (using chipsets for image analysis such as FPGA, TPU, IPU, etc.) and remote drone movement control. During autonomous flight, the drone detects objects in the drone's thermal imaging camera/general camera image by the drone's own intelligent image analysis module, extracts and classifies features of the objects of the camera image, identifies people (displaced people) in case of a forest fire/fire and a person/ship during a patrol on the sea/along the coast, transmits image data in which the objects in the drone's camera image are identified to a media server (RTSP server) through a communication network (RF, Wi-Fi, LTE 4G/ 5G, IoT communication network), and displays the transmitted image data to a client of a ground terminal (RTSP client).
RESEARCH GAP: Cost-effective: reduces the number of human security personnel required, thereby reducing operational costs.
US11978256B2 A monitoring system is configured to monitor a property. The monitoring system includes a camera, a sensor, and a monitor control unit. The monitor control unit is configured to receive image data and sensor data. The monitor control unit is configured to determine that the image data includes a representation of a person. The monitor control unit is configured to determine an orientation of a representation of a head of the person. The monitor control unit is configured to determine that the representation of the head of the person likely includes a representation of a face of the person. The monitor control unit is configured to determine that the face of the person is likely concealed. The monitor control unit is configured to determine a malicious intent score that reflects likelihood that the person has a malicious intent. The monitor control unit is configured to perform an action.
RESEARCH GAP: Speed and Efficiency: Crowd management tasks can be automated, thus being a less need for human intervention.
None of the prior art indicate above either alone or in combination with one another disclose what the present invention has disclosed. This invention relates to Computer vision based Face Recognition Drone System.
SUMMARY OF THE INVENTION
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 key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is 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 with the accompanying drawings.
The proposed invention is a sophisticated robot designed for crowd management, utilizing a combination of advanced components to analyze behavior, guide individuals to safe areas, and send alerts in case of disturbances. Now, the system's centerpiece is the Raspberry Pi; it acts as the central processing unit for coordinating the operations of many attached parts.
The camera is a high-definition one on the robot to capture the real-time images and videos of the crowd. The captured visual data is processed by the neural compute stick to accelerate neural network interference for behavior analysis to distinguish between normal and strange or suspicious activities. Its sensors further enhance accuracy in measuring distances and detecting obstacles during safe movement through the crowded environment using the LiDAR, ultrasonic, and infrared sensors. Microphones are integrated to record peripheral sounds and perhaps vocal cues that might signal distress or emergencies.
The robot accommodates wheeled systems mounted on motors and servo drivers, allowing smooth and accurate movement. It is powered by a reliable battery system, which includes a voltage-buck converter that stabilizes the battery voltage and all components powered.
A Wi-Fi module allows smooth communication with a cloud server, where all data is stored securely and further analyzed if need be. Further, the robot can have an emergency; therefore, the remote monitoring and control features enable it to send some alerts to a control room in due time. The infrared sensors come in where the lighting is dim; they give the robot the ability to identify heat signatures. This is to let the robot continue practical functionality even when the room is dark. It is a compact and robust integrated system that allows the robot to move in heavy crowds and restricted passages. Over some time, the camera captures continuous shots, which are analyzed with the help of the neural computer stick to identify any behavioral anomalies.
The LiDAR and ultrasonic sensors ensure that, based on environmental mapping, the robot can safely remain mobile and avoid each obstacle. The infrared sensors help find individuals under poor visibility, and the microphones capture any sounds that might indicate a disturbance or emergency.
With everything set, the proposed crowd management robot can go into an active-monitoring mode. The high-definition camera always initiates the algorithmic flow mounted on the robot, capturing real-time images and continuous videos. These visual inputs are transmitted instantly to the Raspberry Pi for preliminary processing. The Raspberry Pi does preliminary processing on the visual data received, which includes noise reduction, image stabilization, and frame rate adjustment, through which data is shown in the best form for final analysis.
