3D-CenterNet: 3D object detection network for point clouds with center estimation priority. (July 2021)

• Record Type: Journal Article
• Authors: Wang, Qi; Chen, Jian; Deng, Jianqiang; Zhang, Xinfang
• Is Part Of: Pattern recognition. Volume 115(2021)
• Publication Date: 2021-07
• Subjects: 3D object detection -- Point cloud -- Deep learning; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.107884
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We propose the center regression module to estimate centers' locations of objects only with point cloud. We propose the new single-stage 3D object detector, 3D-CenterNet, which emphasizes the object centers' regressions. The results evaluated on the open datasets show that our framework is superior to the existing single-stage methods. Abstract: In this paper, a single-stage 3D object detection framework, 3D-CenterNet, is proposed for accurate 3D object detection from point clouds. We find that the center position is more critical for accurate bounding box detection than the other two parameters, the size and the orientation. Motivated by this discovery, we propose the center regression module (CRM) to regress the centers' location from the point-wise features. In CRM, the representative points belonging to objects are sampled to regress the center locations of the corresponding objects. The semantic and geometric information related to the estimated centers is aggregated for the following location refinement and other parameters' estimation. The 3D-CenterNet stacks the CRMs to improve the accuracy of the estimated centers gradually. The size and orientation of the bounding boxes are decoded from the high dimensional center-wise features. The experiments on the KITTI benchmark and the SUN RGB-D datasets show that our proposed 3D-CenterNet achieves high-quality results in real time.