Pose-Based Temporal-Spatial Network (PTSN) for Gait Recognition with Carrying and Clothing Variations

Liao, Rijun; Cao, Chunshui; García, Edel B.; Yu, Shiqi; Huang, Yongzhen

doi:10.1007/978-3-319-69923-3_51

Cited by 166 publications

(110 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They used pendular motion to describe the thigh and lower leg motion, and studied on different walking styles, walking and running. Recently Liao et al [14] took the advantage of deep learning and used a pose estimation by deep learning to recover human skeleton models. They also converted 2D pose data to 3D for view invariant feature extraction in [37].…”

Section: Gait Recognitionmentioning

confidence: 99%

“…Thereafter, deep learning-based approaches significantly advanced state-of-the-art human pose estimation, and standard techniques such as OpenPose [12] and AlphaPose [13] have been widely used in many research fields, which indicates the possibility of model-based gait recognition with conventional cameras in visual surveillance scenarios. For example, Liao et al [14] proposed a pose-based temporalspatial network (PTSN) that takes a sequence of estimated human poses as input and showed its effectiveness on crossview gait recognition with a publicly available gait database, i.e., CASIA B [15]. Although CASIA B contains large view variations (eleven views) from 0 • to 180 • , the number of subjects is still limited to 124, which is insufficient to fully demonstrate the possibility of model-based gait recognition in this deep learning era.…”

Section: Introductionmentioning

confidence: 99%

“…, which results in the world's largest gait database with pose sequence. As deep learning-based methods require massive samples for sufficient training and reliable evaluation, the constructed database is suitable for evaluating modelbased gait recognition with deep neural networks such as [14].…”

mentioning

confidence: 99%

“…• Performance evaluation of the model-based gait recognition. We conducted a set of evaluation experiments with a variety of model-based approaches ranging from a traditional method [4] to recent deep learning-based methods [14]. This can be a good milestone for future studies of model-based gait recognition.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Performance Evaluation of Model-Based Gait on Multi-View Very Large Population Database With Pose Sequences

Makihara

et al. 2020

IEEE Trans. Biom. Behav. Identity Sci.

Self Cite

110

View full text Add to dashboard Cite

Model-based gait recognition is considered to be promising due to the robustness against some variations, such as clothing and baggage carried. Although model-based gait recognition has not been fully explored due to the difficulty of human body model fitting and the lack of a large-scale gait database, recent progress in deep learning-based approaches to human body model fitting and human pose estimation is mitigating the difficulty. In this paper, we, therefore, address the remaining issue by presenting a large-scale human pose-based gait database, OUMVLP-Pose, which is based on a publicly available multi-view large-scale gait database, OUMVLP. OUMVLP-Pose has many unique advantages compared with other public databases. First, OUMVLP-Pose is the first gait database that provides two datasets of human pose sequences extracted by two standard deep learning-based pose estimation algorithms, OpenPose and AlphaPose. Second, it contains multi-view large-scale data, i.e., over 10,000 subjects and 14 views for each subject. In addition, we also provide benchmarks in which different kinds of gait recognition methods, including model-based methods and appearance-based methods, have been evaluated comprehensively. The model-based gait recognition methods have shown promising performances. We believe this database, OUMVLP-Pose, will greatly promote model-based gait recognition in the next few years.

show abstract

Section: Gait Recognitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Performance Evaluation of Model-Based Gait on Multi-View Very Large Population Database With Pose Sequences

Makihara

et al. 2020

IEEE Trans. Biom. Behav. Identity Sci.

Self Cite

110

View full text Add to dashboard Cite

show abstract

“…Recently, the use of deep CNNs, such as VGG-16 [19] or pose based temporal-spatial networks [20], have significantly improved the performance of silhouette based gait recognition systems. Similar improvements have also been seen in the medical domain, especially in detecting Alzehimer's disease [21].…”

Section: B Motivation and Contributionmentioning

confidence: 99%

Using transfer learning for classification of gait pathologies

Verlekar

Lobat

Soares

2018

2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

View full text Add to dashboard Cite

Different diseases can affect an individual's gait in different ways and, therefore, gait analysis can provide important insights into an individual's health and well-being. Currently, most systems that perform gait analysis using 2D video are limited to simple binary classification of gait as being either normal or impaired. While some systems do perform gait classification across different pathologies, the reported results still have a considerable margin for improvement. This paper presents a novel system that performs classification of gait across different pathologies, with considerably improved results. The system computes the walking individual's silhouettes, which are computed from a 2D video sequence, and combines them into a representation known as the gait energy image (GEI), which provides robustness against silhouette segmentation errors. In this work, instead of using a set of handcrafted gait features, feature extraction is done using the VGG-19 convolutional neural network. The network is fine-tuned to automatically extract the features that best represent gait pathologies, using transfer learning. The use of transfer learning improves the classification accuracy while avoiding the need of a very large training set, as the network is pre-trained for generic image description, which also contributes to a better generalization when tested across different datasets. The proposed system performs the final classification using linear discriminant analysis (LDA). Obtained results show that the proposed system outperforms the state-of-the-art, achieving a classification accuracy of 95% on a dataset containing gait sequences affected by diplegia, hemiplegia, neuropathy and Parkinson's disease, along with normal gait sequences.

show abstract

Gait Recognition with Clothing and Carrying Variations Based on GEI and CAPDS Features

Yang

Jiang

Sun

et al. 2019

Pattern Recognition and Computer Vision

View full text Add to dashboard Cite

Pose-Based Temporal-Spatial Network (PTSN) for Gait Recognition with Carrying and Clothing Variations

Cited by 166 publications

References 20 publications

Performance Evaluation of Model-Based Gait on Multi-View Very Large Population Database With Pose Sequences

Performance Evaluation of Model-Based Gait on Multi-View Very Large Population Database With Pose Sequences

Using transfer learning for classification of gait pathologies

Gait Recognition with Clothing and Carrying Variations Based on GEI and CAPDS Features

Contact Info

Product

Resources

About