Robust Vehicle and Traffic Information Extraction for Highway Surveillance
| Autor: | C.-C. Jay Kuo, Akio Yoneyama, Chia-Hung Yeh |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2005 |
| Předmět: |
nighttime detection
Computer science Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION lcsh:TK7800-8360 occlusion computer.software_genre lcsh:Telecommunication Robustness (computer science) lcsh:TK5101-6720 Shadow Computer vision Electrical and Electronic Engineering Simulation object tracking background subtraction Background subtraction traffic monitoring business.industry lcsh:Electronics Information extraction moving cast shadow Hardware and Architecture Video tracking Signal Processing Artificial intelligence business computer |
| Zdroj: | EURASIP Journal on Advances in Signal Processing, Vol 2005, Iss 14, Pp 2305-2321 (2005) EURASIP Journal on Advances in Signal Processing, Vol 2005, Iss 14, p 912501 (2005) |
| ISSN: | 1687-6180 1687-6172 |
| Popis: | A robust vision-based traffic monitoring system for vehicle and traffic information extraction is developed in this research. It is challenging to maintain detection robustness at all time for a highway surveillance system. There are three major problems in detecting and tracking a vehicle: (1) the moving cast shadow effect, (2) the occlusion effect, and (3) nighttime detection. For moving cast shadow elimination, a 2D joint vehicle-shadow model is employed. For occlusion detection, a multiple-camera system is used to detect occlusion so as to extract the exact location of each vehicle. For vehicle nighttime detection, a rear-view monitoring technique is proposed to maintain tracking and detection accuracy. Furthermore, we propose a method to improve the accuracy of background extraction, which usually serves as the first step in any vehicle detection processing. Experimental results are given to demonstrate that the proposed techniques are effective and efficient for vision-based highway surveillance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink