TANet: Robust 3D Object Detection from Point Clouds with Triple Attention

Abstract

In this paper, we focus on exploring the robustness of the 3D object detection in point clouds, which has been rarely discussed in existing approaches. We observe two crucial phenomena: 1) the detection accuracy of the hard objects, e.g., Pedestrians, is unsatisfactory, 2) when adding additional noise points, the performance of existing approaches decreases rapidly. To alleviate these problems, a novel TANet is introduced in this paper, which mainly contains a Triple Attention (TA) module, and a Coarse-to-Fine Regression (CFR) module. By considering the channel-wise, point-wise and voxel-wise attention jointly, the TA module enhances the crucial information of the target while suppresses the unstable cloud points. Besides, the novel stacked TA further exploits the multi-level feature attention. In addition, the CFR module boosts the accuracy of localization without excessive computation cost. Experimental results on the validation set of KITTI dataset demonstrate that, in the challenging noisy cases, i.e., adding additional random noisy points around each object, the presented approach goes far beyond state-of-the-art approaches. Furthermore, for the 3D object detection task of the KITTI benchmark, our approach ranks the first place on Pedestrian class, by using the point clouds as the only input. The running speed is around 29 frames per second.

PSANet: Pyramid Splitting and Aggregation Network for 3D Object Detection in Point Cloud

“…They are mainly divided into two directions: (1) optimizing SECOND [ 12 ] and designing a novel one-stage detector. For example, Pointpillars [ 13 ] and TANet [ 14 ] simplify the encoding method of SECOND [ 12 ]. They chose to abandon the 3D sparse convolutional backbone network, and use a pillar encoder to convert point clouds into a pseudo-image of the BEV, and finally use the 2D backbone network to generate the detection results.…”

“…Then, the simplified PointNet [ 19 ] is used to learn the features and convert the sparse 3D data into 2D pseudo-images for detection. Taking advantage of Pointpillars [ 13 ], TANet [ 14 ] studies the robustness of point cloud-based 3D object detection. A triple attention module is proposed to suppress the unstable point clouds, and the coarse-to-fine regression (CFR) module is used to refine the position of objects.…”

“…Many follow-up works are carried out on this basis. For example, Pointpillars [ 13 ] and TANet [ 14 ] optimize the point cloud encoder and abandon the 3D backbone network, thereby further improving the inference speed of the network.…”

“…In this paper, we propose a novel detection framework called PSANet (Pyramid Splitting and Aggregation Network), which skillfully combines a 3D backbone network and a 2D backbone network. Inspired by TANet [ 14 ] and FPTNet [ 15 ], we propose a new 2D backbone network to complete the cross-layer fusion of multi-scale feature maps and extract robust features of BEV. Specifically, our proposed backbone network can be divided into a coarse branch and a fine branch.…”

Perceiving Humans: From Monocular 3D Localization to Social Distancing

“…O VER the past decades, we have witnessed new emerging technologies to localize humans in 3D, ranging from vision-based [1]- [5], to LiDAR-based solutions [6], [7] and multi-sensor approaches [8], [9]. On one hand, vision-based technologies can capture detailed body poses and texture properties, but rely on a costly calibrated network of cameras [10]- [12].…”