Aiming at the problems of low detection accuracy, high false detection rate, and high missed detection rate in bridge apparent disease detection based on target detection method, an improved YOLOv3 high accuracy bridge apparent disease detection and recognition method is proposed. Firstly, in order to realize the effective fusion of local features and global features, a pooling module with a fixed block size is added to the detection layer of YOLOv3. Secondly, in order to enhance the transmission and utilization efficiency of bridge disease features in the network and improve the detection efficiency, DenseNet dense connection network structure is introduced in the feature extraction network of YOLOv3. Finally, due to the insufficient number of samples in the existing bridge disease data set, data enhancement technology is used to expand the sample images. The experimental results show that the improved YOLOv3's average accuracy rate (mAP) on bridge apparent disease detection is 3.0% higher than the original YOLOv3 and the model training time is reduced by 33.2%, while reducing the false detection of bridge apparent disease detection rate and missed detection rate.