Due to the complex and varied background of the infrared image and the influence of the environment on the recognition of moving target recognition, the accuracy of target recognition in infrared images is very low. Aiming at the emergence of this problem, an infrared image target recognition algorithm based on multi-feature fusion is proposed. The algorithm extracts the color features, motion and edge features of the image, based on the particle filter framework, the above three feature data fusion processing is applied to the particle weight calculation. The experimental results show that the fusion algorithm can improve the robustness and recognition accuracy of infrared image targets in complex and variable environments.