Afterward, the pre-processed visual data is submitted to the neural compute stick, which runs on pre-learned models that are usually prepared using TensorFlow and YOLOv5 to inspect new data. Specifically, using models, the visual data is analyzed to identify and recognize erratic patterns, movements, and behaviors in large groups of people. That latter means signs of panic, aggression, or another indication of abnormal dynamics of the people in a group that may signal trouble or an emergency.
Simultaneously, it scans the external environment with its LiDAR, ultrasonic, and infrared sensors. These sensors measure the distance and continue to detect obstacles in the way, such that the robot creates inches of 3D mapping of the surroundings. Once again, its Raspberry Pi receives the data from these sensors to add this to the visual data, making the overall situational awareness more enhanced.
It processes visual data and identifies any anomalies based on behavior. If the system detects some sign of distress or unusually unwanted event, it triggers an alert within the Raspberry Pi. The Raspberry Pi, in turn, powers and guides the motors and servo drivers to move the robot closer to the detected area. The robot's labor is carefully controlled and guided by real-time inputs from LiDAR and ultrasonic sensors to navigate through this crowd in an safe and efficient way.
The robot further keeps on capturing the visual and acoustic data during its movement. The microphones on the robot capture the ambient sounds and possible speech prompts which might help to provide more context to the detected disturbance. This stream of audio is then processed to find key words and patterns of sounds revealing problems of stress or emergencies.
When the robot enters the emergency area, it voices the crowd through in-built speakers and visual displays. It delivers people clear messages and directions to go to exits, safe zones, or stay in pre-determined areas. Despite the pitch black, the robot detects and interacts with individuals using infrared sensors that are part of the robot structure.
At any moment, the robot Wi-Fi module requires constant contact connected back to the server located in the cloud. The robot collects information—including visual, audio, and sensor data—and sends all of that into the cloud server based on advanced analysis and retention. This would enable surveillance to be non-local, relieve security personnel of qualitative oversight duties, and provide real-time situational report updates from the robot.
For instance, in case a significant threat or an emergency is detected, it sends an alert to the control room right away using the Wi-Fi module. The message contains the detailed nature of the problem identified, its present location, and the robot status at that instance. Security personnel can now take appropriate actions with the data provided in real-time by the robot.
With its capability to steer the crowds to safety and notify the control rooms during a disturbance, it ensures a high degree of safety and efficiency in managing large gatherings. This technology is not only innovative but also quite indispensable in today's situations, where crowd control and safety are taken into account. The crowd management robot can be released in multiple areas, such as massive public events, concerts, sports stadiums, airports, train stations, shopping malls, and emergency evacuations. By providing people with security while passing through different natural disasters such as earthquakes or fire, it can be effectively applied to manage a disaster. In addition, it can also be used to monitor and efficiently check the flow of crowds on corporate campuses and at both government and educational institutions.
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
Figure 1: General Architecture of the system
Figure 2: Detailed architecture of the system
Figure 3: Algorithmic structure of the system
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a",” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", “third”, and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The proposed invention is a sophisticated robot designed for crowd management, utilizing a combination of advanced components to analyze behavior, guide individuals to safe areas, and send alerts in case of disturbances. Now, the system's centerpiece is the Raspberry Pi; it acts as the central processing unit for coordinating the operations of many attached parts.
The camera is a high-definition one on the robot to capture the real-time images and videos of the crowd. The captured visual data is processed by the neural compute stick to accelerate neural network interference for behavior analysis to distinguish between normal and strange or suspicious activities. Its sensors further enhance accuracy in measuring distances and detecting obstacles during safe movement through the crowded environment using the LiDAR, ultrasonic, and infrared sensors. Microphones are integrated to record peripheral sounds and perhaps vocal cues that might signal distress or emergencies.
The robot accommodates wheeled systems mounted on motors and servo drivers, allowing smooth and accurate movement. It is powered by a reliable battery system, which includes a voltage-buck converter that stabilizes the battery voltage and all components powered.
