State Key Laboratory of Mechanical Transmission, College of Mechanical Engineering, Chongqing University, Chongqing 400044, China.
State Key Laboratory of Mechanical Transmission, College of Automotive Engineering, Chongqing University, Chongqing 400044, China.
Sensors (Basel). 2018 Dec 6;18(12):4308. doi: 10.3390/s18124308.
To improve the accuracy of lane detection in complex scenarios, an adaptive lane feature learning algorithm which can automatically learn the features of a lane in various scenarios is proposed. First, a two-stage learning network based on the YOLO v3 (You Only Look Once, v3) is constructed. The structural parameters of the YOLO v3 algorithm are modified to make it more suitable for lane detection. To improve the training efficiency, a method for automatic generation of the lane label images in a simple scenario, which provides label data for the training of the first-stage network, is proposed. Then, an adaptive edge detection algorithm based on the Canny operator is used to relocate the lane detected by the first-stage model. Furthermore, the unrecognized lanes are shielded to avoid interference in subsequent model training. Then, the images processed by the above method are used as label data for the training of the second-stage model. The experiment was carried out on the KITTI and Caltech datasets, and the results showed that the accuracy and speed of the second-stage model reached a high level.
为了提高复杂场景下的车道检测精度，提出了一种自适应的车道特征学习算法，该算法能够自动学习各种场景下的车道特征。首先，构建了一个基于 YOLO v3（You Only Look Once，v3）的两阶段学习网络。修改了 YOLO v3 算法的结构参数，使其更适合车道检测。为了提高训练效率，提出了一种简单场景下自动生成车道标签图像的方法，为第一阶段网络的训练提供了标签数据。然后，采用基于 Canny 算子的自适应边缘检测算法对第一阶段模型检测到的车道进行重定位。此外，屏蔽未识别的车道，以避免在后续模型训练中产生干扰。然后，将经过上述方法处理的图像作为第二阶段模型的训练标签数据。在 KITTI 和 Caltech 数据集上进行了实验，结果表明，第二阶段模型的准确性和速度达到了较高水平。
Zotero 插件
