Joint Metric Learning and Hierarchical Network for Gait Recognition

Xu, Huanhuan; Li, Yuqian; Sun, Xuemei; Wang, Shengjin

doi:10.1109/access.2020.3044580

Cited by 3 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to [43] that presents an approach for gait recognition that employs hierarchical convolutional neural networks. The hierarchical structure is specifically devised to capture and depict both local and global characteristics in gait patterns.…”

Section: E Related Workmentioning

confidence: 99%

“…• CNN-based approaches: Studies [46], [43], and [44] utilize CNNs for biometric recognition and authentication. • DNN-based approaches: Studies [46], [38], and [43] employ DNNs for ISSN 2549-7286 (online) gait analysis, smart home applications, and biometric recognition.…”

Section: Deep Learning Techniquesmentioning

confidence: 99%

“…• Biometric and authentication: Studies [46], [40], [39] , [41], [44], [47], and [43] explore biometric recognition using gait or video frames. • Human Activity Recognition: Studies [48] and [45] address human activity recognition using different sensor modalities.…”

Section: Application Areasmentioning

confidence: 99%

“…• CASIA datasets: Studies [39] , [40], [41], [44], [43], [45] and [46] utilize the CASIA dataset for biometric recognition. • Other studies use various datasets specific to their application areas.…”

Section: Dataset Usagementioning

confidence: 99%

See 3 more Smart Citations

Human Gait Recognition Based on Deep Learning: A Review

Atrushi,

Adnan Mohsin Abdulazeez

2024

ijcs

View full text Add to dashboard Cite

Human gait recognition as a branch of biometric identification, has witnessed remarkable progress in recent years, thanks to the integration of deep learning techniques. This paper presents a comprehensive review of the latest advancements in the field, specifically focusing on the transformative role of deep learning methodologies. Recent research papers highlight novel approaches in gait recognition, including deferent models proposed that is consisted of using more than one approach together to increase the accuracy. Subsequently, we undertake a comprehensive investigation of the most relevant literature and present an analysis of gait recognition techniques employing deep learning. We discuss the models, systems, accuracy, applications, and datasets utilized in these studies, aiming to outline and structure the research landscape and literature in this domain. Methods for acquiring gait data are distinguished between capturing video frame, radar signals, or from wearable sensors as well as from the available online datasets that are large-scale and significantly contributed to the advancement of deep learning models. The study also shows the verity applications that can utilize human gait recognition to achieve certain goals.

show abstract

Section: E Related Workmentioning

confidence: 99%