Monocular 3D object detection is very challenging in autonomous driving due to the lack of depth information. This paper proposes a one-stage monocular 3D object detection algorithm based on multi-scale depth stratification, which uses the anchor-free method to detect 3D objects in a per-pixel prediction. In the proposed MDS-Net, a novel depth-based stratification structure is developed to improve the network's ability of depth prediction by establishing mathematical models between depth and image size of objects. A new angle loss function is then developed to further improve the accuracy of the angle prediction and increase the convergence speed of training. An optimized soft-NMS is finally applied in the post-processing stage to adjust the confidence of candidate boxes. Experiments on the KITTI benchmark show that the MDS-Net outperforms the existing monocular 3D detection methods in 3D detection and BEV detection tasks while fulfilling real-time requirements.

翻译：由于缺乏深度信息, 单体三维天体探测在自动驾驶中非常困难。 本文建议采用基于多级深度分层的一阶段单体三维天体探测算法, 使用无锚方法在每像素预测中检测三维天体。 在拟议的 MDS- Net 中, 开发了一种新的深度分层结构, 通过在物体的深度和图像大小之间建立数学模型, 提高网络的深度预测能力。 然后开发了新的角度丢失功能, 以进一步提高角度预测的准确性, 提高训练的趋同速度。 最终在后处理阶段应用了优化软式NMS, 以调整候选盒的信心。 KITTI 基准实验显示, MDS- 网络在满足实时要求的同时, 超越了3D 探测和 BEV 探测任务的现有单体3D 探测方法 。