Vehicle Reidentification in Low-Resolution Videos for Travel Time Estimation

Wenchao Jiang, Haohan Li, Yao-Jan Wu, Zhaozheng YinTransportation 2015

Abstract

Vehicle reidentification is investigated as a method to analyze the traffic system, such as the estimation of travel time distribution in freeway network. In this paper, a vision-based algorithm is proposed to match vehicles between upstream and downstream videos captured by low-resolution (360*240) surveillance cameras and then estimate the travel time distributions. The algorithm consists of three stages: 1. Vehicles are detected by Motion History Image (MHI) and Viola-Jones vehicle detector, and then image segmentation and warping are conducted to the detected vehicle images; 2. Features (e.g., size, color, texture) are extracted from vehicle images to uniquely describe each vehicle in low-resolution images; 3. Vehicles from two cameras are matched by solving two problems: Support Vector Machine (SVM) to classify a pair of vehicles to be identical or not and linear programming to globally match groups of vehicles between upstream and downstream cameras with context constraints. The proposed algorithm is validated on two sections of freeway in St Louis, United States, which outperforms the state-of-the-art methods and accurate travel time estimation is achieved based on the reidentification results.
BibTeX
@inproceedings{jiang2015vehicle,
  author = {Wenchao Jiang and Haohan Li and Yao-Jan Wu and Zhaozheng Yin},
  title = {{Vehicle Reidentification in Low-Resolution Videos for Travel Time Estimation}},
  booktitle = {Transportation},
  year = {2015},
}

Loading related content...

Figure