Stereo R-CNN based 3D Object Detection for Autonomous Driving

02/26/2019
by   Peiliang Li, et al.
0

We propose a 3D object detection method for autonomous driving by fully exploiting the sparse and dense, semantic and geometry information in stereo imagery. Our method, called Stereo R-CNN, extends Faster R-CNN for stereo inputs to simultaneously detect and associate object in left and right images. We add extra branches after stereo Region Proposal Network (RPN) to predict sparse keypoints, viewpoints, and object dimensions, which are combined with 2D left-right boxes to calculate a coarse 3D object bounding box. We then recover the accurate 3D bounding box by a region-based photometric alignment using left and right RoIs. Our method does not require depth input and 3D position supervision, however, outperforms all existing fully supervised image-based methods. Experiments on the challenging KITTI dataset show that our method outperforms the state-of-the-art stereo-based method by around 30 3D detection and 3D localization tasks. Code will be made publicly available.

READ FULL TEXT

page 2

page 3

page 4

page 5

page 7

research
03/20/2021

Stereo CenterNet based 3D Object Detection for Autonomous Driving

In recent years, 3D detection based on stereo cameras has made great pro...
research
08/27/2016

3D Object Proposals using Stereo Imagery for Accurate Object Class Detection

The goal of this paper is to perform 3D object detection in the context ...
research
10/27/2020

Stereo Frustums: A Siamese Pipeline for 3D Object Detection

The paper proposes a light-weighted stereo frustums matching module for ...
research
03/26/2019

GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving

We present an efficient 3D object detection framework based on a single ...
research
06/15/2020

Visibility Guided NMS: Efficient Boosting of Amodal Object Detection in Crowded Traffic Scenes

Object detection is an important task in environment perception for auto...
research
01/03/2018

Spot the Difference by Object Detection

In this paper, we propose a simple yet effective solution to a change de...
research
03/01/2020

ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection

3D object detection is an essential task in autonomous driving and robot...

Please sign up or login with your details

Forgot password? Click here to reset