Research on Human Action Recognition Method Based on Machine Learning

Human action recognition (HAR) is an important research direction in the field of computer vision, and human action recognition technology provides an important foundation for computers to understand and simulate human behavior. It has been widely used in many practical applications, including human-computer interaction, gesture recognition, motion analysis, motion capture, virtual reality and augmented reality. Early methods were mainly based on the characteristics of manual design and traditional machine learning methods, such as support vector machine (SVM) and Random Forest. These methods usually rely on manually extracted features, such as edge, texture and color information, but they do not perform well in complex scenes and changing environments. With the rise of deep learning, especially the successful application of Convolutional Neural Network (CNN), great breakthroughs have been made in human action recognition. Using CNN, we can learn the feature representation directly from the original image data, which avoids the trouble of manually designing features. This paper expounds the research progress and future development trend of human action recognition methods based on machine learning.