DeepAI AI Chat
Log In Sign Up

Stereo RGB and Deeper LIDAR Based Network for 3D Object Detection

06/09/2020
by   Qingdong He, et al.
University of Electronic Science and Technology of China
0

3D object detection has become an emerging task in autonomous driving scenarios. Previous works process 3D point clouds using either projection-based or voxel-based models. However, both approaches contain some drawbacks. The voxel-based methods lack semantic information, while the projection-based methods suffer from numerous spatial information loss when projected to different views. In this paper, we propose the Stereo RGB and Deeper LIDAR (SRDL) framework which can utilize semantic and spatial information simultaneously such that the performance of network for 3D object detection can be improved naturally. Specifically, the network generates candidate boxes from stereo pairs and combines different region-wise features using a deep fusion scheme. The stereo strategy offers more information for prediction compared with prior works. Then, several local and global feature extractors are stacked in the segmentation module to capture richer deep semantic geometric features from point clouds. After aligning the interior points with fused features, the proposed network refines the prediction in a more accurate manner and encodes the whole box in a novel compact method. The decent experimental results on the challenging KITTI detection benchmark demonstrate the effectiveness of utilizing both stereo images and point clouds for 3D object detection.

READ FULL TEXT

page 3

page 8

06/23/2021

FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detection

Accurate detection of obstacles in 3D is an essential task for autonomou...
06/07/2020

SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds

Accurate 3D object detection from point clouds has become a crucial comp...
11/08/2021

Frustum Fusion: Pseudo-LiDAR and LiDAR Fusion for 3D Detection

Most autonomous vehicles are equipped with LiDAR sensors and stereo came...
07/04/2021

Similarity-Aware Fusion Network for 3D Semantic Segmentation

In this paper, we propose a similarity-aware fusion network (SAFNet) to ...
08/17/2022

Stereo Superpixel Segmentation Via Decoupled Dynamic Spatial-Embedding Fusion Network

Stereo superpixel segmentation aims at grouping the discretizing pixels ...
05/03/2021

Pedestrian Detection in 3D Point Clouds using Deep Neural Networks

Detecting pedestrians is a crucial task in autonomous driving systems to...
11/14/2019

PI-RCNN: An Efficient Multi-sensor 3D Object Detector with Point-based Attentive Cont-conv Fusion Module

LIDAR point clouds and RGB-images are both extremely essential for 3D ob...