Human motion tracking and 3D motion track detection technology based on visual information features and machine learning

Zhang, Xin; Xu, Zhongqiu; Liao, Hongbo

doi:10.1007/s00521-021-06703-2

Cited by 7 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fast SVD method [25] is sensitive to different types of background. To solve this problem, a salience enhancement method inspired by the human visual mechanism [39] is adopted to extract local features. However, it does not perform well on strong infrared edges.…”

Section: B the Enhancement Methodsmentioning

confidence: 99%

“…Both the background suppression approach and the SR approach may not effectively differentiate targets from background clutter. Furthermore, a salience enhancement method inspired by the human visual mechanism [39] is adopted to extract local features. However, it does not perform well on strong infrared edges.…”

Section: Strcfd: Small Object Tracking Algorithm Based On Improved St...mentioning

confidence: 99%

See 1 more Smart Citation

STRCFD: Small Maneuvering Object Tracking via Improved STRCF and Redetection in Near Infrared Videos

Qian,

Wang,

Zhang

2024

IEEE Access

View full text Add to dashboard Cite

Tracking small objects in infrared videos is challenging due to a complex background, weak information and target mobility. To deal with these difficulties, an infrared small target tracking algorithm is proposed, which utilizes the Spatial-Temporal Regularized Correlation Filter (STRCF) as the backbone. First, the local image patch that refers to the target and its neighborhood background is given in the STRCF. Then, the guided local contrast mechanism is designed to eliminate noise and distinguish the target from the background. Furthermore, the robustness of the tracking is improved by using the detection model with an adaptive factor of search range, helping to alleviate the problem of tracking migration. Experimental results on entire public near-infrared videos show the superior performance of the proposed algorithm (named STRCFD), compared to several related algorithms in visual effects and objective evaluation. It should be mentioned that the proposed STRCFD achieves an overall precision of 81.1%.

show abstract

Section: B the Enhancement Methodsmentioning

confidence: 99%

Section: Strcfd: Small Object Tracking Algorithm Based On Improved St...mentioning

confidence: 99%

STRCFD: Small Maneuvering Object Tracking via Improved STRCF and Redetection in Near Infrared Videos

Qian,

Wang,

Zhang

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Due to the complexity of human motion, existing research methods impose many constraints on the human body of the research project. In this paper, we present a new method to study various types of human motion information to mainly discuss the reconstruction of the three-dimensional motion skeleton of the human body [1,2]. The basic idea is to build an image of each image based on calibration, applying knowledge of the 3D human models and motion continuity [3].…”

Section: Introductionmentioning

confidence: 99%

Development of Three-dimensional Human Motion Modeling Framework and Its Computational Techniques

Li¹

2022

Proceedings of the 2022 International Conference on Computer Science, Information Engineering and Digital Economy (CSIEDE 2022)

View full text Add to dashboard Cite

The research of virtual human motion modeling and simulation technology is a challenging subject involving physics, robotics, biomechanics, and computer graphics. Virtual human motion simulation based on a physical model is a research hotspot of computer graphics and animation technology, but the algorithm of kinematics and dynamics calculation has not been deeply studied. In this paper, we developed a protocol where the joints are removed in the reverse order of the connection stage in the segmentation stage, and the constraint forces and joint accelerations of the complete kinematic chain are solved. And the hierarchical control strategy of the human reach movement was discussed, and the experimental prototype of the human reach movement was constructed to verify the correctness and effectiveness of the research results.

show abstract

Topical collections on machine learning based semantic representation and analytics for multimedia application

Yan

Liu

2022

Neural Comput & Applic

View full text Add to dashboard Cite

Human motion tracking and 3D motion track detection technology based on visual information features and machine learning

Cited by 7 publications

References 22 publications

STRCFD: Small Maneuvering Object Tracking via Improved STRCF and Redetection in Near Infrared Videos

STRCFD: Small Maneuvering Object Tracking via Improved STRCF and Redetection in Near Infrared Videos

Development of Three-dimensional Human Motion Modeling Framework and Its Computational Techniques

Topical collections on machine learning based semantic representation and analytics for multimedia application

Contact Info

Product

Resources

About