AU2020101134A4 - A Vehicle Anti-Theft System Based on Facial Expression Action Recognition - Google Patents

A Vehicle Anti-Theft System Based on Facial Expression Action Recognition Download PDF

Info

Publication number
AU2020101134A4
AU2020101134A4 AU2020101134A AU2020101134A AU2020101134A4 AU 2020101134 A4 AU2020101134 A4 AU 2020101134A4 AU 2020101134 A AU2020101134 A AU 2020101134A AU 2020101134 A AU2020101134 A AU 2020101134A AU 2020101134 A4 AU2020101134 A4 AU 2020101134A4
Authority
AU
Australia
Prior art keywords
vehicle
driver
face
owner
module
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
AU2020101134A
Inventor
Haibin LIAO
Dianhua WANG
Bin Xu
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hubei University of Science and Technology
Original Assignee
Hubei University of Science and Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hubei University of Science and Technology filed Critical Hubei University of Science and Technology
Priority to AU2020101134A priority Critical patent/AU2020101134A4/en
Application granted granted Critical
Publication of AU2020101134A4 publication Critical patent/AU2020101134A4/en
Ceased legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
    • B60R25/30—Detection related to theft or to other events relevant to anti-theft systems
    • B60R25/305—Detection related to theft or to other events relevant to anti-theft systems using a camera
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
    • B60R25/01—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles operating on vehicle systems or fittings, e.g. on doors, seats or windscreens
    • B60R25/02—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles operating on vehicle systems or fittings, e.g. on doors, seats or windscreens operating on the steering mechanism
    • B60R25/022—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles operating on vehicle systems or fittings, e.g. on doors, seats or windscreens operating on the steering mechanism operating on the steering wheel, e.g. bars locked to the steering wheel rim
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
    • B60R25/01—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles operating on vehicle systems or fittings, e.g. on doors, seats or windscreens
    • B60R25/04—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles operating on vehicle systems or fittings, e.g. on doors, seats or windscreens operating on the propulsion system, e.g. engine or drive motor
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
    • B60R25/10—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles actuating a signalling device
    • B60R25/102—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles actuating a signalling device a signal being sent to a remote location, e.g. a radio signal being transmitted to a police station, a security company or the owner
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
    • B60R25/20—Means to switch the anti-theft system on or off
    • B60R25/25—Means to switch the anti-theft system on or off using biometry
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
    • B60R25/30—Detection related to theft or to other events relevant to anti-theft systems
    • B60R25/31—Detection related to theft or to other events relevant to anti-theft systems of human presence inside or outside the vehicle
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G06V40/173—Classification, e.g. identification face re-identification, e.g. recognising unknown faces across different face tracks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/174—Facial expression recognition
    • G06V40/176—Dynamic expression
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
    • B60R25/10—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles actuating a signalling device
    • B60R2025/1013—Alarm systems characterised by the type of warning signal, e.g. visual, audible
    • B60R2025/1016—Remote signals alerting owner or authorities, e.g. radio signals
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
    • B60R2300/30—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing
    • B60R2300/307—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing virtually distinguishing relevant parts of a scene from the background of the scene
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
    • B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
    • B60R2300/8006—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for monitoring and displaying scenes of vehicle interior, e.g. for monitoring passengers or cargo
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
    • B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
    • B60R2300/8073—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for vehicle security, e.g. parked vehicle surveillance, burglar detection
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R2325/00—Indexing scheme relating to vehicle anti-theft devices
    • B60R2325/20—Communication devices for vehicle anti-theft devices
    • B60R2325/205—Mobile phones
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R2325/00—Indexing scheme relating to vehicle anti-theft devices
    • B60R2325/40—Programmable elements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00—Burglar, theft or intruder alarms
    • G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
    • G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
    • G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
    • G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
    • G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
    • G08B13/19613—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00—Burglar, theft or intruder alarms
    • G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
    • G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
    • G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
    • G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
    • G08B13/19678—User interface
    • G08B13/19684—Portable terminal, e.g. mobile phone, used for viewing video remotely

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Burglar Alarm Systems (AREA)

