Li Hao, Zhao Sanyuan, Zhao Wenjun, Zhang Libin, Shen Jianbing
Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing 100081, China.
State Key Laboratory of Smart Manufacturing for Special Vehicles and Transmission System, Inner Mongolia No.2 Mailbox, Baotou City 014030, China.
Sensors (Basel). 2021 Apr 9;21(8):2651. doi: 10.3390/s21082651.
Recent one-stage 3D detection methods generate anchor boxes with various sizes and orientations in the ground plane, then determine whether these anchor boxes contain any region of interest and adjust the edges of them for accurate object bounding boxes. The anchor-based algorithm calculates the classification and regression label for each anchor box during the training process, which is inefficient and complicated. We propose a one-stage, anchor-free 3D vehicle detection algorithm based on LiDAR point clouds. The object position is encoded as a set of keypoints in the bird's-eye view (BEV) of point clouds. We apply the voxel/pillar feature extractor and convolutional blocks to map an unstructured point cloud to a single-channel 2D heatmap. The vehicle's Z-axis position, dimension, and orientation angle are regressed as additional attributes of the keypoints. Our method combines SmoothL1 loss and IoU (Intersection over Union) loss, and we apply (cosθ,sinθ) as angle regression labels, which achieve high average orientation similarity (AOS) without any direction classification tricks. During the target assignment and bounding box decoding process, our framework completely avoids any calculations related to anchor boxes. Our framework is end-to-end training and stands at the same performance level as the other one-stage anchor-based detectors.
最近的单阶段3D检测方法在地面平面上生成具有各种大小和方向的锚框，然后确定这些锚框是否包含任何感兴趣区域，并调整其边缘以获得准确的物体边界框。基于锚框的算法在训练过程中为每个锚框计算分类和回归标签，效率低下且复杂。我们提出了一种基于激光雷达点云的单阶段、无锚框3D车辆检测算法。物体位置在点云的鸟瞰图（BEV）中被编码为一组关键点。我们应用体素/柱形特征提取器和卷积块将非结构化点云映射到单通道2D热图。车辆的Z轴位置、尺寸和方向角作为关键点的附加属性进行回归。我们的方法结合了SmoothL1损失和IoU（交并比）损失，并且我们应用（cosθ，sinθ）作为角度回归标签，无需任何方向分类技巧即可实现高平均方向相似度（AOS）。在目标分配和边界框解码过程中，我们的框架完全避免了与锚框相关的任何计算。我们的框架是端到端训练的，并且与其他单阶段基于锚框的检测器处于相同的性能水平。
