TU-Net and TDeepLab: Deep Learning-Based Terrain Classification Robust to Illumination Changes, Combining Visible and Thermal Imagery

Yumi Iwashita, Kazuto Nakashima, Adrian Stoica, Ryo Kurazume

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

3 引用 (Scopus)

抜粋

In this paper we propose two novel deep learning-based terrain classification methods robust to illumination changes. The use of cameras is challenged by a variety of factors, of most importance being the changes in illumination. On the other hand, since the temperature of various types of terrains depends on the thermal characteristics of the terrain, the terrain classification can be aided by utilizing the thermal information in addition to visible information. Thus we propose 'TU-Net (Two U-Net)' based on the U-Net and 'TDeepLab (Two DeepLab)' based on DeepLab, which combine visible and thermal images and train the network robust to illumination changes implicitly. To improve the network's learning capability, we expand the proposed methods to the Siamese-based method, which explicitly trains the network to be robust to illumination changes. We also investigate multiple options to fuse the visible and thermal images at at the bottom layer, middle layer, or the top layer of the network. We evaluate the proposed methods with a challenging new dataset consisting of visible and thermal images, which were collected from 10 am till 5 pm (after sunset), and we show the effectiveness of the proposed methods.

元の言語英語
ホスト出版物のタイトルProceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019
出版者Institute of Electrical and Electronics Engineers Inc.
ページ280-285
ページ数6
ISBN(電子版)9781728111988
DOI
出版物ステータス出版済み - 4 22 2019
イベント2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019 - San Jose, 米国
継続期間: 3 28 20193 30 2019

出版物シリーズ

名前Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019

会議

会議2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019
米国
San Jose
期間3/28/193/30/19

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Signal Processing
  • Media Technology

フィンガープリント TU-Net and TDeepLab: Deep Learning-Based Terrain Classification Robust to Illumination Changes, Combining Visible and Thermal Imagery' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用

    Iwashita, Y., Nakashima, K., Stoica, A., & Kurazume, R. (2019). TU-Net and TDeepLab: Deep Learning-Based Terrain Classification Robust to Illumination Changes, Combining Visible and Thermal Imagery. : Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019 (pp. 280-285). [8695421] (Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MIPR.2019.00057