Abstract

The invention provides a vehicle anti-theft system based on facial expression action recognition, belonging to the technical field of image processing and pattern recognition. It solves the technical problems of vehicle theft prevention and the like. The invention relates to a vehicle anti-theft system based on facial expression action recognition. The anti-theft system comprises a storage module, a face recognition module, an expression action recognition module, a communication module, a control module and the like. The invention has the functions of preventing false alarm, deception and hijacking. Drawings of Description Start the camera Inconsistent Consistenit Background analysis Anormal _LNnal reso iracogii E)Fig. 1 1/1 resoeddie

Description

Drawings of Description
Start the camera
Inconsistent Consistenit
Background analysis
Anormal _LNnal reso
iracogii
E)Fig. 1
1/1 resoeddie
Description
A Vehicle Anti-Theft System Based on Facial Expression Action Recognition
Technical Field
[0001] The invention belongs to the technical field of image processing and pattern recognition, and relates to a vehicle anti-theft system based on facial expression action recognition.
Background Technology
[0002] With the rapid development of the automobile industry, people are paying more and more attention to the anti-theft of automobiles and the personal safety of drivers on the way. At present, the automobile anti theft technology is developing towards automation and intelligence. The automobile anti-theft device mainly includes electronic anti-theft device and network anti-theft device. The electronic anti-theft device can send out sound and light to deter intruders and can lock the ignition to achieve the purpose of anti-theft. The network anti-theft device adopts the combination of GPS satellite positioning system and mobile communication system, in addition to locking ignition to achieve the purpose of anti-theft, at the same time the alarm information and vehicle location are transmitted to the alarm center or the owner's mobile phone.
[0003] The anti-theft device for automobiles can play a certain anti-theft role, but the anti-theft device cannot effectively prevent the theft of automobiles after stealing automobile keys. Therefore, there is an urgent need for new anti-theft technology. With the development of artificial intelligence technology, especially face recognition technology, it provides intelligent and automatic technical support for vehicle anti-theft system.
[0004] In recent years, with the breakthrough development of face recognition technology, the combination of face recognition and automobile anti-theft is becoming an important research direction, because the use of face for identity verification is the most natural and direct means, with the characteristics of direct, friendly and convenient, and easy to be accepted by users. For example, the technology is introduced in the patents entitled An Intelligent Face Recognition Vehicle Anti-theft Device (Patent Publication No.: CN103538563A) and A Face Recognition Based Vehicle Anti-theft System and Method (Patent Publication No.: CN105882605A). However, the current vehicle anti-theft method based on face recognition is not perfect, and the following problems mainly exist:
[0005] 1) The method adopted is not advanced enough to overcome the problems of face illumination, hairstyle, age and other changes in actual scenes. Regarding the problem of illumination change, patent CN106218584A proposes A Vehicle Anti-theft System Based on Infrared and Face Recognition Technology, but it cannot solve the problems of hairstyle and age change. Therefore, the patent of the present invention proposes to adopt a depth learning method to overcome the above face change problem and improve the face recognition accuracy.
[0006] 2) Can't solve the problem of false report of others (relatives, friends, etc.) borrowing the vehicle or driving on behalf of others. At present, most methods focus on how to improve the anti-theft level and prevent missing reports. For example, patent 201751248u discloses an automobile starting system with bus function of fingerprint and voice recognition. Patent CN104097611A discloses an automobile anti-theft method based on face recognition technology and multiple identity verification. Although these double authentication methods improve the safety level of vehicles to a certain extent, they are prone to false positives and reduce the user experience. In reality, vehicle theft is a rare occurrence, while vehicle borrowing and driving on behalf of others are common. Therefore, the designed system should not only have anti-theft function, but also have anti-false alarm strategy. According to the invention, the problem of false alarm such as vehicle borrowing, driving on behalf of others and the like is solved by adopting a mode of combining confirmation with a mobile phone.
[0007] 3) Anti-deception problem. In the vehicle theft prevention method based on face recognition, in recognition technology, simple static face recognition cannot prevent thieves from using printed photos for fraudulent authentication. Currently, there is a patent CN104494564A, A Vehicle Anti-theft System Based on Face Recognition, which uses a living body detection method, that is, a method of letting users blink to judge whether it is a living person or a photo, so as to prevent thieves from deceiving the authentication system with printed photos. However, this method requires the cooperation of users, and the user experience is not good. The invention provides an anti-fraud authentication method by using an in-vehicle background analysis method.
[0008] 4) Anti-hijacking problem. At present, all anti-theft methods for automobiles do not have the function of anti-hijacking. According to the invention, a method for recognizing facial expressions and actions is adopted to carry out clamping judgment. The system specifies several expression actions as the sign of being held in advance. Once the holding occurs, the user can make the preset expression actions to alarm.
