Computer vision can facilitate the resue of firefighters in a disaster with the searching timeshortened. To solve the problem that the traditional algorithm is difficult to accurately detect the humanbody target in a disaster environment due to multi-scale, partial occlusion and environmental interfer-ence, a human body detection network based on decoupled head and attention model is proposed. First-ly, for the missing detection caused by small-scale human body targets in disaster environment,YOLOv5 framework was used to construct a shallow detection layer to enhance the recognition ability ofthe network for small targets. Secondly, aiming at the problem that human targets are prone to submergein a complex background in a disaster environment, which leads to the inability to effectively expressthe target features, the lightweight attention module was fused to enhance the saliency of human targets,and the links were added between the original input and output nodes of features to improve the multi-scale feature fusion capability of the network. Finally, in order to reduce the influence of the differencesbetween classification and regression tasks on the detection performance in the human detection net-work, a decoupled head was constructed for human target recognition and localization respectively. Andthe advantages of the proposed algorithm have been verified in various disaster rescue scenarios overthose with five classical algorithms. Compared to the comparison algorithm, the proposed algorithm hasthe highest accuracy, and the mean avearage precision and recall rate can reach 92. 2% and 90. 5% re-spectively. It can not only accurately detect human targets, but also has good real-time and robustness.