期刊名称：International Journal of Advances in Engineering and Management
电子版ISSN：2395-5252
出版年度：2021
卷号：3
期号：6
页码：192-197
DOI：10.35629/5252-03063037
语种：English
出版社：IJAEM JOURNAL
摘要：The promising key issue of automobiledevelopment is a self-driving technique. One of the keychallenges for intelligent selfdriving cars includes alane-detecting and lanetracking capability for driverassistance systems. Driverless vehicles need to learn toobserve the road from the visual point of view if theywant to achieve automatic driving, which specifically isthe detection of road lines. Most research works couldonly detect the lanes or vehicles separately.However,the combination of laneinformationandvehicle/obstacle informationcan support the driverassistance system or the lane change assistant systemand enhance the quality of results. For the lane changeassistant system (LCAS), it must detect the lane linesand detect the vehicles around a test vehicle. In the lanedetection, line detection is used. Canny Edge detectionalgorithm is used to detect the lane edges. For vehicledetection, we use the horizontal edge filter, the Otsu’sthresholding, and the vertical edge. The horizontal edgefilter and the Otsu’s thresholding are used to detect thevehicles around the test vehicles, then the vertical edgeis used to verify the vehicles detected.
