Journal of Electrical and Computer Engineering
| Hi-index | 0.00 |
In an embedded system, the hardware resources are limited. In order to obtain such traffic information as traffic volume and vehicle speed in an embedded system, a series of efficient video processing algorithms and optimization techniques are proposed. The key algorithm to detect vehicles is the background subtraction method, in which the approximated median filter is applied to obtain the simulated background. Parallelogrammatic "virtual loop" is used to restrict the calculation in an interested region in the traffic scene. Tracking of a vehicle is done by the detection and tracking of the front of it. Results show that the system can detect and track vehicles effectively and efficiently with these optimized algorithms.