In recent years, extreme weather disasters such as heavy snowfall and floods have occurred frequently, bring great challenges to the safe operation of transmission lines. In order to quickly assess the disaster situation of the transmission towers, it is necessary to use satellite-bone synthetic aperture radar (SAR) to quickly survey the conditions of large-scale transmission lines, and to quickly locate and identify hidden dangers of large-scale transmission towers. At present, for the identification of electric towers from high-resolution SAR images in complex background, the existing target detection algorithms have shortcomings in accuracy and efficiency. Therefore, this paper proposes a two-stage target detection algorithm that combines model cascades of YOLO v2 and VGG based on migration learning. In the Stage-1 phase, combined sliding window and non-maximum suppression algorithm, YOLO v2 is used to perform fast electric tower detection on the whole scene SAR image, and the target detection result with high recall rate is obtained. In the Stage-2 stage, the VGG classification model is used to perform secondary classification of the target and background of the target detection result in the Stage-1 stage, further eliminating false positives. This algorithm can improve the accuracy of target recognition using YOLO v2 alone, and effectively reduce the false alarm rate of the model. Through model migration and two-stage deep learning algorithm, the tower targets in the entire scene of one SAR image can be accurately identified. The algorithm is tested by COSMO image of Zhijiang, Hubei Province, and the results show that the recall rate of electric towers can reach 85.7%.