Optical Remote Sensing Object Detection Based on Background Separation and Small Object Compensation Strategy
Yan Dong, Haotian Yang, Shanliang Liu, Guangshuai Gao, Chunlei Li
Abstract
Solid and accurate object detection in optical remote sensing images still remains significant challenges such as complex background and weak object information. To alleviate above problems, we propose a revolutionary one-stage object detection network. Specifically, the proposed effective localization attention is embedded in deep feature maps with more channels, and is used to locate channels that are effective for detection tasks through one dimensional convolution operations. Following that, a small object compensation strategy is proposed to use compensation fusion operation to enable the reuse and compensation of weak object information. Additionally, a background separation strategy is designed to separate foreground and background, highlighting the features of interest, suppressing background noise. To ascertain our model, extensive experiments are conducted in three public datasets, it can simply achieve mAP of 94.2%, 70.7% and 80.5% in NWPU VHR-10, DIOR and DOTA datasets.