SAR Image Target Detection and Recognition based on Deep Network

摘要

In this paper, a deep neural network regression method is adopted for SAR images target detection and recognition. Based on the characteristics of SAR images, a deep network model is utilized. This network is effective for extracting neural networks with low resolution and complex composition. At the same time, target detection, recognition and positioning are combined in a regression manner, which improves the detection rate under the condition of ensuring accuracy. It lays a foundation for large-scale SAR image detection of multi-objective types in complex scenes, and has broad application prospects.