Multi-feature fusion tracking algorithm based on generative compression network

Wang, Peng; Fu, Huitong; Li, Xiaoyan; Guo, Jian; Lv, Zhigang; Di, Ruohai

doi:10.1016/j.future.2021.05.031

Cited by 8 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, Motion Capture System (MoCap) and related technologies have been widely used in the fields of sports science, biomechanics, and rehabilitation medicine [ 1 , 2 ]. For example, the wearable Inertial Measurement Unit (IMU) contains components such as accelerometer, gyroscope, and magnetometer sensors, which can perform three-axis measurements and quantify acceleration, angular velocity, and direction of motion based on the hierarchical structure of human motion [ 3 ].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Algorithm-Based Target Detection and Fine Localization of Technical Features in Basketball

Lian

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Based on SSD to detect players, a super-pixel-based FCN-CNN player segmentation algorithm is proposed to filter out the complex background around players, which is more conducive to the subsequent pose estimation for target detection and fine localization of basketball technical features. The high resolution capability of CNN is used to extract images and perform computational preprocessing to identify typical basketball sports actions in video streams—rebounds, shots, and passes—with an accuracy rate of up to 95.6%. By comparing with three classical classification algorithms, the results prove that the target detection system proposed in this study is effective for target detection and fine localization of basketball sports technical features.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Learning Algorithm-Based Target Detection and Fine Localization of Technical Features in Basketball

Lian

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…According to the research of relevant experts, mainly according to the following recruitment criteria to determine the candidates. According to the requirements of the company, the recruitment indicators adopted in this paper are shown in Table 1 [7].…”

Section: Selection Of Recruitment Indicatorsmentioning

confidence: 99%

Intelligent collection system of human resource information based on clustering algorithm

Liu¹,

Xie²,

Chen³

et al. 2023

International Conference on Signal Processing and Communication Technology (SPCT 2022)

View full text Add to dashboard Cite

Aiming at the popularization of intelligent information collection technology and the demand of fairness and objectivity of human resource assessment, a human resource assessment management system based on K-means clustering is proposed. This paper introduces the principle and steps of K-means clustering algorithm, designs its functional modules and overall architecture in combination with the requirements and indicators of human resources assessment, designs and codes the realization of each functional module in detail, and gives the interface diagrams of some functional modules. Through the design, it provides a new reference for the objective evaluation of human resources assessment, and further strengthens the practical application of information technology in enterprise management.

show abstract

“…Targets in complex real-world scenes are susceptible to interference factors such as motion blur, low resolution, illumination scale changes, and occlusion deformation, so designing a robust tracking algorithm to achieve robust real-time tracking of targets still faces a great challenge among existing target tracking algorithms, which are mainly divided into traditional classical target tracking algorithms based on the artificial features and deep network target tracking algorithms based on the depth features [1]. The overall artificial features widely used in traditional target tracking algorithms can be divided into grayscale features, color features concave, and gradient features.…”

Section: Introductionmentioning

confidence: 99%

Generative Target Tracking Method with Improved Generative Adversarial Network

Yang,

Chen

2023

IET Circuits, Devices & Systems

View full text Add to dashboard Cite

Multitarget tracking is prone to target loss, identity exchange, and jumping problems in the context of complex background, target occlusion, target scale, and pose transformation. In this paper, we proposed a target tracking algorithm based on the conditional adversarial generative twin networks, using the improved you only look once multitarget association algorithm to classify and detect the position of the target to be detected in the current frame, constructing a feature extraction model using generative adversarial networks (GANs) to learn the main features and subtle features of the target, and then using GANs to generate the motion trajectories of multiple targets, finally fuzing the motion and appearance information of the target to obtain the optimal match. The optimal matching of the tracked targets is obtained. The experimental results under OTB2015 and IVOT2018 datasets demonstrate that the proposed multitarget tracking algorithm has high accuracy and robustness, with 65% less jumps and 0.25% more accuracy than the current algorithms with minimal identity exchange and jumps.

show abstract

Multi-feature fusion tracking algorithm based on generative compression network

Cited by 8 publications

References 18 publications

Deep Learning Algorithm-Based Target Detection and Fine Localization of Technical Features in Basketball

Deep Learning Algorithm-Based Target Detection and Fine Localization of Technical Features in Basketball

Intelligent collection system of human resource information based on clustering algorithm

Generative Target Tracking Method with Improved Generative Adversarial Network

Contact Info

Product

Resources

About