Research on Miners' Human Posture Detection Algorithm Based on MMPose

Abstract

With the continuous improvement of intelligence in the coal industry, intelligent video analysis and judgment of dangerous behaviors that have occurred can no longer meet the needs of human posture detection in underground mines. In this paper, a human posture detection algorithm based on MMPose is proposed to determine the body posture of personnel under the mine at different times, in order to provide effective information for standardizing miner operations, disaster early warning, and accident rescue. The algorithm is based on MMPose technology, which improves and optimizes the existing shortcomings, facilitating the determination of the body posture of underground personnel at different times, and solving the low accuracy issues of occlusion image detection, multi-person image detection, and dark environment detection. The designed algorithm achieves labeling of 17 key points such as eyes, nose, ears, shoulders, elbows, hands, legs, knees, and feet, and can detect various postures such as standing upright, standing sideways, sitting, squatting, and walking. Experiments have shown that this algorithm has a high accuracy in human posture detection and prediction, and can better mark the key points of the human body for occluded images, multi-person images, and dark environments, meeting the real-time requirements of underground personnel posture detection.