Stop-and-go and Top-view Obstacle Detection based on Dynamic Vision

• Main Authors: Lan-Yi Kang, 藍易康
• Other Authors: Din-Chang Tseng
• Format: Others
• Language: zh-TW
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/83329889085318959910

碩士 === 國立中央大學 === 資訊工程研究所 === 98 === It is inconvenience and danger while driving in urban areas. Drivers spend much time waiting for traffic signals and stuck in jams. Lack of concentration at such moments may lead to accidents. Due to the limitation of field of view, drivers are mostly unable to see all the area around the vehicle during driving. For the safety of drivers, the stop-and-go and top-view obstacle detection methods are proposed in this study. Corners are used as features to calculate optical flow. We perform stop-and-go and top-view obstacle detections based on the optical flow. In the stop-and-go detection method, we first filter optical flow and adjust the length of optical flow. The length of optical flows of an object is almost the same. The adjusted length is used as the condition for clustering. Then, we use these moving objects to recognize whether the front vehicle is stopping or going. This detection method can also avoid the effects of vehicles in different direction, variant weather, and the light at nighttime. In the top-view obstacle detection method, the direction, position, and length of optical flows are used as condition for clustering. By analyzing the trajectory of moving objects and computing the possible collision time, we can recognize whether the moving object is dangerous. The proposed methods are evaluated in several variant environments. The detection rate of stop-and-go method is 99? and the frame rate is 25 frames per second. The detection rate of the top-view detection method is 98? and the frame rate is 30 frames per second.