computer vision video surveillance system n.
Skip this Video
Loading SlideShow in 5 Seconds..
Computer Vision Video Surveillance System PowerPoint Presentation
Download Presentation
Computer Vision Video Surveillance System

Computer Vision Video Surveillance System

460 Vues Download Presentation
Télécharger la présentation

Computer Vision Video Surveillance System

- - - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript

  1. Computer VisionVideo Surveillance System Dr. Aree Ali Mohammed Assistant professor 2012-2013 3rd Stage University of Sulaimani - School of Science - Computer Dept.

  2. Presentation Overview • Video surveillance systems. • Traffic monitoring issues. • Object tracking techniques. • Vehicle tracking strategies. • A real time system Explanation.

  3. Why Video Surveillance? • Improve public safety • Mitigate risks of crime and terrorism • Protect assets • Prevent fraud • Improve efficiency • Automate more processes • Train dispatch • Self-checking counters • Provide better healthcare

  4. what is video surveillance? • Present Implementations? • Human detection systems. • vehicle monitoring systems. • Advantages of video surveillance? • Keep track of information video data for future use. • Helpful in identifying people in the crime scenes etc.. • Disadvantages of the present system? • It’s difficult to maintain heavy amount of raw video data • Human interaction. • Require higher bandwidth for transmitting the visual data.

  5. Video Surveillance Addressable Market • Video surveillance application areas are myriad. Though their true scope remains almost unlimited, a few of the important areas of application are listed below: Monitoring process: traffic monitoring, border control Transport : Railways, airports and ports Government buildings : Museums and military bases Educational institutions: Distance learning, Telemedicine Energy: Oil & Gas, Utilities Public Security: Police/Fire/Ambulance CCTV: Closed Circuit Television Manufacturing: Production line quality management Leisure and entertainment areas: Stadiums Commercial units : Retail outlets, banks and casinos

  6. Video Surveillance Applications: Forbidden Zone Alarm • Forbidden Zone protection • Intruder detection • Object tracing • Object detection of moving trail in open area

  7. Video Surveillance Applications: Behavior Analysis Personal injury detection • Public responsibility • Elderly home care • Instant assistance and prevention Suspicious behavior detection • Loaf and run behavior • Custom behavior detection model

  8. Video Surveillance Applications: Pedestrian and Traffic Flow Analysis Pedestrian flow management Traffic flow management • Allows threshold value to be set • Raises alarms when threshold is exceeded • Detects overcrowding/congestion • Assures public safety • Assures good traffic flow

  9. Video Surveillance Applications: Night Video Night video surveillance assures public safety

  10. Video Surveillance Applications: Others Identification by license plate or face Record by trigger event Extended services to consumers

  11. Video Surveillance Basics : System Components • Camera • Analog or IP • Fixed or PTZ (Pan, Tilt, Zoom) • Standard or High definition • Encoder • Typically consists of a modular analog to IP video converter • Supports different encoding formats • MJPEG, MPEG2, MPEG4 (part2), H.264 • DVR/NVR • Digital or Networked Video Recorder • Video Management System • Centralized, Distributed • Control Center • Display Wall • Storage • Network

  12. Integrated Video Surveillance Solution - Network • Wire line • Broadband access: ADSL, VDSL, LAN • Leased line: G.SHDSL • Transmission: SONET,DWDM • Wireless • PTP: Microwave • Point to multi-point: LMDS • Wireless broadband access:WiMAX, WiFi • Switching/Routing • L2/L3, MPLS

  13. Source Core Receiver Aggregation Receiver Access Source Video Surveillance Network • Has to be built for: • Operational flexibility • Scalability • Redundancy Should have: • Standards Compliancy • RAMS • Reliability • Availability • Maintainability • Safety

  14. Video surveillance in the context of Computer Vision • Detection and tracking of moving objects are the important tasks of the computer vision. • The video surveillance systems not only need to track the moving objects but also interpret their patterns of behaviours. This means solving the information and integration the pattern. • Advantages • Minimizes the user interaction. • Less amount of prohibitive bandwidth. • Minimizes the cost and time.

