Abstract
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%.
Highlights
In the field of computer vision, depth information provides more possibilities for various computer vision applications such as human-computer interaction, three-dimensional scene reconstruction, and 3D printing
Depth images are similar to grayscale images, and each pixel value indicates the distance between the surface of the object in the scene and the sensor
Is article outlines the research difficulties and common research methods of human motion recognition, introduces the research background and significance of human motion recognition, and explains the reasons for choosing to use depth information for human motion recognition [8]. En, it summarizes the principles, advantages, and disadvantages of the three mainstream methods for obtaining depth and outlines the classification basis and main categories of the human motion recognition methods based on depth information, and deep research and discussion were carried out from two aspects of human motion recognition based on depth map and skeleton joint points. two aspects of human motion recognition of data comprehensively expound the human motion recognition algorithm based on depth information
Summary
In the field of computer vision, depth information provides more possibilities for various computer vision applications such as human-computer interaction, three-dimensional scene reconstruction, and 3D printing. E acquisition of Mathematical Problems in Engineering high-quality depth images mainly depends on the performance of hardware devices and effective image enhancement algorithms. To solve the shortcomings of the instability of the original depth data received by the Kinect device, especially the problems of noise and large holes, Wang Fuwei proposed a depth recovery algorithm that combines the color map to control the filling and filtering of the holes. Because of its motion characteristics, small area jitter, and difficulty in segmentation, he proposed an improved tracking algorithm for multiple abnormal targets in microscopic images. Two aspects of human motion recognition of data comprehensively expound the human motion recognition algorithm based on depth information This method extracts the outline of the human body in the foreground from the depth image, and it extracts the body skeleton model according to whether the body has occluded by the limbs. Experiments were conducted on the Action 3D dataset and UTD-MHAD dataset and compared with the previous results
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
