Gait Recognition with Self-Supervised Learning of Gait Features Based on Vision Transformers

Pinčić, Domagoj; Sušanj, Diego; Lenac, Kristijan

doi:10.3390/s22197140

Cited by 8 publications

(5 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 195º , the approach is close to 90%, and the highest score was 91.80%, achieved by SelfGait [48]. The second score achieved by ViTs16 [45] was 90.57%.…”

Section: Discussionmentioning

confidence: 76%

See 1 more Smart Citation

Advanced Age Group Estimation Using Gait Analysis: A Novel Multi-Energy Image and Invariant Moments Method

Al Musalhi,

Celebi

2024

View full text Add to dashboard Cite

The precise estimation of age is pivotal in identity verification across critical security checkpoints, including seaports, land borders, and airports. This study introduces an innovative methodology for age estimation based on gait analysis, enhancing security measures and providing reliable identity confirmation. Utilizing a novel preprocessing technique on gait datasets, this approach amalgamates three integral components: the Accumulated Frame Difference Energy Image (AFDEI), the Gait Energy Image (GEI), and the Invariant Moment of the image. These elements collectively facilitate the efficient extraction and analysis of critical gait data. Evaluation of the model, employing a Convolutional Neural Network (CNN), was conducted on the publicly available OU-ISRI with age dataset. The model demonstrated remarkable proficiency, achieving an average accuracy of 90.40% across 14 distinct view angles within a 5 K-Fold framework. This methodological advancement significantly outperforms existing state-of-the-art techniques in accuracy. The findings highlight the efficacy and potential of the proposed method for age grouping estimation through human gait analysis. Despite these advancements, it is crucial to acknowledge the study's limitations, particularly the dependency on silhouette images. Preprocessing is essential prior to implementing the proposed methodology. The outcomes of this study are instrumental in reinforcing age estimation as a key factor in bolstering identity verification processes at essential security junctures.

show abstract

“…In 195º , the approach is close to 90%, and the highest score was 91.80%, achieved by SelfGait [48]. The second score achieved by ViTs16 [45] was 90.57%.…”

Section: Discussionmentioning

confidence: 76%

“…Pinčić et al [45] developed a new method that uses selfsupervised learning (SSL) to complete the gait identification test. They used the vision transformer (ViT) architecture presented in the self-supervised DINO approach for image classification.…”

Section: Related Workmentioning

confidence: 99%

Advanced Age Group Estimation Using Gait Analysis: A Novel Multi-Energy Image and Invariant Moments Method

Al Musalhi,

Celebi

2024

View full text Add to dashboard Cite

show abstract

“…Moreover, the Transformer model has been applied in gait recognition tasks. For instance, Mogan et al [28] and Pinvcic et al [29] directly employed the Vision Transformer (ViT) model on gait silhouettes. These methods involve converting gait silhouette images into onedimensional sequences, followed by feature extraction and classification using the ViT model.…”

Section: Transformermentioning

confidence: 99%

Gait Recognition with Global-Local Feature Fusion Based on Swin Transformer-3DCNN

Wang,

Zhou,

et al. 2024

Preprint

View full text Add to dashboard Cite

Gait recognition is a biometric technology that can be used for identification over long distances and has great application prospects in the field of public security. Currently, the majority of gait recognition approaches rely on either global or local information from gait features for the representation. However, representing global information frequently leads to the loss of intricate details of gait features, while local information may neglect the interrelations among different local features. Therefore, in this paper, a novel Swin Transformer-Conventional Neural Network Gait framework is proposed to effectively integrate both global and local information of gait features for the recognition. Within the framework, the Swin transformer module is incorporated to extract global information. The Swin transformer employs shift windows for hierarchical feature extraction, facilitating improved capture of global features and long-range dependencies in images. Within local branches, feature maps are segmented for feature extraction by using multiple 3D Convolutional Neural Networks to enhance the capture of local information. Furthermore, attention module is introduced to boost the locally extracted information from Convolutional Neural Network. Through results of experiments, our approach has substantially enhanced performance in gait recognition, achieving optimal recognition across most conditions.

show abstract

“…By stacking attentional layers that scan the sequence, Transformers are capable of producing position and context aware representations. Inspired by Transformers, a few attempts have been made to introduce transformer-like architectures to vision tasks [29], [30], one of which, called vision transformer (ViT) [31], has been successfully applied for image recognition and shows competitive performance [32], [33]. Hussain et al [34] explored a pretrained Vision Transformer to extract frame-level features and then passed the features to a long short-term memory to recognize human activities.…”

Section: Table I the Representative Sample Data Collected During Gait...mentioning

confidence: 99%

Dense & Attention Convolutional Neural Networks for Toe Walking Recognition

Chen

Soangra

Grant-Beuttler

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Idiopathic toe walking (ITW) is a gait disorder where children's initial contacts show limited or no heel touch during the gait cycle. Toe walking can lead to poor balance, increased risk of falling or tripping, leg pain, and stunted growth in children. Early detection and identification can facilitate targeted interventions for children diagnosed with ITW. This study proposes a new onedimensional (1D) Dense & Attention convolutional network architecture, which is termed as the DANet, to detect idiopathic toe walking. The dense block is integrated into the network to maximize information transfer and avoid missed features. Further, the attention modules are incorporated into the network to highlight useful features while suppressing unwanted noises. Also, the Focal Loss function is enhanced to alleviate the imbalance sample issue. The proposed approach outperforms other methods and obtains a superior performance. It achieves a test recall of 88.91% for recognizing idiopathic toe walking on the local dataset collected from real-world experimental scenarios.To ensure the scalability and generalizability of the proposed approach, the algorithm is further validated through the publicly available datasets, and the proposed approach achieves an average precision, recall, and F1-Score of 89.34%, 91.50%, and 92.04%, respectively. Experimental results present a competitive performance and demonstrate the validity and feasibility of the proposed approach.

show abstract

Gait Recognition with Self-Supervised Learning of Gait Features Based on Vision Transformers

Cited by 8 publications

References 39 publications

Advanced Age Group Estimation Using Gait Analysis: A Novel Multi-Energy Image and Invariant Moments Method

Advanced Age Group Estimation Using Gait Analysis: A Novel Multi-Energy Image and Invariant Moments Method

Gait Recognition with Global-Local Feature Fusion Based on Swin Transformer-3DCNN

Dense & Attention Convolutional Neural Networks for Toe Walking Recognition

Contact Info

Product

Resources

About