Frame-level refinement networks for skeleton-based gait recognition

Wang, Likai; Chen, Jinyan; Liu, Yuxin

doi:10.1016/j.cviu.2022.103500

Cited by 14 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides the aforementioned appearance-based methods, model-based methods [18], [54]- [60] have also shown impressive results recently. After obtaining body skeletons from RGB images using pose estimation works (e.g., OpenPose [61]), CNN models [54], [55] and graph convolutional networks [57]- [59] were employed to learn pose features for recognition. The first gait database with pose sequences, OUMVLP-Pose, was proposed in [56], promoting model-based gait recognition research.…”

Section: B Robust Gait Recognition Against Various Covariatesmentioning

confidence: 99%

Occlusion-Aware Human Mesh Model-Based Gait Recognition

Makihara

et al. 2023

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

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.

show abstract

Section: B Robust Gait Recognition Against Various Covariatesmentioning

confidence: 99%

Occlusion-Aware Human Mesh Model-Based Gait Recognition

Makihara

et al. 2023

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

show abstract

“…Based on the appearance and gait graph, we aim to estimate confidence for the appearance/gait feature of each sample, which explicitly represents the reliability of the feature. Inspired by the effectiveness and generalization that GCN has demonstrated in many computer vision applications [10,18,36,[41][42][43] , we adopt GCN here to explore the latent structural relationships among the candidate samples. The message passing of node k in layer l can be formulated as…”

Section: Confidence Balanced Re-rankingmentioning

confidence: 99%

A benchmark for clothes variation in person re‐identification

Wang

Chen

et al. 2020

Int J Intell Syst

View full text Add to dashboard Cite

Person re-identification (re-ID) has drawn attention significantly in the computer vision society due to its application and research significance. It aims to retrieve a person of interest across different camera views. However, there are still several factors that hinder the applications of person re-ID. In fact, most common data sets either assume that pedestrians do not change their clothing across different camera views or are taken under constrained environments. Those constraints simplify the person re-ID task and contribute to early development of person re-ID, yet a person has a great possibility to change clothes in real life. To facilitate the research toward conquering those issues, this paper mainly introduces a new benchmark data set for person reidentification. To the best of our knowledge, this data set is currently the most diverse for person re-identification. It contains 107 persons with 9,738 images, captured in 15 indoor/outdoor scenes from September 2019 to December 2019, varying according to viewpoints, lighting, resolutions, human pose, seasons, backgrounds, and clothes especially. We hope that this benchmark data set will encourage further research on person re-identification with clothes variation. Moreover, we also perform extensive analyses on this data set using several

show abstract