Presentation | 2023-03-03 Unknown Object Segmentation by View Independent Scene Change Detection Li Jiaxin, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Exploring the indoor environment and finding unknown objects that appeared in a scene is important for scene understanding by a robot. While background subtraction is traditionally used for segmenting unknown object regions, it cannot be directly used for a moving camera on the robot. In this paper, we address a task called view-independent panoptic scene change detection, which is the task of segmenting unknown object regions by comparing two images from different viewpoints before and after the objects appear. We propose a method for segmenting unknown object regions by modeling each segmented known instance region as a background. For the background modeling, we propose a deep metric learning-based method. In addition, we create a new panoptic scene change detection dataset consisting of images taken from different camera viewpoints. Through experiments, we confirm that the proposed method can segment regions of unknown class objects; the deep-metric-learning-based method performs more accurately than a simple histogram-based method, achieving good performance on the change detection dataset. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Scene change detectionUnknown objectBackground modelingDeep metric learning |
Paper # | PRMU2022-99,IBISML2022-106 |
Date of Issue | 2023-02-23 (PRMU, IBISML) |
Conference Information | |
Committee | PRMU / IBISML / IPSJ-CVIM |
---|---|
Conference Date | 2023/3/2(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Future University Hakodate |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Seiichi Uchida(Kyushu Univ.) / Masashi Sugiyama(Univ. of Tokyo) |
Vice Chair | Takuya Funatomi(NAIST) / Mitsuru Anpai(Denso IT Lab.) / Toshihiro Kamishima(AIST) / Koji Tsuda(Univ. of Tokyo) |
Secretary | Takuya Funatomi(CyberAgent) / Mitsuru Anpai(Univ. of Tokyo) / Toshihiro Kamishima(NTT) / Koji Tsuda(Hokkaido Univ.) |
Assistant | Nakamasa Inoue(Tokyo Inst. of Tech.) / Yasutomo Kawanishi(Riken) / Yoshinobu Kawahara(Osaka Univ.) / Taiji Suzuki(Tokyo Inst. of Tech.) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Information-Based Induction Sciences and Machine Learning / Special Interest Group on Computer Vision and Image Media |
---|---|
Language | ENG-JTITLE |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Unknown Object Segmentation by View Independent Scene Change Detection |
Sub Title (in English) | |
Keyword(1) | Scene change detectionUnknown objectBackground modelingDeep metric learning |
1st Author's Name | Li Jiaxin |
1st Author's Affiliation | Nagoya University(Nagoya Univ.) |
2nd Author's Name | Yasutomo Kawanishi |
2nd Author's Affiliation | RIKEN(RIKEN) |
3rd Author's Name | Daisuke Deguchi |
3rd Author's Affiliation | Nagoya University(Nagoya Univ.) |
4th Author's Name | Hiroshi Murase |
4th Author's Affiliation | Nagoya University(Nagoya Univ.) |
Date | 2023-03-03 |
Paper # | PRMU2022-99,IBISML2022-106 |
Volume (vol) | vol.122 |
Number (no) | PRMU-404,IBISML-405 |
Page | pp.pp.211-216(PRMU), pp.211-216(IBISML), |
#Pages | 6 |
Date of Issue | 2023-02-23 (PRMU, IBISML) |