RSAN: A Retinex based Self Adaptive Stereo Matching Network for Day and Night Scenes

Haoyuan Zhang, Lap Pui Chau, Danwei Wang

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

It is essential in many robot tasks to retrieve depth information, while it still remains a challenging problem to get robust depth in unfavorable conditions such as night or rainy environments. With the development of convolutional neural networks (CNNs), a large number of algorithms have emerged to tackle the problem of dark image enhancement and depth estimation, but there are few works focus on recovering depth map in dark environments and normal light condition. To meet this demand, we proposed a neural network which takes the paired stereo images in all light conditions as input and estimates the fully scaled depth map. The network contains a novel feature extractor and a stereo matching module which follows a light-weight manner to guarantee this work practical for real robotic applications. We introduced the Retinex Theory into depth estimation and trained the decomposition module with LOL dataset. Then it is adapted into depth estimation by fusing the decompose module into stereo matching algorithm. The whole network is then trained in an end-to-end manner. To demonstrate the robustness and effectiveness of our proposed method, we perform various studies and compare our results to the state-of-the-art algorithms in depth estimation as well as direct combination of image enhancement and stereo matching algorithm. We also collect stereo images in real night environments and present the improved performance of our network.

Original languageEnglish
Title of host publication16th IEEE International Conference on Control, Automation, Robotics and Vision, ICARCV 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages381-386
Number of pages6
ISBN (Electronic)9781728177090
DOIs
Publication statusPublished - 13 Dec 2020
Externally publishedYes
Event16th IEEE International Conference on Control, Automation, Robotics and Vision, ICARCV 2020 - Virtual, Shenzhen, China
Duration: 13 Dec 202015 Dec 2020

Publication series

Name16th IEEE International Conference on Control, Automation, Robotics and Vision, ICARCV 2020

Conference

Conference16th IEEE International Conference on Control, Automation, Robotics and Vision, ICARCV 2020
Country/TerritoryChina
CityVirtual, Shenzhen
Period13/12/2015/12/20

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Control and Systems Engineering
  • Control and Optimization

Fingerprint

Dive into the research topics of 'RSAN: A Retinex based Self Adaptive Stereo Matching Network for Day and Night Scenes'. Together they form a unique fingerprint.

Cite this