Efficient human motion capture data annotation via multi‐view spatiotemporal feature fusion

Liu, Xin; Meng, Xu; Peng, Shu-Juan; Fan, Wentao; Du, Ji-Xiang

doi:10.1049/iet-spr.2016.0542

Cited by 5 publications

(4 citation statements)

References 30 publications

(76 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, they use discriminant correlation analysis to fuse these two types of motion features and further employ extreme learning machines to annotate each submotion segment. Extensive experiments in public databases show that the proposed method is effective compared to existing similar methods [7]. The above studies provide a detailed analysis of the application of target tracking techniques and multifeature fusion.…”

Section: Related Workmentioning

confidence: 91%

“…The image corresponding to the minimum cut D is divided into Bð DÞ, and the segmentation cost defined by formula (1), the segmentation cost of Bð DÞ is the smallest among all segmentations. For any partition D in a feasible cut set, according to formula (7) and the weights of the edges in the graph, the cost of the graph cut D can be calculated by the fol-lowing formula:…”

Section: R E T R a C T E D R E T R A C T E Dmentioning

confidence: 99%

See 1 more Smart Citation

Multifeature Fusion Human Pose Tracking Algorithm Based on Motion Image Analysis

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Human pose and motion detection is an important area of computer vision research, covering the interplay of different fields such as image processing, pattern recognition, and artificial intelligence. Due to the complexity of human motion, existing 3D recognition and pose detection methods based on low-quality depth images are not very accurate and reliable. Due to the time-sensitive nature of features, a single feature cannot adapt to the dynamic changes of the scene, so it is difficult for the target tracking algorithm based on a single feature to achieve robust tracking results. If multiple features are fused and applied in the tracking algorithm, the complementarity between different features can be used to better adapt to the scene changes and achieve robust tracking results. In order to solve the problem of human pose and human motion recognition in low-quality depth images, this paper uses the Kinect somatosensory camera to obtain 20 human skeleton joint points through the Kinect skeleton tracking technology. This paper studies the typical human posture and interactive action recognition technology in daily life. On the basis of understanding the characteristics of skeletal data, this paper proposes a distance feature and angle feature model combined with human body structure. Through the experimental results, it is found that the distance feature and the angle feature value are basically not affected by the distance change. When the subjects turned 45° to the left and 45° to the right, the distance characteristics changed, which was different from the characteristic data when the subjects turned around.

show abstract

Section: Related Workmentioning

confidence: 91%

Section: R E T R a C T E D R E T R A C T E Dmentioning

confidence: 99%

Multifeature Fusion Human Pose Tracking Algorithm Based on Motion Image Analysis

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Human error cannot be eliminated since all humans will make mistakes [37]. Instead of placing blame on the operator, efforts should be made to reduce the risk of human error from both consequence and probability perspectives.…”

Section: Proposed Framework For Risk Assessment Of Human Factors In Aviationmentioning

confidence: 99%

Bibliometric analysis of human factors in aviation accident using MKD

Wan

Liang

Yan

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

This study aims to provide a better understanding of human factors and human performance mechanism in aviation accident analysis by visualisation and taxonomy analysis using mapping knowledge domain (MKD). An overview of aviation accident analysis involving human factors is first conducted, followed by an introduction of several conceptual models and human reliability analysis methods. Finally, a specific framework for risk assessment of human factors in aviation is proposed. The human factors analysis and classification system structure combined with the quantitative method is the most frequently used mode in aviation accident analysis. From a macro ergonomic perspective, systematic consideration has been emphasised frequently in existing research. Pilots or individuals are thought to be associated with the organisations and environment they located in. On the other hand, the micro ergonomic aspect prefers a quantitative and probabilistic way to reveal the individual's failure mode or error rate. Based on previous studies, the proposed framework provides a systematic view to help with the evaluation of human performance in aviation, taking into account human issues as well as management and environmental factors.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…Human motion posture analysis first rose abroad. With the advent of the new century, Chinese domestic research experts also began the research and analysis of three-dimensional posture [ 15 ].…”

Section: Introductionmentioning

confidence: 99%

Identification Model of Writhing Posture of Classical Dance Based on Motion Capture Technology and Few-Shot Learning

Zhang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Chinese classical dance is cut into the inner verve from a grasp of external form in dance instruction, and the aesthetic fashion and artistic norms of classical dance are established with historical depth. The “professional specificity” of characters and the “language description” of plots are eliminated in Chinese classical dance creation, highlighting the contemporary spirit of classical dance creation. Chinese classical dance was born during the early years of the People’s Republic of China. The term “classical dance” did not refer to all Chinese classical dances at the time; rather, it referred to a dance form that embodied China’s national spirit and had a classical cultural heritage based on Chinese traditional dance. The average frequency of step-over was 0.9, which was higher than the average rate of basic turnover of 0.75 and step-by-step turnover of 0.5, according to the results of the SPSS19.0 analysis. As a result, except for a few points with loud noise, it can be concluded that stepping over is an effective feature. The recognition model of the somersault posture of classical dance is studied in this paper, a database for real-time acquisition of three-dimensional data of human motion is established, and the Google model of human body characteristics is obtained based on feature plane matching of human body posture, all using motion capture technology and few-shot learning. The above data has good reference and application value for improving teachers’ teaching level and arousing students’ learning enthusiasm in the dance teaching process when applied to posture teaching and analysis. The captured data can convert human motion in real three-dimensional space into data in virtual three-dimensional space. Motion capture technology converts human motion information into a technology that can be recognized by computers.

show abstract

Efficient human motion capture data annotation via multi‐view spatiotemporal feature fusion

Cited by 5 publications

References 30 publications

Multifeature Fusion Human Pose Tracking Algorithm Based on Motion Image Analysis

Multifeature Fusion Human Pose Tracking Algorithm Based on Motion Image Analysis

Bibliometric analysis of human factors in aviation accident using MKD

Identification Model of Writhing Posture of Classical Dance Based on Motion Capture Technology and Few-Shot Learning

Contact Info

Product

Resources

About