Action recognition algorithm based on skeletal joint data and adaptive time pyramid

Sima, Mingjun; Hou, Mingzheng; Zhang, Xin; Ding, Jianwei; Feng, Ziliang

doi:10.1007/s11760-021-02116-9

Cited by 5 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, All the machine learning algorithms require manual labeling of discrete actions into letters, demanding significant time and effort. Some researchers automatically extracted features from image and recognized human activities [9][10][11][12][13]. Karpathy A proposed the LTC-CNN algorithm, a full convolutional network that achieved recognition accuracy of 63.3% on the UCF101 dataset [14].…”

Section: Introductionmentioning

confidence: 99%

HAR-ViT:A human activity recognition method based on ViT

Han,

Zeng,

Kuang

et al. 2024

Preprint

View full text Add to dashboard Cite

Human activity recognition has a wide range of applications in various fields, such as video surveillance, virtual reality, and human-computer intelligent interaction. It has emerged as a significant research area in computer vision. Key algorithms utilized include P-LSTM (partial sensing LSTM), ST-GCN (Spatiotemporal graph convolutional networks), and 2s-AGCN (two-flow adaptive graph convolutional networks). Despite the remarkable achievements made by these algorithms, there are still some challenges to address, including unsatisfactory recognition accuracy, convergence difficulties, and limited generalization ability. To tackle these issues, this paper proposes HAR-ViT - a human activity recognition method based on Vision Transformer architecture. The enhanced AGCN (eAGCN) map filter is employed to assign weights to human skeleton data, highlighting key nodes and promoting model convergence. The position encoder module captures precise timing information while the transformer encoder efficiently compresses sequence data features to enhance calculation speed. Human activity recognition is accomplished through multi-layer perceptron (MLP) classifiers. Experimental results demonstrate that the proposed method achieves an accuracy of 91.06% for cross-subject and 96.73% for cross-view human behavior recognition on the NTU60 dataset respectively; similarly achieving accuracies of 87.61% and 89.02% on the NTU120 dataset for the same task respectively compared to state-of-the-art algorithms with an improved accuracy of approximately 1%, while reducing total parameter count by 57.24%.

show abstract

Section: Introductionmentioning

confidence: 99%

HAR-ViT:A human activity recognition method based on ViT

Han,

Zeng,

Kuang

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Human action recognition (HAR) 1–4 has been identified as an indispensable element of computer vision due to its wide scope of applicability that includes but not limited to security, gaming, rehabilitation, sports training, surveillance, and health care. The two most commonly used methodologies for HAR are the vision and wearable sensor‐based methodologies.…”

Section: Introductionmentioning

confidence: 99%

Representative‐discriminativedictionary learning algorithm for human action recognition using smartphone sensors

Rajamoney¹,

Ramachandran²

2022

Concurrency and Computation

View full text Add to dashboard Cite

SUMMARY With the advancement of mobile computing, understanding, and interpretation of human activities has become increasingly popular as an innovative human computer interaction application over the past few decades. This article presents a new scheme for action recognition based on sparse representation theory using a novel dictionary learning algorithm. This system employs two types of inertial signals from smartphones namely, accelerometer and gyroscope sensory data. Attainment of higher values of classification accuracy depends on the creation of effective dictionaries that completely retain the important features of every action while maintaining the least correlation with the features of other actions. Accordingly, in this research, we propose a new algorithm for learning dictionaries with two levels of dictionary training that aims at learning a compact, representative, and discriminative dictionary for each class. Unlike typical dictionary learning algorithms that aim at the creation of dictionaries that best represents the features of each class, our proposed algorithm incorporates a discriminative criterion that eventually produces better classification results. To validate the proposed framework, all the experiments were performed using three publicly available datasets.

show abstract