Pixel segmentation is one of the most commonly used deep learning methods for modern lanelinedetection. Although deep segmentation outperforms traditional methods, there are two main problems: slow speed and limited...
详细信息
Pixel segmentation is one of the most commonly used deep learning methods for modern lanelinedetection. Although deep segmentation outperforms traditional methods, there are two main problems: slow speed and limited receptive field. In response to these problems, this paper proposes a lightweight lane line detection algorithm based on learnable cluster segmentation and self-attention mechanism, which has extremely fast speed and the ability to adapt to real scenes. The lanedetection process is considered as clustering under row segmentation. The data is processed through row segmentation and fed into a self-attention mechanism. In addition to the benchmark dataset for lanedetection, the algorithm was ported to real vehicles for real-time road testing. Two tests show that our method performs very well on TuSimple, with an accuracy of 97.15%, an F1 score of 73.5 on CUlane, and a speed of 142.7 frames per second (FPS), which solves the problem of slow cluster segmentation, while improving the accuracy of row segmentation. In the new scenario, the method has a misjudgment rate of only 6.7% for laneline points, which is suitable for the high standard requirements of autonomous driving.
暂无评论