Summary of the Invention
[0009] The purpose of the present invention is to provide a vehicle anti-theft system based on facial expression action recognition aiming at the above problems existing in the prior art. The technical problem to be solved by the present invention is how to judge the legitimacy of a vehicle operator through recognition of facial expression actions, thereby effectively preventing vehicle theft.
[0010] The object of the present invention can be achieved by the following technical scheme: a vehicle anti theft system based on facial expression action recognition, characterized in that the anti-theft system comprises:
[0011] The storage module is used for prestoring common driver face images, agreed anti-seizure expression action images and in-vehicle background images;
[0012] The face recognition module is used for judging the identity of the driver. In order to improve the accuracy of face recognition, the present invention adopts an advanced face recognition method based on depth learning.
[0013] The expression action recognition module is used for recognizing the expression action of the driver and judging the holding situation. In order to improve the accuracy of facial expression and motion recognition, the invention adopts the current advanced expression and motion recognition method based on depth learning.
[0014] The communication module is use for communicating with that vehicle own to confirm the legality of the driver. When the face recognition module judges that the driver is not a designated driver, the communication module sends a scene driver photo to the owner's mobile phone, requesting to confirm the legality of the driver. When the face recognition module judges that the driver is the person who borrowed the vehicle or drove on his behalf last time, the communication module sends a picture of the driver on the spot to the owner's mobile phone, requesting whether to stop his behavior request (the default is permission).
[0015] A control module for controlling the vehicle. If that identity confirmation of the face recognition module fail and no owner confirmation feedback is receive. The control module locks the steering wheel and stops the engine. If that identity of the face recognition module is confirm to be the person who borrowed the vehicle or drive on behalf of the driver last time, and the feedback that the owner explicitly stops is receive. Then the control module locks the steering wheel and stops the engine from working, otherwise it runs normally. If the expression action module detects a prescribed expression action. Then the control module immediately alarms the public security department.
[0016] Further, the storage module also has an automatic updating function, that is, every time a legal driver is detected, the system automatically collects standard (front, neutral expression, uniform illumination) legal
driver face images to update the face database. In addition, when vehicle borrowing or driving on behalf of others occurs, the storage module automatically collects standard face images of vehicle borrowing or driving on behalf of others, and constructs a legal face borrowing library for next identification.
[0017] Furthermore, the face recognition module also has an anti-deception function. First of all, face detection and analysis are carried out on the images taken by the camera in the vehicle to see if there is a face. If there are no faces in multiple consecutive images, indicating that the camera head is intentionally blocked, the vehicle owner will be alerted and feedback will be requested. Then, it is analyzed whether the captured image shows the scene of holding the photo in hand. If so, it means that a thief cheated by printing the owner's photo, and he should immediately report to the owner or the public security system. Finally, the background of the shot image (the background image after removing the human face) is extracted and compared with the pre-stored background image in the car. If the difference is found, it indicates that the thief cheated by printing the owner's photo and should immediately report to the owner or the public security system.
[0018] Furthermore, the expression action recognition module also has a nervous expression recognition function. When the vehicle owner is held hostage, the facial expression must be nervous and uneasy. Therefore, it is possible to judge whether the vehicle owner has been hijacked by using nervous and uneasy expression recognition technology. If the expression and action recognition module recognizes that the vehicle owner has nervous and uneasy expressions, it will immediately report to the public security system and transmit the images taken at the scene.
[0019] Compared with the prior art, the invention has the following advantages and effects:
[0020] 1) False alarm prevention function: At present, anti-theft methods for automobiles based on biological characteristics (fingerprints, faces, voice, etc.) are not widely used because such methods cannot overcome false alarm problems such as vehicle borrowing or driving on behalf of users, and the user experience is not good. The invention successfully solves the problem of false positives by combining with a mobile phone for confirmation. That is, when the face recognition module recognizes the illegal driver, the problem of borrowing or driving on behalf of the driver is solved by sending the scene picture to the owner for confirmation.
[0021] 2) Anti-deception function: one of the difficulties in anti-theft of automobiles by using face recognition technology is how to prevent thieves from deceiving the owner's photo. The invention uses two image analysis technologies to prevent deception: one is to analyze whether there is a case of holding a photo by hand in the image captured by the camera, and if so, it is proved to be cheating. The second is to use background contrast analysis technology to see whether the image background taken by the camera is consistent with the inherent background stored in the car. If not, it is proved to be cheating.
