Title: |
Vehicles Detection Algorithm for the High-Definition Image Based on Edge Information |
Source: |
Proceedings of 2009 Conference onCommunication Faculity (PCCF 2009 E-BOOK)
(pp 77-81)
|
Author(s): |
Zhitong Su, North China University of Technology, Beijing, China Jianjun Xiao, North China University of Technology, Beijing, China Changzhen Xiong, North China University of Technology, Beijing, China |
Abstract: |
For vehicles in the detection of high-definition images, although the existing background modeling methods can extract the vehicle prospect, but with too much computation, while exists empty and chasm in the detected vehicle regions. This article proposes a prospect-extraction algorithm based on the high clear image. First of all, we need to remove the interference region to reduce the computation by setting the region of interest. Secondly, we will definite vehicle region through the background difference algorithm and edge detection, then contour tracing of the contours to extract the complete contour of the vehicle. The experimental results show that the algorithm does not need to model, and with high speed in high-definition image vehicle detection. Compared with existing methods, this algorithm can extract the vehicle completely with higher speed, solving the empty and chasm caused by the existing background modeling algorithms, and can apply to high-definition graphics applications.
|