School of Automation, Chongqing University, Chongqing, China.
School of Traffic & Transportation, Chongqing Jiaotong University, Chongqing, China.
PLoS One. 2022 Mar 4;17(3):e0264551. doi: 10.1371/journal.pone.0264551. eCollection 2022.
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.
针对道路场景中的车辆和车道检测，本文提出了一种适用于跟驰场景的车辆和车道线联合检测方法。该方法采用编解码器结构和多任务思想，共享特征提取网络和特征增强融合模块。同时使用 ASPP（空洞空间金字塔池化）和 FPN（特征金字塔网络）来提高 MobileNetV3 的特征提取能力和实时性，将注意力机制 CBAM（卷积块注意力模块）引入 YOLOv4 中，为语义像素级分割网络设计了“更多编码-更少解码”的非对称网络架构。所提出的模型采用改进的 MobileNetV3 作为特征提取块，YOLOv4-CBAM 和 Asymmetric SegNet 分别作为分支来检测车辆和车道线。该模型在 BDD100K 数据集上进行训练和测试，同时在 KITTI 数据集和重庆道路图像上进行测试，重点关注跟驰场景中的检测效果。实验结果表明，所提出的模型在 BDD100k 上比 YOLOv4 大幅提高了+1.1 AP50、+0.9 召回率、+0.7 F1 和+0.3 精度，比 SegNet 大幅提高了+1.2 IoU。同时，检测速度分别是 YOLOv4 和 SegNet 的 1.7 倍和 3.2 倍。充分证明了改进方法的可行性和有效性。
