RoIFusion: 3D Object Detection from LiDAR and Vision
arXiv:2009.04554
Abstract
When localizing and detecting 3D objects for autonomous driving scenes, obtaining information from multiple sensor (e.g. camera, LIDAR) typically increases the robustness of 3D detectors. However, the efficient and effective fusion of different features captured from LIDAR and camera is still challenging, especially due to the sparsity and irregularity of point cloud distributions. This notwithstanding, point clouds offer useful complementary information. In this paper, we would like to leverage the advantages of LIDAR and camera sensors by proposing a deep neural network architecture for the fusion and the efficient detection of 3D objects by identifying their corresponding 3D bounding boxes with orientation. In order to achieve this task, instead of densely combining the point-wise feature of the point cloud and the related pixel features, we propose a novel fusion algorithm by projecting a set of 3D Region of Interests (RoIs) from the point clouds to the 2D RoIs of the corresponding the images. Finally, we demonstrate that our deep fusion approach achieves state-of-the-art performance on the KITTI 3D object detection challenging benchmark.
11 pages
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Submanifold Sparse Convolutional Networks
- IPOD: Intensive Point-based Object Detector for Point Cloud
- 3DSSD: Point-based 3D Single Stage Object Detector
- GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud
- Patch Refinement -- Localized 3D Object Detection