A Wi-Fi module allows smooth communication with a cloud server, where all data is stored securely and further analyzed if need be. Further, the robot can have an emergency; therefore, the remote monitoring and control features enable it to send some alerts to a control room in due time. The infrared sensors come in where the lighting is dim; they give the robot the ability to identify heat signatures. This is to let the robot continue practical functionality even when the room is dark. It is a compact and robust integrated system that allows the robot to move in heavy crowds and restricted passages. Over some time, the camera captures continuous shots, which are analyzed with the help of the neural computer stick to identify any behavioral anomalies.
The LiDAR and ultrasonic sensors ensure that, based on environmental mapping, the robot can safely remain mobile and avoid each obstacle. The infrared sensors help find individuals under poor visibility, and the microphones capture any sounds that might indicate a disturbance or emergency.
With everything set, the proposed crowd management robot can go into an active-monitoring mode. The high-definition camera always initiates the algorithmic flow mounted on the robot, capturing real-time images and continuous videos. These visual inputs are transmitted instantly to the Raspberry Pi for preliminary processing. The Raspberry Pi does preliminary processing on the visual data received, which includes noise reduction, image stabilization, and frame rate adjustment, through which data is shown in the best form for final analysis.
Afterward, the pre-processed visual data is submitted to the neural compute stick, which runs on pre-learned models that are usually prepared using TensorFlow and YOLOv5 to inspect new data. Specifically, using models, the visual data is analyzed to identify and recognize erratic patterns, movements, and behaviors in large groups of people. That latter means signs of panic, aggression, or another indication of abnormal dynamics of the people in a group that may signal trouble or an emergency.
Simultaneously, it scans the external environment with its LiDAR, ultrasonic, and infrared sensors. These sensors measure the distance and continue to detect obstacles in the way, such that the robot creates inches of 3D mapping of the surroundings. Once again, its Raspberry Pi receives the data from these sensors to add this to the visual data, making the overall situational awareness more enhanced.
It processes visual data and identifies any anomalies based on behavior. If the system detects some sign of distress or unusually unwanted event, it triggers an alert within the Raspberry Pi. The Raspberry Pi, in turn, powers and guides the motors and servo drivers to move the robot closer to the detected area. The robot's labor is carefully controlled and guided by real-time inputs from LiDAR and ultrasonic sensors to navigate through this crowd in an safe and efficient way.
The robot further keeps on capturing the visual and acoustic data during its movement. The microphones on the robot capture the ambient sounds and possible speech prompts which might help to provide more context to the detected disturbance. This stream of audio is then processed to find key words and patterns of sounds revealing problems of stress or emergencies.
When the robot enters the emergency area, it voices the crowd through in-built speakers and visual displays. It delivers people clear messages and directions to go to exits, safe zones, or stay in pre-determined areas. Despite the pitch black, the robot detects and interacts with individuals using infrared sensors that are part of the robot structure.
At any moment, the robot Wi-Fi module requires constant contact connected back to the server located in the cloud. The robot collects information—including visual, audio, and sensor data—and sends all of that into the cloud server based on advanced analysis and retention. This would enable surveillance to be non-local, relieve security personnel of qualitative oversight duties, and provide real-time situational report updates from the robot.
For instance, in case a significant threat or an emergency is detected, it sends an alert to the control room right away using the Wi-Fi module. The message contains the detailed nature of the problem identified, its present location, and the robot status at that instance. Security personnel can now take appropriate actions with the data provided in real-time by the robot.
With its capability to steer the crowds to safety and notify the control rooms during a disturbance, it ensures a high degree of safety and efficiency in managing large gatherings. This technology is not only innovative but also quite indispensable in today's situations, where crowd control and safety are taken into account. The crowd management robot can be released in multiple areas, such as massive public events, concerts, sports stadiums, airports, train stations, shopping malls, and emergency evacuations. By providing people with security while passing through different natural disasters such as earthquakes or fire, it can be effectively applied to manage a disaster. In addition, it can also be used to monitor and efficiently check the flow of crowds on corporate campuses and at both government and educational institutions.
