Lane detection algorithm based on MoblieNet + UNet lightweight network

In order to meet the requirements of high accuracy, high real-time and low number of parameters in lane detection algorithm in industrial practice, a lightweight network detection algorithm based on MoblieNet+UNet is proposed. This method takes UNet as the main structure of the network and applies MoblieNet to the process of network encoding. MoblieNet can decompose standard convolution into deep convolution and pointwise convolution when encoding. It can significantly reduce the amount of network parameters and improve the real-time performance of detection algorithm. At the same time, the UNet network framework can also segment the pixels with high precision, which ensures the accurate extraction of lane information. The experimental results show that the average cross merge ratio of the training set is 87% and 82.1 % respectively on the MHDD and bctd data sets, and the average cross merge ratio of the verification set is 84.5% and 81.6% respectively. The average time of a single frame in the PC terminal is 40ms. Experimental results show that the algorithm can extract lane line features in complex environment efficiently and accurately.