Loading...
|
Please use this identifier to cite or link to this item:
http://ntour.ntou.edu.tw:8080/ir/handle/987654321/44049
|
Title: | Real-time dynamic vehicle detection on resource-limited mobile platform |
Authors: | Duan-Yu Chen Guo-Ruei Chen Yu-Wen Wang Jen-Yu Yu Jun-Wei Hsieh Chi-Hung Chuang |
Contributors: | 國立臺灣海洋大學:資訊工程學系 NTOU:Department of Computer Science and Engineering |
Keywords: | Vehicle detection Haar-like feature eigencolor |
Date: | 2012-07
|
Issue Date: | 2017-11-13T07:21:12Z
|
Publisher: | International Conference on Machine Learning and Cybernetics |
Abstract: | Abstract:Given the rapid expansion of car ownership worldwide, vehicle safety is an increasingly critical issue in the automobile industry. The reduced cost of cameras and optical devices has made it economically feasible to deploy front-mounted intelligent systems for visual-based event detection. Prior to vehicle event detection, detecting vehicles robustly in real time is challenging, especially conducting detection process in images captured by a dynamic camera. Therefore, in this paper, a robust vehicle detector is developed. Our contribution is three-fold. Road modeling is first proposed to confine detection area for maintaining low computation complexity and reducing false alarms as well. Haar-like features and eigencolors are then employed for the vehicle detector. To tackle the occlusion problem, chamfer distance is used to estimate the probability of each individual vehicle. AdaBoost algorithm is used to select critical features from a combined high dimensional feature set. Experiments on an extensive dataset show that our proposed system can effectively detect vehicles under different lighting and traffic conditions, and thus demonstrates its feasibility in real-world environments. |
URI: | http://ntour.ntou.edu.tw:8080/ir/handle/987654321/44049 |
Appears in Collections: | [資訊工程學系] 演講及研討會
|
Files in This Item:
File |
Description |
Size | Format | |
index.html | | 0Kb | HTML | 37 | View/Open |
|
All items in NTOUR are protected by copyright, with all rights reserved.
|