Relation Graph Network for 3D Object Detection in Point Clouds

doi:10.1109/TIP.2020.3031371

Return

Relation Graph Network for 3D Object Detection in Point Clouds

2021-01-01

Mingtao Feng

Syed Zulqarnain Gilani

王耀南 (Yaonan Wang)

Liang Zhang *

Ajmal Mian

DOI：10.1109/TIP.2020.3031371

Original

Save

View PDF

Abstract

En 中文

Convolutional Neural Networks (CNNs) have emerged as a powerful tool for object detection in 2D images. However, their power has not been fully realised for detecting 3D objects directly in point clouds without conversion to regular grids. Moreover, existing state-of-the-art 3D object detection methods aim to recognize objects individually without exploiting their relationships during learning or inference. In this article, we first propose a strategy that associates the predictions of direction vectors with pseudo geometric centers, leading to a win-win solution for 3D bounding box candidates regression. Secondly, we propose point attention pooling to extract uniform appearance features for each 3D object proposal, benefiting from the learned direction features, semantic features and spatial coordinates of the object points. Finally, the appearance features are used together with the position features to build 3D object-object relationship graphs for all proposals to model their co-existence. We explore the effect of relation graphs on proposals' appearance feature enhancement under supervised and unsupervised settings. The proposed relation graph network comprises a 3D object proposal generation module and a 3D relation module, making it an end-to-end trainable network for detecting 3D objects in point clouds. Experiments on challenging benchmark point cloud datasets (SunRGB-D, ScanNet and KITTI) show that our algorithm performs better than existing state-of-the-art.

Keywords:

Three-dimensional displays

Proposals

Object detection

Two dimensional displays

Feature extraction

Laser radar

Semantics

3D object detection

point cloud

deep learning

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.