Abstract
Aiming at vehicle and lane detections on road scene, this paper proposes a vehicle and lane line joint detection method suitable for car following scenes. This method uses the codec structure and multi-task ideas, shares the feature extraction network and feature enhancement and fusion module. Both ASPP (Atrous Spatial Pyramid Pooling) and FPN (Feature Pyramid Networks) are employed to improve the feature extraction ability and real-time of MobileNetV3, the attention mechanism CBAM (Convolutional Block Attention Module) is introduced into YOLOv4, an asymmetric network architecture of "more encoding-less decoding" is designed for semantic pixel-wise segmentation network. The proposed model employed improved MobileNetV3 as feature ex-traction block, and the YOLOv4-CBAM and Asymmetric SegNet as branches to detect vehicles and lane lines, respectively. The model is trained and tested on the BDD100K data set, and is also tested on the KITTI data set and Chongqing road images, and focuses on the detection effect in the car following scene. The experimental results show that the proposed model surpasses the YOLOv4 by a large margin of +1.1 AP50, +0.9 Recall, +0.7 F1 and +0.3 Precision, and surpasses the SegNet by a large margin of +1.2 IoU on BDD100k. At the same time, the detection speed is 1.7 times and 3.2 times of YOLOv4 and SegNet, respectively. It fully proves the feasibility and effectiveness of the improved method.
Highlights
Accurate road environment perception and understanding are crucial for the realization of autonomous driving, which provide the decision system to operate the vehicle with information including: locations, lanes, obstacles, drivable area, and so on
The loss function of the vehicle and lane line multi-task joint detection model is more complicated than single vehicle or lane line detection, because it is necessary to measure the loss of vehicle and lane line detection at the same time
In order to reduce the amount of model parameters and improve the speed of detection and segmentation, the lightweight network MobileNetV3 is employed as the backbone network, which greatly improves the detection speed of the network
Summary
Accurate road environment perception and understanding are crucial for the realization of autonomous driving, which provide the decision system to operate the vehicle with information including: locations, lanes, obstacles, drivable area, and so on. The cost of laser radar is very high, though it has been used to detect lane lines [2, 3] and vehicle [4]. The SCNN [8] and SAD-ENet [9] networks are used for lane line detection These methods usually handle vehicle or lane line detection tasks separately. Multi-Task Learning uses same backbone to extract feature and multi heads to deal with multitasks [10] It could be more efficient for multi detection tasks for autonomous driving. In this paper, we attempt to design a simple and efficient network to detect vehicle and lane line at the same time.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
