Lightweight Deep Learning for Road Environment Recognition

Abstract

With recent developments in the field of autonomous driving, recognition algorithms for road environments are being developed very rapidly. Currently, most of the network models have good recognition rates, but as the accuracy rate increases, the models become more complex and thus lack real-time performance. Therefore, there is an urgent need to propose a lightweight recognition system for road environments to assist autonomous driving. We propose a lightweight road environment recognition system with two different detection routes based on the same backbone network for objects and lane lines. The proposed approach uses MobileNet as the backbone network to acquire the feature layer, and our improved YOLOv4 and U-Net allows the number of parameters of the model to be greatly reduced and combined with the improved attention mechanism. The lightweight residual convolutional attention network (LRCA-Net) proposed in this work allows the network to adaptively pay attention to the feature details that need attention, which improves the detection accuracy. Finally, the object detection model and the lane line detection model of this lightweight road environment detection system evaluated on the PASCAL VOC dataset and the Highway Driving dataset show that their mAP and mIoU reach 93.2% and 93.3%, respectively, achieving excellent performance compared to other methods.