YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection

03/17/2021
by   YuXuan Liu, et al.
23

Object detection in 3D with stereo cameras is an important problem in computer vision, and is particularly crucial in low-cost autonomous mobile robots without LiDARs. Nowadays, most of the best-performing frameworks for stereo 3D object detection are based on dense depth reconstruction from disparity estimation, making them extremely computationally expensive. To enable real-world deployments of vision detection with binocular images, we take a step back to gain insights from 2D image-based detection frameworks and enhance them with stereo features. We incorporate knowledge and the inference structure from real-time one-stage 2D/3D object detector and introduce a light-weight stereo matching module. Our proposed framework, YOLOStereo3D, is trained on one single GPU and runs at more than ten fps. It demonstrates performance comparable to state-of-the-art stereo 3D detection frameworks without usage of LiDAR data. The code will be published in https://github.com/Owen-Liuyuxuan/visualDet3D.

READ FULL TEXT

page 2

page 4

page 7

12/30/2020

RTS3D: Real-time Stereo 3D Detection from 4D Feature-Consistency Embedding Space for Autonomous Driving

Although the recent image-based 3D object detection methods using Pseudo...
02/18/2022

Lightweight Multi-Drone Detection and 3D-Localization via YOLO

In this work, we present and evaluate a method to perform real-time mult...
02/25/2022

Towards Safe, Real-Time Systems: Stereo vs Images and LiDAR for 3D Object Detection

As object detectors rapidly improve, attention has expanded past image-o...
12/06/2020

Computer Stereo Vision for Autonomous Driving

For a long time, autonomous cars were found only in science fiction movi...
06/02/2021

Low-cost Stereovision system (disparity map) for few dollars

The paper presents an analysis of the latest developments in the field o...
08/22/2021

MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching

Recent methods in stereo matching have continuously improved the accurac...
02/06/2021

Gated3D: Monocular 3D Object Detection From Temporal Illumination Cues

Today's state-of-the-art methods for 3D object detection are based on li...

Code Repositories

visualDet3D

Official Repo for Ground-aware Monocular 3D Object Detection for Autonomous Driving / YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection


view repo