Skeleton-based abnormal gait recognition with spatio-temporal attention enhanced gait-structural graph convolutional networks

Tian, Haoyu; Ma, Xin; Wu, Hanbo; Li, Yibin

doi:10.1016/j.neucom.2021.12.004

Cited by 14 publications

(13 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the effectiveness of our proposed method, we compared it with results obtained from various deep learning-based classifiers as reported in previous researches [ 15 , 17 , 25 , 26 ]. These models were used to classify one normal gait and five pathological gaits in the GIST dataset.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Besides the public dataset, another comparative experiment was conducted between the proposed method and ST-GCN [ 26 ] algorithm whose performance was similar to the proposed work on the GIST dataset. Other works like Multiple-input ST-GCN [ 17 ] and AGS-GCN [ 15 ] were not selected for this experiment due to the lack of their source code. The following Table 2 summarizes the composition of our dataset, detailing the number of subjects and video sequences for each gait.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…For instance, Zeng et al [ 14 ] introduced Slow-Fast GCN to quantify Parkinsonian gait by detecting bilateral asymmetry and gait features. Tian et al [ 15 ] proposed AGS-GCN, which introduced a novel joint partitioning strategy and attention mechanism for pathological gait classification. Jun et al [ 16 ] implemented a bidirectional gated recurrent network algorithm for abnormal gait video classification.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

FP-GCN: Frequency Pyramid Graph Convolutional Network for Enhancing Pathological Gait Classification

Zhao,

Li,

Hua

2024

Sensors

View full text Add to dashboard Cite

Gait, a manifestation of one’s walking pattern, intricately reflects the harmonious interplay of various bodily systems, offering valuable insights into an individual’s health status. However, the current study has shortcomings in the extraction of temporal and spatial dependencies in joint motion, resulting in inefficiencies in pathological gait classification. In this paper, we propose a Frequency Pyramid Graph Convolutional Network (FP-GCN), advocating to complement temporal analysis and further enhance spatial feature extraction. specifically, a spectral decomposition component is adopted to extract gait data with different time frames, which can enhance the detection of rhythmic patterns and velocity variations in human gait and allow a detailed analysis of the temporal features. Furthermore, a novel pyramidal feature extraction approach is developed to analyze the inter-sensor dependencies, which can integrate features from different pathways, enhancing both temporal and spatial feature extraction. Our experimentation on diverse datasets demonstrates the effectiveness of our approach. Notably, FP-GCN achieves an impressive accuracy of 98.78% on public datasets and 96.54% on proprietary data, surpassing existing methodologies and underscoring its potential for advancing pathological gait classification. In summary, our innovative FP-GCN contributes to advancing feature extraction and pathological gait recognition, which may offer potential advancements in healthcare provisions, especially in regions with limited access to medical resources and in home-care environments. This work lays the foundation for further exploration and underscores the importance of remote health monitoring, diagnosis, and personalized interventions.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

FP-GCN: Frequency Pyramid Graph Convolutional Network for Enhancing Pathological Gait Classification

Zhao,

Li,

Hua

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Moreover, they improved the characteristics of joint points through the spatiotemporal attention mechanism. Extensive experiments demonstrate that the AGS-GCN scores better performance metrics than the other recent studies [ 10 ].…”

Section: Related Workmentioning

confidence: 89%

Model-based and model-free deep features fusion for high performed human gait recognition

Yousef¹,

Khalil

Samra

et al. 2023

J Supercomput

View full text Add to dashboard Cite

In the last decade, the need for a non-contact biometric model for recognizing candidates has increased, especially after the pandemic of COVID-19 appeared and spread worldwide. This paper presents a novel deep convolutional neural network (CNN) model that guarantees quick, safe, and precise human authentication via their poses and walking style. The concatenated fusion between the proposed CNN and a fully connected model has been formulated, utilized, and tested. The proposed CNN extracts the human features from two main sources: (1) human silhouette images according to model-free and (2) human joints, limbs, and static joint distances according to a model-based via a novel, fully connected deep-layer structure. The most commonly used dataset, CASIA gait families, has been utilized and tested. Numerous performance metrics have been evaluated to measure the system quality, including accuracy, specificity, sensitivity, false negative rate, and training time. Experimental results reveal that the proposed model can enhance recognition performance in a superior manner compared with the latest state-of-the-art studies. Moreover, the suggested system introduces a robust real-time authentication with any covariate conditions, scoring 99.8% and 99.6% accuracy in identifying casia (B) and casia (A) datasets, respectively.

show abstract

“…Single-LSTM model [12] 94 Ensemble-LSTM model [12] 91 AGS-GCN [52] Multiple-input ST-GCN (+Attention) 92.3 95.5…”

Section: Model Accuracy (%)mentioning

confidence: 99%

Pathological-Gait Recognition Using Spatiotemporal Graph Convolutional Networks and Attention Model

Kim

Suh

Naseem

et al. 2022

Sensors

View full text Add to dashboard Cite

Walking is an exercise that uses muscles and joints of the human body and is essential for understanding body condition. Analyzing body movements through gait has been studied and applied in human identification, sports science, and medicine. This study investigated a spatiotemporal graph convolutional network model (ST-GCN), using attention techniques applied to pathological-gait classification from the collected skeletal information. The focus of this study was twofold. The first objective was extracting spatiotemporal features from skeletal information presented by joint connections and applying these features to graph convolutional neural networks. The second objective was developing an attention mechanism for spatiotemporal graph convolutional neural networks, to focus on important joints in the current gait. This model establishes a pathological-gait-classification system for diagnosing sarcopenia. Experiments on three datasets, namely NTU RGB+D, pathological gait of GIST, and multimodal-gait symmetry (MMGS), validate that the proposed model outperforms existing models in gait classification.

show abstract

Skeleton-based abnormal gait recognition with spatio-temporal attention enhanced gait-structural graph convolutional networks

Cited by 14 publications

References 34 publications

FP-GCN: Frequency Pyramid Graph Convolutional Network for Enhancing Pathological Gait Classification

FP-GCN: Frequency Pyramid Graph Convolutional Network for Enhancing Pathological Gait Classification

Model-based and model-free deep features fusion for high performed human gait recognition

Pathological-Gait Recognition Using Spatiotemporal Graph Convolutional Networks and Attention Model

Contact Info

Product

Resources

About