A Vision Sensor System for Intelligent Vehicles

This paper proposes a vision sensor system to facilitate safer driving. The proposed system utilizes two low-cost compact Complementary Metal-Oxide Semiconductor (CMOS) cameras as vision sensors and an effective real-time detection algorithm to detect front vehicles and measure distances. Further, a custom-made binocular is used to capture pairs of images via a low-cost grabber card. This low-cost vision sensor is an asynchronous vision system because the left and right images have a slight time difference. However, the proposed detection algorithm, which comprises four modules-namely, image preprocessing, vehicle detection, detected vehicle tracking, and distance measurement-is unrestrained by the limitations of the epipolar constraints for synchronous vision systems, and also enables the system to overcome the asynchronous detection problem affecting conventional low-cost vision systems. The results of long-term performance tests conducted on highways and urban and country roads confirm that the proposed system can successfully detect the distance of the front vehicle with detection rates of up to 99%, and detect the distances of front vehicles under various weather and illumination conditions with detection rates of up to 93%.

關鍵字

vision sensor ； intelligent vehicles ； stereo vision system ； disparity

並列摘要

本論文提出一種視覺感測系統，以增進安全的駕駛。所提出的系統利用兩個低成本的小型互補式金屬氧化物半導體（CMOS）相機作為視覺感測器，運用有效的即時偵測演算法來偵測前方車輛和測量距離。此外，客製化的雙鏡頭是經由擷取卡來依序擷取成對的影像，因為左和右影像具有輕微的時間差，所以這種低成本視覺感測器屬於非同步的視覺系統。本論文提出的偵測演算法包含四個模組，分別為影像預處理、車輛偵測、追踪已偵測的車輛及距離測量。利用所提出的偵測演算法解決低價的非同步拍攝影像視覺偵測的問題，使得立體視覺的偵測可以不受到同步拍攝系統的限制。針對高速公路、城市和鄉村道路進行長期性能測試的結果，證實該系統成功地偵測前方車輛距離高達99％的偵測率，在各種天氣狀況下和照明條件下，偵測前方車輛距離的偵測率高達93％。

並列關鍵字

視覺感測；智能車輛；立體視覺系統；視差

主題瀏覽