College of Electronic Information Engineering, Chang Chun University of Science and Technology, Changchun 130022, China.
College of Artificial Intelligence, Chang Chun University of Science and Technology, Changchun 130022, China.
Sensors (Basel). 2023 Feb 23;23(5):2467. doi: 10.3390/s23052467.
The importance of panoramic traffic perception tasks in autonomous driving is increasing, so shared networks with high accuracy are becoming increasingly important. In this paper, we propose a multi-task shared sensing network, called CenterPNets, that can perform the three major detection tasks of target detection, driving area segmentation, and lane detection in traffic sensing in one go and propose several key optimizations to improve the overall detection performance. First, this paper proposes an efficient detection head and segmentation head based on a shared path aggregation network to improve the overall reuse rate of CenterPNets and an efficient multi-task joint training loss function to optimize the model. Secondly, the detection head branch uses an anchor-free frame mechanism to automatically regress target location information to improve the inference speed of the model. Finally, the split-head branch fuses deep multi-scale features with shallow fine-grained features, ensuring that the extracted features are rich in detail. CenterPNets achieves an average detection accuracy of 75.8% on the publicly available large-scale Berkeley DeepDrive dataset, with an intersection ratio of 92.8% and 32.1% for driveableareas and lane areas, respectively. Therefore, CenterPNets is a precise and effective solution to the multi-tasking detection issue.
全景交通感知任务在自动驾驶中的重要性日益增加，因此高精度的共享网络变得越来越重要。在本文中，我们提出了一种名为 CenterPNets 的多任务共享感知网络，可一次性执行交通感知中的三个主要检测任务：目标检测、驾驶区域分割和车道检测，并提出了几个关键优化措施来提高整体检测性能。首先，本文提出了一种基于共享路径聚合网络的高效检测头和分割头，以提高 CenterPNets 的整体复用率，以及一种高效的多任务联合训练损失函数来优化模型。其次，检测头分支使用无锚框机制自动回归目标位置信息，以提高模型的推理速度。最后，分接头分支融合了深层多尺度特征和浅层细粒度特征，确保提取的特征细节丰富。CenterPNets 在公开的大型 Berkeley DeepDrive 数据集上实现了 75.8%的平均检测精度，对于可驾驶区域和车道区域，交并比分别为 92.8%和 32.1%。因此，CenterPNets 是解决多任务检测问题的精确而有效的解决方案。