[0022] 3) Anti-hijacking function: The invention uses facial expression and action recognition technology to judge whether the driver is hijacked and automatically gives an alarm.
Brief Description of Drawings
[0023] Fig. 1 is an anti-theft flow chart of the anti-theft system.
Detailed Description of the Preferred Embodiments
[0024] The following are specific embodiments of the present invention and further describe the technical scheme of the present invention with reference to the drawings, but the present invention is not limited to these embodiments.
[0025] The flow steps of a vehicle anti-theft method and system based on face and expression recognition disclosed by the invention are shown in fig. 1, and mainly comprise four steps:
[0026] Step 1: Start
[0027] When the driver starts the car, the system automatically starts the camera inside the vehicle to take pictures of the driver inside the car.
[0028] It is preferable to stop starting the vehicle if the camera cannot be started after ignition. If the camera is intentionally blocked, stop starting the car.
[0029] It is preferable to judge whether the camera is intentionally shielded by analyzing the difference between the normal background in the vehicle and the background of the shielding object.
[0030] Step 2: Background Analysis
[0031] Firstly, the face detection technology is used to judge whether there is a human face in the shot image. If there is no human face in several consecutive images, it is judged that someone intentionally shields the camera or avoids the camera. Then stop the engine to start and lock the steering wheel, notify the owner and request feedback whether to give an alarm.
[0032] Then, Adaboost method is used to detect whether there is a scene of holding the corner of the picture by hand in the shot image. If so, it is judged that someone cheated with the owner's photo. Then stop the engine and lock the steering wheel, notify the owner and call the police.
[0033] Finally, the background is extracted from the normal image taken without hand-held photos, and the extracted background is compared with the pre-stored in-vehicle background. If the comparison results are inconsistent, it is judged that someone cheated by printing photos. Then stop the engine and lock the steering wheel, notify the owner and call the police.
[0034] Preferably, in order to improve the accuracy of face detection, Faster-RCNN face detection technology with better effect is adopted. In order to improve the accuracy of background contrast analysis, Gabor and LBP features are extracted from the extracted background images, and support vector machine (SVM) is used for consistency classification.
[0035] Step 3: Face Recognition
[0036] For normally photographed images, standard (positive, neutral expression and good illumination) face images are extracted by using face detection technology, and the identity of the driver is recognized by using face recognition technology. If the identified identity is a legal driver such as the owner or his family, the driving will be started normally. Otherwise, the photographed face image is transmitted to the owner's mobile phone for legality confirmation: if the owner feedback is legal (relatives and friends borrow the car), the driving is started normally; Otherwise, stop the engine and lock the steering wheel, and call the police.
[0037] Preferably, in order to improve the accuracy of face recognition, the depth learning method with better effect is adopted for face recognition. Specifically, FaceNet network is used to extract face features, and SVM is used for face classification and recognition.
[0038] Step 4: Expression and Action Recognition
[0039] The expression and action recognition technology is used to recognize the driver's expression and action. If the agreed expression action is recognized, it is determined that the hijacking occurs, and the captured video is immediately transmitted to the public security department for alarm.
[0040] Furthermore, if the driver is identified to have continuous expressions of panic and uneasiness through expression recognition technology, the captured video will be transmitted to the traffic control department for alarm.
[0041] Preferably, the agreed optional expressions include: Nodding three times in a row, blinking three times in a row, opening and closing your mouth three times in a row, supporting your eyebrows three times in a row and spitting your tongue three times in a row. Expression can only be divided into normal expression, panic expression and uneasy expression to reduce classification difficulty. In addition, in order to improve the accuracy of facial expression recognition, the depth learning method with better effect is adopted for facial expression recognition.
[0042] In summary, the vehicle anti-theft method and system based on face and expression recognition provided by the present invention has the following characteristics:
[0043] 1) The vehicle anti-theft system provided by the invention not only has an anti-theft function, but also has a clamping alarm function.
[0044] 2) The vehicle anti-theft system provided by the invention not only has high anti-theft level, but also solves the false alarm condition. That is, the contradiction between theft prevention and false alarm is solved.
[0045] 3) The invention realizes the functions of theft prevention and support, only needs to install a camera, and does not need to adjust the structure of the automobile. In addition, the additional camera can also be used for in-vehicle safety detection, such as overload, children and the elderly sitting in the front row and driver drowsiness detection, etc.
[0046] The specific embodiments described herein are merely illustrative of the spirit of the present invention. Those skilled in the art to which the present invention belongs can make various modifications or supplements to the described specific embodiments or replace them in a similar way without departing from the spirit of the present invention or exceeding the scope defined in the appended claims.

