深度学习的车道线检测方法

Lane Line Detection Method Based on Deep Learning

随着人工智能技术的不断发展,无人驾驶技术已经成为当下社会发展的热门,车道线检测是无人驾驶技术的关键一环,但传统的基于视觉的车道线检测方法处理时间较长、过程繁琐、需要人为干预。基于深度学习的车道线检测可大大减少此类问题。文章设计了一个完成双任务的Enet网络,分别解决目标区域分割问题和不同车道区分问题,以实现端到端的检测。与主流车道线检测网络模型deeplab v3和YOLO v3进行对比。实验验证表明,网络模型的最终训练准确率为99.8%,相对于deeplab v3和YOLO v3网络分别提升1.2%和0.8%。

With the continuous development of artificial intelligence technology,driverless technology has become a hot topic in the current social development.Lane line detection is a key link of driverless technology,but the traditional vision-based lane line detection method takes a long time to process,and the process is tedious,requiring human intervention.The lane line detection based on deep learning can greatly reduce such problems.In this paper,an Enet network is designed to complete dual tasks,which solves the problem of target area segmentation and different lane differentiation respectively to achieve end-to-end detection.Compared with mainstream lane line detection network models deeplab v3 and YOLO v3,the experimental verification shows that the final training accuracy of the network model used in this experiment is 99.8%,which is 1.2%and 0.8%higher than deeplab v3 and YOLO v3,respectively.