A computer vision based Face recognition drone system comprises Robot (2), Cloud Server (3), Web Interface for authorities (4), Wifi Module (5), Camera FHD (1280x1080) (6), Neural Stick (7), LiDar Sensor (8), Ultrasonic (9), Raspberry Pi 3v+ (10), Microcontroller (11), Microphone (12), Infrared Sensor (13), Motor Driver (14), 12v 3amp Lithium Polymer (Battery) (15), Motor (16), DC Included Motor (17), Charger (18), AC Outlet (19) and Changing Current (20) wherein the camera (6) is a high-definition one on the robot to capture the real-time images and videos of the crowd; the captured visual data is processed by the neural compute stick (7) to accelerate neural network interference for behavior analysis to distinguish between normal and strange or suspicious activities.
In another embodiment the sensors enhance accuracy in measuring distances and detecting
obstacles during safe movement through the crowded environment using the LiDAR, ultrasonic,
and infrared sensors.
In another embodiment the microphone (12) is integrated to record peripheral sounds and perhaps vocal cues that might signal distress or emergencies.
In another embodiment the robot accommodates wheeled systems mounted on motors and servo drivers, allowing smooth and accurate movement; It is powered by a reliable battery system (15), which includes a voltage-buck converter that stabilizes the battery voltage and all components powered.
In another embodiment the robot's Wi-Fi module (5) allows for secure communication with a cloud server (3), as well as secure data storage and remote monitoring in emergency situations.
In another embodiment the robot can have an emergency; therefore, the remote monitoring and control features enable it to send some alerts to a control room in due time.
ADVANTAGES OF THE INVENTION
Improved security: real-time detection and analysis of the situation for appropriate responses to possible threats.
Accuracy: Utilizes advanced sensors and neural networks for precise detection and analysis.
Safety: Directs crowds to places of safety in emergencies to reduce safety risks.
Real-time Alerting: It issues alerts in real-time to control rooms for a quick response to be affected.
Scalable: Can be deployed across different environments and scaled up using requirement.
Flexibility: Works flexibly in diverse lighting conditions and surroundings.
Made Data Collection: Stores data in the cloud for subsequent analysis and reporting.
, Claims:1. A computer vision based Face recognition drone system comprises Robot (2), Cloud Server (3), Web Interface for authorities (4), Wifi Module (5), Camera FHD (1280x1080) (6), Neural Stick (7), LiDar Sensor (8), Ultrasonic (9), Raspberry Pi 3v+ (10), Microcontroller (11), Microphone (12), Infrared Sensor (13), Motor Driver (14), 12v 3amp Lithium Polymer (Battery) (15), Motor (16), DC Included Motor (17), Charger (18), AC Outlet (19) and Changing Current (20) wherein the camera (6) is a high-definition one on the robot to capture the real-time images and videos of the crowd; the captured visual data is processed by the neural compute stick (7) to accelerate neural network interference for behavior analysis to distinguish between normal and strange or suspicious activities.
2. The system as claimed in claim 1, wherein the sensors Camera FHD (1280x1080) (6), Neural Stick (7), LiDar Sensor (8), Ultrasonic (9), Microcontroller (11), Microphone (12), Infrared Sensor (13) enhance accuracy in measuring distances and detecting obstacles during safe movement through the crowded environment using the LiDAR, ultrasonic, and infrared sensors.
3. The system as claimed in claim 1, wherein the microphone (12) are integrated to record peripheral sounds and perhaps vocal cues that might signal distress or emergencies.
4. The system as claimed in claim 1, wherein the robot accommodates wheeled systems mounted on motors and servo drivers, allowing smooth and accurate movement; It is powered by a reliable battery system, which includes a voltage-buck converter that stabilizes the battery voltage and all components powered.
5. The system as claimed in claim 1, wherein the robot's Wi-Fi module (5) allows for secure communication with a cloud server (3), as well as secure data storage and remote monitoring in emergency situations.
6. The system as claimed in claim 1, wherein the robot can have an emergency; therefore, the remote monitoring and control features enable it to send some alerts to a control room in due time.