DocumentCode :
50926
Title :
Gait-Based Person Recognition Using Arbitrary View Transformation Model
Author :
Muramatsu, Daigo ; Shiraishi, Akira ; Makihara, Yasushi ; Uddin, Md Zasim ; Yagi, Yasushi
Author_Institution :
Inst. of the Sci. & Ind. Res., Osaka Univ., Ibaraki, Japan
Volume :
24
Issue :
1
fYear :
2015
fDate :
Jan. 2015
Firstpage :
140
Lastpage :
154
Abstract :
Gait recognition is a useful biometric trait for person authentication because it is usable even with low image resolution. One challenge is robustness to a view change (cross-view matching); view transformation models (VTMs) have been proposed to solve this. The VTMs work well if the target views are the same as their discrete training views. However, the gait traits are observed from an arbitrary view in a real situation. Thus, the target views may not coincide with discrete training views, resulting in recognition accuracy degradation. We propose an arbitrary VTM (AVTM) that accurately matches a pair of gait traits from an arbitrary view. To realize an AVTM, we first construct 3D gait volume sequences of training subjects, disjoint from the test subjects in the target scene. We then generate 2D gait silhouette sequences of the training subjects by projecting the 3D gait volume sequences onto the same views as the target views, and train the AVTM with gait features extracted from the 2D sequences. In addition, we extend our AVTM by incorporating a part-dependent view selection scheme (AVTM_PdVS), which divides the gait feature into several parts, and sets part-dependent destination views for transformation. Because appropriate destination views may differ for different body parts, the part-dependent destination view selection can suppress transformation errors, leading to increased recognition accuracy. Experiments using data sets collected in different settings show that the AVTM improves the accuracy of cross-view matching and that the AVTM_PdVS further improves the accuracy in many cases, in particular, verification scenarios.
Keywords :
feature extraction; gait analysis; image matching; image sequences; object recognition; transforms; 2D gait silhouette sequence generation; 3D gait volume sequences; AVTM_PdVS; arbitrary view transformation model; biometric trait; cross-view matching accuracy improvement; discrete training views; gait feature extraction; gait-based person recognition; low image resolution; part-dependent destination view selection; part-dependent view selection scheme; person authentication; recognition accuracy degradation; transformation error suppression; view change; Accuracy; Cameras; Feature extraction; Image sequences; Three-dimensional displays; Training; Visualization; Gait recognition;
fLanguage :
English
Journal_Title :
Image Processing, IEEE Transactions on
Publisher :
ieee
ISSN :
1057-7149
Type :
jour
DOI :
10.1109/TIP.2014.2371335
Filename :
6963466
Link To Document :
بازگشت