Individuality-preserving Silhouette Extraction for Gait Recognition
-
- Makihara Yasushi
- Osaka University
-
- Tanoue Takuya
- Osaka University
-
- Muramatsu Daigo
- Osaka University The National Institute of Information and Communications Technology
-
- Yagi Yasushi
- Osaka University
-
- Mori Syunsuke
- Osaka Prefecture University
-
- Utsumi Yuzuko
- Osaka Prefecture University
-
- Iwamura Masakazu
- Osaka Prefecture University
-
- Kise Koichi
- Osaka Prefecture University
Abstract
Most gait recognition approaches rely on silhouette-based representations due to high recognition accuracy and computational efficiency, and a key problem for those approaches is how to accurately extract individuality-preserved silhouettes from real scenes, where foreground colors may be similar to background colors and the background is cluttered. We therefore propose a method of individuality-preserving silhouette extraction for gait recognition using standard gait models (SGMs) composed of clean silhouette sequences of a variety of training subjects as a shape prior. We firstly match the multiple SGMs to a background subtraction sequence of a test subject by dynamic programming and select the training subject whose SGM fit the test sequence the best. We then formulate our silhouette extraction problem in a well-established graph-cut segmentation framework while considering a balance between the observed test sequence and the matched SGM. More specifically, we define an energy function to be minimized by the following three terms: (1) a data term derived from the observed test sequence, (2) a smoothness term derived from spatio-temporally adjacent edges, and (3) a shape-prior term derived from the matched SGM. We demonstrate that the proposed method successfully extracts individuality-preserved silhouettes and improved gait recognition accuracy through experiments using 56 subjects.
Journal
-
- IPSJ Transactions on Computer Vision and Applications
-
IPSJ Transactions on Computer Vision and Applications 7 (0), 74-78, 2015
Information Processing Society of Japan
- Tweet
Details 詳細情報について
-
- CRID
- 1390001205294119680
-
- NII Article ID
- 130005091219
-
- ISSN
- 18826695
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed