MDS-Net: A Multi-scale Depth Stratification Based Monocular 3D Object Detection Algorithm
This addresses the challenge of accurate 3D object detection from single images for autonomous driving systems, representing an incremental improvement with specific gains.
The paper tackled monocular 3D object detection in autonomous driving by proposing MDS-Net, a one-stage algorithm using multi-scale depth stratification and anchor-free per-pixel prediction, which outperformed existing methods on the KITTI benchmark in 3D and BEV detection tasks while meeting real-time requirements.
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.