Dissertation > Excellent graduate degree dissertation topics show

Image-based vehicle detection and tracking to keep track, line

Author: CaiAoShuang
Tutor: RenMingWu
School: Nanjing University of Technology and Engineering
Course: Applied Computer Technology
Keywords: intelligent transportation line detection subtracted image weighted Hough transform line tracking
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 53
Quote: 0
Read: Download Dissertation

Abstract


With the development of technology and society, the per capita consumption of motor vehicles increased rapidly and the traffic safety issues have been the world’s attention. The survey shows that many car accidents due to the car far away from the current vehicle line when the drivers are drunk or fatigue. Therefore, line detection and tracking is the important part of intelligent driving assistance system. This paper is the research around the line detection and tracking based on image.First, we do research and experiment on the segmentation based on the brightness estimation and multi-threshold. To deal with the character of camera, we use average filter to estimate the brightness of the road image, then subtracted by the original gray image. The minus image can highlight the line region in the road image. To adapt variety of climatic conditions, lighting conditions and other traffic with complex condition, we use multi-threshold segmentation method to replace a certain threshold which the segmentation result may be inaccurate.Second, we do research and experiment on the regions of interest precession based on estimates of the vanishing point. We calculate the vanishing point to determine the line region of interest (ROI). Then take advantage of the structural characteristics of the line, we propose interference cancellation method based on Run-Length and refine the line with fixed width. Through these steps can eliminate some noises such as:the fence of both sides on highway, the vehicles in front.Third, we do research and achieve the line selection based on the weighted Hough transform and space constraint conditions. We use the weighted Hough transform to extract the candidate lines, and then use the space constraint conditions to select lines. Last, we choose the most suitable pair of lines as detected lines.Finally, the using of Kalman filter to track and keep line. This method can adjust the case according to track the interest regions effectively. Also Kalman filter can shorten extract time and robustness can be further improved.After a large number of experiments show that the method in this paper can get suitable lines, where the method is robust and effective. This research also have some reference on intelligent transportation.

Related Dissertations

  1. Research on Autamatic Music Structrue Analysis,TN912.3
  2. The Recognization of License Plate Based on EMD and Its Application,TP391.41
  3. Study on the Road Condition Monitoring Based on Vehicular 3D Acceleration Sensor,TP274
  4. Based on ZigBee Technology Vehicle Traffic Information Collection System,TP274.2
  5. A Design of Intelligent Terminal in Internet of Vehicles and Research of Its Routing Algorithm,TP391.44
  6. Design and Implementation of Intelligent Transportation Video Monitoring System Based on 3G Network,TP391.41
  7. Research and Realization of Vehicle Detection and Tacking Algorithm Based on Video,TP391.41
  8. The Research of the Application of Neural Network in Short-Time Traffic Flow Forecasting,U491.112
  9. The Design of An Intelligent Online Electronic Ballasts Diagnosis System,TM923.61
  10. City Bus Transfer System Optimization Study and Implementation,U12
  11. The Description and Services of the Reference Frames System of Roads Meshwork,TP311.52
  12. Based on magnetoresistive sensors and ZigBee network traffic monitoring system ITS,TP277
  13. The Research of the Algorithm in Vehicles Speed Measurement Through Video Based on Moving Object Detection and Tracking,TP391.41
  14. Phone-based traffic information collection and processing technology,U495
  15. Guangzhou City Tramways Intelligent Bus Dispatch System Design and Implementation,U495
  16. Video-based sports vehicle trajectory access to research,TP391.41
  17. The Solution and Intelligent Arithmatic Research for Shanghai Yangtze Tunnle Bridge Monitoring System,TP277
  18. The Development of Intelligent Vehicle Detector,U495
  19. Video Vehicle Detection Algorithm Based on Gaussian Model and Condensation Filter,TP391.41
  20. The Design and Realization of Vehicle Information Detecting System Based on Ultrasonic Technology,U495
  21. PLC-based intelligent adaptive traffic light control system design,TP273.5

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