Due to the lack of a priori information of the object,the real-time early warning detection system has problems such as high false alarm rate and low real-time performance,which limits its wide application in actual combat environments.In order to improve the performance of object detection and recognition in real-world combat environment,this paper proposes a two-channel saliency object recognition algorithm based on improved YOLO network,which firstly uses the complementary characteristics of infrared image and visible image for multi-scale fusion,and uses saliency detection to obtain the suspected object area on the fusion image.Finally,the improved recognition network is used to recognize the suspected area in multi-level.The improved YOLO recognition network adds an auxiliary network to improve the performance of the whole feature extraction network,and uses the attention mechanism to fuse the feature information of the auxiliary network and the backbone network,enhances the effective information channel,suppresses the invalid information channel,and improves the network recognition efficiency.Simulation results show that our proposed model can effectively improve the accuracy of object detection and recognition,and the real-time performance is greatly enhanced.