Dissertation > Excellent graduate degree dissertation topics show

Video-based motion detection and tracking algorithm for human

Author: LuZhenShan
Tutor: ChenQingLin
School: Nanjing University of Technology and Engineering
Course: Control Theory and Control Engineering
Keywords: detection tracking Kalman adaptive feature select
CLC: TP391.41
Type: Master's thesis
Year: 2010
Downloads: 241
Quote: 0
Read: Download Dissertation

Abstract


Detection and tracking of the body targets in video image is a fundamental step in many vision system including intelligent surveillance and humen-machine interface.The design and implementation of algorithms for detection and tracting of body targets are given in this paper.A common solutation for detection of moving objects in video images is to use Gaussian mixture model to represent per pixel,but it suffers form solw learing at the beginning,in-additon,a promblem of this approache is balancing between speed and stabillity. This paper present a effective scheme which reconstruct the background model using frame substracti-on.we get the background model from pixel which keeping stability in the several images of frame substraction. A comparision has been made between the two methods,result show that our system learn faster as well as better segmentation.Meanshift algorithm doesn’t consider the target’s motion direction and speed information, and it easily fails to track the target when affected by complex environment or occlusion dist-urbence.on the one hand,this paper propse an algorithm combined Kalman filter with Meansh-ift altorithm,the position of the target can be predicted by the Kalman of the approache, it can solve defects above.on the other hand,considering the Meanshift applay to track with certain spatial aspectst,an improve method that based on adaptive features select is presented in this paper.by combining the hue space and gray gradiant space and the current feature space was selected dynamically according to the distance defined in this paper.inaddition,a practical trac-king system is required to update the appearance change of moving object,a intergal projecti-ion has been introduced into humen targets in this paper.The experiental testing demonstrated that the tracking algorithm worked better than Combining Meanshift and Kalman algorithm in complex environment and occlusion case.it also can realize the real-time humen targets track-ing while ensuring the tracking veracity.

Related Dissertations

  1. High Dynamic Carrier Tracking Algorithm of Software GNSS Receiver,P228.4
  2. Research and Realization on Synchronization Technology of High Sensitivity GNSS Software Receiver,P228.4
  3. Signal Detection Circuit Design for Slow-Light Optic Fiber Gyroscope,V241.5
  4. Research on Gyro Stabilized and Tracking Platform,V241.5
  5. Realization of Fiber Optic Gyroscope Signal Processing Circuits Based on FPGA,V241.5
  6. The Research of Navigation Multi-Sensor Data Fusion Technology Based on Micro Unmanned Platform,V249.32
  7. Algorithm Research on SINS/GPS Integrated Navigation Syste,V249.328
  8. Satellite Attitude Determination Based on Gyro and Star Sensor,V448.2
  9. Research on Transfer Alignment of the Missile Onboard the Aircraft,V249.322
  10. Polarized-Light/Geomagnetism/GPS/SINS Integrated Navigation Algorithm,V249.328
  11. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  12. Research of Image Guided Technology for Cable Tunnel Patrol Vehicle,U469.6
  13. Well Detection Pump Steady-Speed Driving System of Brushless DC Motor,TM33
  14. Research on Autamatic Music Structrue Analysis,TN912.3
  15. Research of Electromagnetic Tracking Experimental System for Medical Application,TN966
  16. Research on 8 Mm-Band Direct Detection Radiometer,TN850.7
  17. Research on Intelligent Learning-Based Multi-Sensor Target Recognition and Tracking System,TP391.41
  18. Research on Joint Target Detection for Dual-Sensor Image and System Implementation,TP391.41
  19. Research on Visual Measurement for Spacecraft Rendezvous and Approach,TP391.41
  20. Multi-currency Notes Technology Research and Implementation,TP391.41
  21. The Research of Moving Object Tracking System Based on Embeded Image Process Unit,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