Object Detection of Armored Vehicles Based on Deep Learning in Battlefield Environment

摘要

In this paper, the method based on the deep learning is applied to the object detection and recognition task of the armored vehicle. According to the test results, the feasibility of the method is analyzed, it is proved that the Faster RCNN ZF model has a good effect on the detection and recognition of armored armored vehicles in battlefield environment. Compared with the traditional method, the method eliminates the cumbersome image preprocessing link, and it's end-to-end architecture greatly improves the detection and recognition efficiency, showing a strong application prospect.