Loading...

Detecting and Tracking Desired Objects in Consecutive Images

Panahi, Rahim | 2013

751 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 45105 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Gholampour, Iman; Movahhedian, Hamid
  7. Abstract:
  8. Detection and Tracking objects in various environmental conditions is a challenging task in computer vision. Abrupt changes in illumination, object size and noise level make this task even harder. Due to these problems, it is somehow impossible to propose a fully functional system for tracking every type of object. In this thesis we propose a new method for detection and tracking vehicles in traffic scenes. The problem is solved by dividing it into two parts: at First we have evaluated more than ten state-of-the art trackers, the final multi-vehicle tracker is chosen, and then, like any other object tracking method, we have used a unique identiy for each vehicle. This traffic identity is known as vehicle plate. Vehicle plate is the only trustable identity that can be used in issueing traffic fines and recording traffic violations. In this thesis, we propose a new algorithm to detect vehicles based on their plates and backlights. The vehicles are tracked using a mixture of two background subtraction methods: GMM and Mean-Block. Mean Shift algorithm is used for detecting vehicles body. Color is used as input feature for this algorithm. The Final accuracy for detection of plates is 98.5%. The recognition process of detected plates is done with 97.6% accuracy. We evaluated our method over two previous datasets by other researches. Our methoud outperformed on their methods in detecting and recognizing plates. The tracking algorithm is also tested for traffic videos. Our implemented tracking algorithm is capable of tracking vehicles in real-time. The evaluation is done on a normal PC platform
  9. Keywords:
  10. Traffic ; Tracking ; Plate Detection ; Plate Recognition ; Background Subtraction ; Intelligent Transportation System (ITS) ; Optical Character Recognition (OCR) ; Object Detection

 Digital Object List

 Bookmark

No TOC