Dissertation > Excellent graduate degree dissertation topics show

Research on People Counting in Real-time Video Surveillance

Author: SunTongYi
Tutor: LuHuanZhang
School: National University of Defense Science and Technology
Course: Information and Communication Engineering
Keywords: Video surveillance Statistics on the number Background modeling Shadow Elimination Target tracking
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 90
Quote: 0
Read: Download Dissertation

Abstract


With the social and economic development, the video surveillance system in all aspects of a wide range of applications. The use of computer vision technology to improve the level of intelligent video surveillance system, reduce the participation of the people, is the development direction of the video surveillance system. Video surveillance system for the platform, the statistics in the detection and tracking of pedestrians in video sequences based on the precise number of extremely important significance, the video surveillance statistics on the number of technology has become a hot topic in the field of computer vision and difficulty. The paper studies the number of video surveillance statistical image processing algorithms, through analysis of existing moving target detection and tracking algorithms, design of the video surveillance statistics on the number of information processing algorithm processes the video people counting algorithm is divided into moving object detection, moving target tracking and trajectory analysis of the three main sections. Moving object detection is the basis of video demographics, this feature of the fixed background of video surveillance systems, the background subtraction method for moving object extraction. Focus on selective background updating model and Gaussian mixture model, comparison of the two models, improved selective background updating model, put forward on the basis of a robust, real-time and good background estimated method. The estimated background, color background subtraction method to extract the target. For the post-processing of the foreground image, the method using morphological first filtering to remove noise, and then using the luminance combined normalized color information Elimination of the shadow of the moving target, and finally using motion history image so that the detected target is more complete. Moving target tracking, feature target tracking method based on the area, the use of regional characteristics of the target matching tracking. Stable track to achieve the goal, we must overcome the impact of occlusion, occlusion handling is divided into static occlusion and dynamic occlusion of two aspects of the research, and focus on a key pedestrian merger, separation has a significant impact on accurate statistics on pedestrian Finally, the effectiveness of the algorithm is verified by experiment. Achieve the pedestrians stable tracking based on analysis of the trajectory of the target, an effective pedestrian counting judgment method, this method can solve the problem of the number of people out of the room statistics, and exclude pedestrian complex motion count impact. Papers in order to improve the real-time algorithms and practical goal, several key statistics on the number of video surveillance technology, an algorithm of low complexity, robustness and number of video surveillance statistical algorithms, and achieved good Experimental results.

Related Dissertations

  1. Maneuver Detection and Tracking with the Radar Rate Measurement,TN953
  2. The Maneuvering Target Tracking Research Based on VRPF,TN957.52
  3. Research on Multi-Sensor Embattling and Continious Tracking Technique Applying for Anti-Stealth and Anti-Interference,TN953
  4. Moving target trajectory analysis based Intelligent Traffic Monitoring System,TP277
  5. Intelligent video detection technology based on the traffic lights control,TM923.5
  6. Research and Application on Detection and Tracking of Object Based on Video Stream,TP391.41
  7. Detection and Tracking of Moving Object in Complex Background,TP391.41
  8. Design of Ad hoc Network Application Based on Linux Platform,TN929.5
  9. Algorithm Analysis about Traget Tracking in Wireless Sensor Network,TN929.5
  10. The Research on the Target Localization and Tracking Based on WSN,TN929.5
  11. Research on Moving Object Retrieval for Video Surveillance,TP391.41
  12. Research of Moving Object Detection and Tracking Technology,TP391.41
  13. Object Detection and Tracking in Video Image,TP391.41
  14. Pedestrian Detection and Tracking Technology of Vehicle Infrared Image,TP391.41
  15. The Research on Localization and Target Tracking in Wireless Sensor Network,TN929.5
  16. Research and Implementation of Audio and Video Communi Cation Program in the Smart Home.,TN919.8
  17. Connected Cross-regional DVR Achieves Play and Play Back Function Based on DB33,TP391.41
  18. Multi-target tracking algorithm,TN953
  19. Driverless smart car moving target detection and tracking,TP391.41
  20. Video surveillance target behavior analysis,TP391.41
  21. Multi-target detection and tracking method of visual and video surveillance software platform development,TP391.41

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net  Mobile