  15. Need for Traffic Monitoring • To reduce the traffic congestion on highways • Reduce the road accidents • Identifying suspicious vehicles. Etc..,

  16. Traffic Monitoring in Computer Vision • The quest for better traffic information, an increasing reliance on traffic surveillance has resulted in a better vehicle detection. • Taking some intelligent actions based on the conditions. • Traffic scene analysis in 3 categories. • A strait forward vehicle detection and counting system . • Congestion monitoring and traffic scene analysis. • Vehicle classification and tracking systems which involve much more detailed scene traffic analysis.

  17. Responsibilities of reliable Traffic Monitoring System • Adaptive to changes in the real world environments • Easy to set up • Capable of operating independently of human operators. • Capable of intelligent decisions. • Capable of monitoring multiple cameras and continuous operation. • Reasons for unsuccessful implementation**

  18. A Traffic Monitoring System

  19. Object Classification • Shape based classification. • Image blob area, blob bounding box • Classification based on above info. • Motion-based classification. • Human motion shows periodic property. • Time frequency analysis applied. • Residual flow taken under consideration.

  20. Object tracking strategies (I)* • Background subtraction • Difference between the current image and the reference background image in a pixel by pixel fashion. • Sensitive to the background changes • Wallflower principles for effective background maintenance.

  21. Object tracking strategies (II) • Temporal differencing • Moving objects changes intensity faster than static ones • Uses consecutive frames to identify the difference. • Adaptive to dynamic scene changes • Problems in extracting all relevant features. • Improved versions uses three frames instead of two

  22. Object tracking strategies (III) • Optical flow • To identify characteristics of flow vectors of moving objects over time. • It’s used to detect independently moving objects in presence of camera. • Requires a specialized hardware to implement. Optical flow of moving objects Meyer et al

  23. Vehicle detection techniques • Model based detection • Region based detection • Active contour based detection • Feature based detection

  24. Vehicle detection technique (I) • Model based Tracking • The emphasis is on recovering trajectories and models with high accuracy for a small number of vehicles. • The most serious weakness of this approach is the reliance on detailed geometric object models. Disadvantage • It is unrealistic to expect detailed models for all vehicles that could be found on the roadway

  25. Vehicle detection technique (II) • Region based tracking • It detects each vehicle blob using a cross correlation function. • Vehicle detection based on back ground subtraction. Disadvantage • Difficult to detect the vehicles under congested traffic, because vehicles partly occlude with one another Potential segmentation problem

  26. Vehicle detection technique (III) • Active contour based detection • Tracking is based on active contour models, or snakes. • Representing object in bounding contour and keep updating it dynamically. • It reduced computational complexity compared to the region based detection. Disadvantage: • The inability to segment vehicles that are partially occluded remains a problem. Bounding counters

  27. Vehicle detection technique (IV) • Feature based detection • Tracks sub-features such as distinguishable points or lines on the object • Effectiveness improved by the addition of common motion constraint. Features are grouped together based on common motion, avoiding segmentation problem due to occlusion

  28. A typical vehicle tracking procedure

  29. Wallflower Principles & Practice of Background Maintenance. • Foreground capture • Stopped car • Moving car • Shadows • Bootstrapping • Moved objects • Time of day • Light switch • Waving trees • camouflage

  30. Wallflower: Three levels of abstraction • Pixel level • Maintains models of back ground of each individual pixel. • Processing makes the preliminary classification between foreground and background • Dynamic to scene changes. • Region level • Emphasis is on interrelationship between the pixels • Helps to refine raw classification at pixel level • Frame level • It watches for the sudden changes in the large parts of the image and swaps in alternative background models.

  31. A real time traffic monitoring system Feature based tracking algorithm • Camera calibration • Feature detection • Vehicle tracking • Feature grouping Benjamin Coifman, Jitendra Malik, David Beymer

  32. Offline camera definition • Line correspondences for a projective mapping. • A detection region near the image bottom and an exit region at the image top • And multiple fiducialpoints for camera calibration Based on the above information the system computes the homography between the image coordinates(x,y) and the world coordinates(X,Y)

  33. On-line tracking and grouping • Detector • Detecting corners at the bottom of image, where brightness varies in more than one direction. • Detection operationalzed by the points in the image I • Tracker • Uses kalman filters to predict the velocity in the next image. • Normalized correlation is used to search the small region of image. • Group • Grouper uses common motion constraint. • Once all the corner features are identified they are grouped together. • Monitoring the distance between the point d(t)=P1(t)-p2(t)

  34. 2 Sample feature tracks from the tracker 1 3 Sample corner features identified by the tracker Sample feature groups from the tracker