Claims (4)

Claims
1. A vehicle anti-theft system based on facial expression and action recognition, characterized in that the anti-theft system comprises: a storage module, which is used for pre-storing common driver face images, agreed anti-hijacking expression and action images and in-vehicle background images;
The face recognition module is used for judging the identity of the driver. The expression action recognition module is use for recognizing that expression action of the drive and judging the holding situation. The communication module is use for communicating with that vehicle own to confirm the legality of the driver. When the face recognition module judges that the driver is not a designated driver, the communication module sends a scene driver photo to the owner's mobile phone, requesting to confirm the legality of the driver. When the face recognition module judges that the driver is the person who borrowed the vehicle or drove on behalf of the driver last time, the communication module sends a picture of the driver on the spot to the owner's mobile phone, requesting whether to stop his behavior request (the default is permission);
A control module for controlling the vehicle. If that identity confirmation of the face recognition module fail and no owner confirmation feedback is receive. The control module locks the steering wheel and stops the engine from working. If that identity of the face recognition module is confirm to be the person who borrowed the vehicle or drive on behalf of the driver last time, and the feedback that the owner explicitly stops is receive. Then the control module locks the steering wheel and stops the engine from working, otherwise the vehicle runs normally. If the expression action module detects a prescribed expression action. Then the control module immediately alarms the public security department.
2. According to claim 1, a vehicle anti-theft system based on facial expression action recognition is characterized in that the storage module also has an automatic updating function, namely, the system automatically collects standard (front, neutral expression, uniform illumination) legal driver face images to update a face database every time a legal driver is detected. In addition, when vehicle borrowing or driving on behalf of others occurs, the storage module automatically collects standard face images of vehicle borrowing or driving on behalf of others, and constructs a legal face borrowing library for next identification.
3. According to claim 1, a vehicle anti-theft system based on facial expression action recognition is characterized in that the face recognition module also has an anti-fraud function. Firstly, face detection and analysis are carried out on the images shot by the camera in the vehicle to see if there is a face. If there are no faces in consecutive photos, indicating that the shooting head is intentionally blocked, the vehicle owner is alerted and feedback is requested. Then, it is analyzed whether the captured image shows the scene of holding the photo with hands. If so, it means that some thieves cheated by printing the owner's photo, and they should immediately report to the owner or the public security system. Finally, the background of the shot image (the background image after removing the human face) is extracted and compared with the pre-stored background image in the car. If the difference is found, it indicates that the thief cheated by printing the owner's photo and should immediately report to the owner or the public security system.
4. According to claim 1, a vehicle anti-theft system based on facial expression action recognition is characterized in that the expression action recognition module also has a nervous expression recognition function. If the expression and action recognition module recognizes that the vehicle owner has nervous and uneasy expressions, it will immediately report to the public security system and transmit the images taken at the scene.
2020101134 Drawings of Description
Fig. 1
1/1
AU2020101134A 2020-06-25 2020-06-25 A Vehicle Anti-Theft System Based on Facial Expression Action Recognition Ceased AU2020101134A4 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU2020101134A AU2020101134A4 (en) 2020-06-25 2020-06-25 A Vehicle Anti-Theft System Based on Facial Expression Action Recognition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
AU2020101134A AU2020101134A4 (en) 2020-06-25 2020-06-25 A Vehicle Anti-Theft System Based on Facial Expression Action Recognition

