Human Motion Tracking Algorithm Based on Image Segmentation Algorithm and Kinect Depth Information

Human motion recognition has an important application value in scenarios such as intelligent monitoring and advanced human-computer interaction, and it is an important research direction in the field of computer vision. Traditional human motion recognition algorithms based on two-dimensional cameras are susceptible to changes in light intensity and texture. The advent of depth sensors, especially the Kinect series with good performance and low price released by Microsoft, enables extensive research based on depth information. However, to a large extent, the depth information has not overcome these problems based on two-dimensional images. This article introduces the research background and significance of human motion recognition technology based on depth information, introduces in detail the research methods of human motion recognition algorithms based on depth information at home and abroad, and analyzes their advantages and disadvantages. The public dataset is introduced. Then, based on the depth information, a method of human motion recognition is proposed and optimized. A moving human body image segmentation method based on an improved two-dimensional Otsu method is proposed to solve the problem of inaccurate and slow segmentation of moving human body images using the two-dimensional Otsu method. In the process of constructing the threshold recognition function, this algorithm not only uses the cohesion of the pixels within the class but also considers the maximum variance between the target class and the background class. Then, the quantum particle swarm algorithm is used to find the optimal threshold solution of the threshold recognition function. Finally, the optimal solution is used to achieve accurate and fast image segmentation, which increases the accuracy of human body motion tracking by more than 30%.

Download Full-text

The Accurate Repair of Image Contour of Human Motion Tracking Based on Improved Snake Model

Complexity ◽

10.1155/2021/9926936 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Ning Feng ◽

Ping Gao

Keyword(s):

Motion Tracking ◽

Moving Objects ◽

Rapid Development ◽

Human Motion ◽

Motion Recognition ◽

Snake Model ◽

Running Time ◽

Sports Science ◽

Human Motion Recognition ◽

Image Contour

With the rapid development of sports science, human motion recognition technology, as a new biometric recognition technology, has many advantages, such as noncontact target, long recognition distance, secret recognition process, and so on. Traditional human motion recognition technology is affected by environmental factors such as motion background, which is prone to rough edges of the recognized objects and loss of motion tracking information, thus further reducing the recognition accuracy. In this paper, the traditional snake model will be improved and optimized to improve the defect of human motion model contour extraction, so as to realize the accurate repair of image contour; in terms of algorithm running time, this paper innovatively improves the construction process of the snake model, further improves the running time of model evaluation, and solves the concave contour problem of corresponding moving objects in the snake model. In order to solve the problem of accurate convergence, this paper improves the snake model of the average moving algorithm and sets the corresponding weight coefficient to distinguish the corresponding moving target background, so as to achieve the convergence of the differential concave contour. In order to verify the superiority of the improved optimized snake model, experiments are carried out in the corresponding database. The experimental results show that the contour of the moving object extracted by the improved snake model algorithm is complete and the segmentation effect is obvious. At the same time, the running speed of the whole algorithm has been significantly improved.

Download Full-text

2D Multi-Person Pose Estimation Combined with Face Detection

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s021800142256002x ◽

2021 ◽

Author(s):

Qiming Li ◽

Lu Xu ◽

Xiaoyan Yang

Keyword(s):

Face Detection ◽

Pose Estimation ◽

Human Motion ◽

Two Dimensional ◽

Estimation Model ◽

Motion Recognition ◽

Human Motion Recognition ◽

The Mean ◽

Human Pose ◽

Validation Set

Pose estimation is the basis and key of human motion recognition. In the two-dimensional human pose estimation based on image, in order to reduce the adverse effects of mutual occlusion among multiple people and improve the accuracy of motion recognition, a structurally symmetrical two-dimensional multi-person pose estimation model combined with face detection is proposed in this paper. First, transfer learning is used to initialize each sub-branch network model. Then, MTCNN is used for face detection to predict the number of people in the image. According to the number of people, the image is input into the improved two-branch OpenPose network. What is more, the double judgment algorithm is proposed to correct the false detection of MTCNN. The experimental results show that compared with TensorPose, which is the latest improved method based on OpenPose, the Average Precision (AP) (Intersection over Union [Formula: see text]) on the validation set is 8.8 higher. Furthermore, compared with OpenPose, the mean AP ([Formula: see text]) is 1.7 higher on the validation set and is 1.3 higher on the Test-dev test set.

Download Full-text

Radar Human Motion Recognition Using Motion States and Two-Way Classifications

2020 IEEE International Radar Conference (RADAR) ◽

10.1109/radar42522.2020.9114613 ◽

2020 ◽

Cited By ~ 1

Author(s):

Moeness G. Amin ◽

Ronny G. Guendel

Keyword(s):

Human Motion ◽

Motion Recognition ◽

Human Motion Recognition

Download Full-text

Improved One-Dimensional Convolutional Neural Networks for Human Motion Recognition

2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) ◽

10.1109/bibm49941.2020.9313296 ◽

2020 ◽

Author(s):

Shengzhi Wang ◽

Shuo Xiao ◽

Zhenzhen Huang ◽

Zhiou Xu ◽

Wei Chen

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Human Motion ◽

Motion Recognition ◽

One Dimensional ◽

Human Motion Recognition

Download Full-text

Application of human motion recognition technology in extreme learning machine

International Journal of Advanced Robotic Systems ◽

10.1177/1729881420983219 ◽

2021 ◽

Vol 18 (1) ◽

pp. 172988142098321

Author(s):

Anzhu Miao ◽

Feiping Liu

Keyword(s):

Extreme Learning Machine ◽

Research Work ◽

Human Motion ◽

Feature Descriptor ◽

Background Variable ◽

Motion Recognition ◽

Network Training ◽

Other Information ◽

Human Motion Recognition ◽

Learning Machine

Human motion recognition is a branch of computer vision research and is widely used in fields like interactive entertainment. Most research work focuses on human motion recognition methods based on traditional video streams. Traditional RGB video contains rich colors, edges, and other information, but due to complex background, variable illumination, occlusion, viewing angle changes, and other factors, the accuracy of motion recognition algorithms is not high. For the problems, this article puts forward human motion recognition based on extreme learning machine (ELM). ELM uses the randomly calculated implicit network layer parameters for network training, which greatly reduces the time spent on network training and reduces computational complexity. In this article, the interframe difference method is used to detect the motion region, and then, the HOG3D feature descriptor is used for feature extraction. Finally, ELM is used for classification and recognition. The results imply that the method proposed here has achieved good results in human motion recognition.

Download Full-text