In this paper,taking the pictures of the interior of the cargo compartment taken by infrared cameras under different conditions as samples,a method of HOG feature extraction and dimensionality reduction is proposed.Support vector machine,which is commonly used in the field of visible light recognition,was selected as the optimal classification model,and the kernel parameters of the kernel function of support vector machine were found by combining the particle swarm optimization algorithm.Finally,the monitoring of manned operations against rules of the simple lift was realized,with a correct recognition rate of 97%.