Publications (1)

Publication Number Publication Date
AU2020101134A4 true AU2020101134A4 (en) 2020-07-30

Family

ID=71738685

Family Applications (1)

Application Number Title Priority Date Filing Date
AU2020101134A Ceased AU2020101134A4 (en) 2020-06-25 2020-06-25 A Vehicle Anti-Theft System Based on Facial Expression Action Recognition

Country Status (1)

Country Link
AU (1) AU2020101134A4 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112634507A (en) * 2020-12-30 2021-04-09 重庆赤木科技有限公司 Safety access control management system for community
CN113815562A (en) * 2021-09-24 2021-12-21 上汽通用五菱汽车股份有限公司 Vehicle unlocking method and device based on panoramic camera and storage medium
CN115320540A (en) * 2022-08-04 2022-11-11 重庆长安汽车股份有限公司 Vehicle control method, device, system, electronic device, storage medium and vehicle

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112634507A (en) * 2020-12-30 2021-04-09 重庆赤木科技有限公司 Safety access control management system for community
CN113815562A (en) * 2021-09-24 2021-12-21 上汽通用五菱汽车股份有限公司 Vehicle unlocking method and device based on panoramic camera and storage medium
CN115320540A (en) * 2022-08-04 2022-11-11 重庆长安汽车股份有限公司 Vehicle control method, device, system, electronic device, storage medium and vehicle
CN115320540B (en) * 2022-08-04 2024-03-08 重庆长安汽车股份有限公司 Vehicle control method, device, system, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
AU2020101134A4 (en) A Vehicle Anti-Theft System Based on Facial Expression Action Recognition
CN107554483A (en) A kind of VATS Vehicle Anti-Theft System based on human face expression action recognition
US10654448B2 (en) Vehicle security system
US7760070B2 (en) Vehicle security device and system
CN100341732C (en) Automobile anti-theft method based on human face identification technology
EP1700761B1 (en) Apparatus for authenticating vehicle driver
US9235750B1 (en) Using passive driver identification and other input for providing real-time alerts or actions
KR100778060B1 (en) Vehicle emergency preventive terminal device and internet system using facial recognition technology
KR102088590B1 (en) Safety driving system having drunken driving preventing function
JP3699434B2 (en) Vehicle anti-theft device
US20020097145A1 (en) Integrated vehicle security system utilizing facial image verification
JP2020525884A (en) Vehicle control method and system, in-vehicle intelligent system, electronic device and medium
JP2005001642A (en) Antitheft device, monitoring device, and antitheft system
CN110027509A (en) A kind of vehicular theft-prevention monitoring device and method based on recognition of face
CN106394492A (en) Vehicle dynamic face identification safety control system and control method thereof
KR102265624B1 (en) Start-up security system for vehicles using facial recognition
KR101437406B1 (en) an emergency management and crime prevention system for cars and the method thereof
CN215663738U (en) Intelligent security system of storage battery car
JP3797237B2 (en) Vehicle interior monitor device, vehicle interior monitor control device, vehicle thief identification system
JP4030984B2 (en) Vehicle control system and vehicle control program
KR20120012666A (en) System and method for protecting drunk driving using face recognition technology
KR20230002761A (en) Security Notifications Based on Biometric Identifiers
Ofoegbu An adaptive user authentication architecture for drunk driving and vehicle theft mitigation
CN117864061A (en) Method for vehicle anti-theft alarm and vehicle anti-theft alarm system
CN109050246A (en) A kind of method and apparatus of giving fatigue pre-warning

Legal Events

Date Code Title Description
FGI Letters patent sealed or granted (innovation patent)
MK22 Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry