Dissertation > Excellent graduate degree dissertation topics show

Research of Real-time Object Tracking Based on Computer Vision

Author: LiZhiCheng
Tutor: QiaoBing
School: Nanjing University of Aeronautics and Astronautics
Course: Guidance and Control
Keywords: Moving target detection and tracking Computer vision Camshift algorithms Kalman filter Region Of Interest (ROI) Velocity information
CLC: TP391.41
Type: Master's thesis
Year: 2009
Downloads: 116
Quote: 0
Read: Download Dissertation

Abstract


Computer vision is becoming the most important way for intelligent machines to access external information and understand the world. Moving target detection and tracking are among the most important subjects in computer vision, and have been hot issues of international research in recent years. As a technology to anlyse and synthesis the image series which contains the moving object, moving target detection and tracking integrated many advanced technologies such as image processing, pattern recognition, artificial intelligence, automatic control, computer and other related fields. It can be used in many aeraes such as security surveillance, traffic control, visual navigation, video surveillance, medical image analysis and industrial detection.This paper researches the visual detection and tracking algorithms of moving object based on image processing and Kalman filter techniques after surveying the current research literatures in this domain. Camshift, which is a visual tracking method based on the color features of moving object, has been widely accepted and used for its advantages of parameter-less and fast calculation. But the conventional Camshift algorithm uses only one Region Of Interest (ROI) to search and track the target, which will inevitably result in the tracking divergence when the object passes the background with similar color to the target. Furthermore Camshift usually cannot recapture the object after the target is lost because the algorithm relies on the color distributions alone. To remedy these drawbacks of the conventional Camshift, a modified Camshif which utilizes dual ROI to enhance the robustness of the algorithm and prevent divergence is proposed in this paper. Meanwhile, the information of the velocity of the moving object is introduced into the algorithm to solve the problem of occlusion and enable the retracking of the lost object.In order to test and verify the efficiency of the proposed algorithms, different cases of experiments are conducted. The comparative experimental results between the conventional Camshift and the dual ROI Camshif with velocity information involved demonstrate that the Camshift tracking policy proposed in this paper has advantageous performance over traditional Camshift.

Related Dissertations

  1. Algorithm Research on SINS/GPS Integrated Navigation Syste,V249.328
  2. Satellite Attitude Determination Based on Gyro and Star Sensor,V448.2
  3. Research on Transfer Alignment of the Missile Onboard the Aircraft,V249.322
  4. Maneuver Detection and Tracking with the Radar Rate Measurement,TN953
  5. Research on Learning-Based Low-Level Vision Problem,TP391.41
  6. Research on Visual Detection and Tracking of Mobile Robots,TP242.62
  7. Design of Gyro Stabilized Pod Control System,TP273
  8. Research on Nondestructive Detection Technology for External Qualities of Papayas Based-on Vision,S667.9
  9. Study on Detection and Grading of ’Jiro’ Persimmon’s External Quality Based on Computer Vision,S665.2
  10. Prediction of Pork Processing Functionalities,TS251.1
  11. Research on Inspection Technology of Dehydrated Garlic Slice Based on Computer Vision,TP391.41
  12. Moving target trajectory analysis based Intelligent Traffic Monitoring System,TP277
  13. Research and Application on Detection and Tracking of Object Based on Video Stream,TP391.41
  14. Design Control Algorithm of A Dynamic Positioning System for the Large Trailing Suction Hopper Dredger,U674.31
  15. Two Wheel Electric Bicycle Self-balance Control Algorithm Research,TP273
  16. The Study of Moving Object Detection and Tracking Algorithm Based on Image Information,TP391.41
  17. Robot Localization in Fusion with Vision and Inertial Navigation,TP242
  18. Sensor Data Transmission and Processing of Inertia Motion Capture System,TP212
  19. AUV Integrated Navigation Algorithm Study and System Implementation,U666.1
  20. Video image sequence moving target acquisition and tracking,TP391.41
  21. Satellite Formation Satellite Relative Measurement Technology,V448.2

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