Research on High Resolution Optical Remote Sensing Image Technology Based on Internet Architecture

Target detection technology in high-resolution optical remote sensing images is of great significance both civil and military fields. Based on the Internet architecture, this paper proposes a multi-class target method for images. The fused multi-layer features are used detection. In view challenges complex background deformation target, deformable convolution network can be reference to extract characteristics itself reduce interference order storage space required by deep neural model increase portability network, I also put forward lightening network. Experiments show that our proposed feasible. Compared with popular based has advantages precision recall rate.