Learning depth from monocular sequence with convolutional LSTM network

Chia Hung Yeh*, Yao Pao Huang, Chih Yang Lin, Min Hui Lin

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Resolving depth from monocular RGB image has been a long-standing task in computer vision and robotics. Recently, deep learning based methods has become a popular algorithm on depth estimation. Most existing learning based methods take image-pair as input and utilize feature matching across frames to resolve depth. However, two-frame methods require sufficient and static camera motion to reach optimal performance, while camera motion is usually uncontrollable in most application scenarios. In this paper we propose a recurrent neural network based depth estimation network. With the ability of taking multiple images as input, recurrent neural network will decide by itself which image to reference during estimation. We train a u-net like network architecture which utilizes convolutional LSTM in the encoder. We demonstrate our proposed method with the TUM RGB-D dataset, where our proposed method shows the ability of estimating depth with various sequence lengths as input.

Original languageEnglish
Title of host publicationAdvances in Networked-based Information Systems - The 22nd International Conference on Network-Based Information Systems, NBiS 2019
EditorsLeonard Barolli, Hiroaki Nishino, Tomoya Enokido, Makoto Takizawa
PublisherSpringer Verlag
Pages502-507
Number of pages6
ISBN (Print)9783030290283
DOIs
Publication statusPublished - 2020
Event22nd International Conference on Network-Based Information Systems, NBiS 2019 - Oita, Japan
Duration: 2019 Sep 52019 Sep 7

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1036
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

Conference22nd International Conference on Network-Based Information Systems, NBiS 2019
Country/TerritoryJapan
CityOita
Period2019/09/052019/09/07

Keywords

  • Convolutional LSTM
  • Deep learning
  • Multi-view depth estimation
  • Recurrent neural network

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Fingerprint

Dive into the research topics of 'Learning depth from monocular sequence with convolutional LSTM network'. Together they form a unique fingerprint.

Cite this