Occlusion-Aware Human Mesh Model-Based Gait Recognition
Open Access
- 11 January 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 18 (15566013) , 1309-1321
Abstract
Partial occlusion of the human body caused by obstacles or a limited camera field of view often occurs in surveillance videos, which affects the performance of gait recognition in practice. Existing methods for gait recognition against occlusion require a bounding box or the height of a full human body as a prerequisite, which is unobserved in occlusion scenarios. In this paper, we propose an occlusion-aware model-based gait recognition method that works directly on gait videos under occlusion without the above-mentioned prerequisite. Specifically, given a gait sequence that only contains non-occluded body parts in the images, we directly fit a skinned multi-person linear (SMPL)-based human mesh model to the input images without any pre-normalization or registration of the human body. We further use the pose and shape features extracted from the estimated SMPL model for recognition purposes, and use the extracted camera parameters in the occlusion attenuation module to reduce intra-subject variation in human model fitting caused by occlusion pattern differences. Experiments on occlusion samples simulated from the OU-MVLP dataset demonstrated the effectiveness of the proposed method, which outperformed state-of-the-art gait recognition methods by about 15% rank-1 identification rate and 2% equal error rate in the identification and verification scenarios, respectively.Keywords
Funding Information
- Japan Society for the Promotion of Science (JSPS) Kakenhi (JP20H00607)
This publication has 76 references indexed in Scilit:
- Gait-Based Person Identification Robust to Changes in AppearanceSensors, 2013
- Occlusion detection and gait silhouette reconstruction from degraded scenesSignal, Image and Video Processing, 2011
- On Using Gait in Forensic BiometricsJournal of Forensic Sciences, 2011
- Clothing-invariant gait identification using part-based clothing categorization and adaptive weight controlPattern Recognition, 2010
- The effect of arm movements on the lower limb during gait after a strokeGait & Posture, 2010
- Frame difference energy image for gait recognition with incomplete silhouettesPattern Recognition Letters, 2009
- Reducing the Effect of Noise on Human Contour in Gait Recognition2007
- Human gait recognition based on matching of body componentsPattern Recognition, 2007
- Gait recognition using fractal scalePattern Analysis and Applications, 2007
- The FERET evaluation methodology for face-recognition algorithmsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000