A Deep Learning Detection Method for Dense Targets in Remote Sensing Images

Abstract

The invention discloses a deep learning detection method for dense targets in remote sensing images, which is used for extracting dense targets in remote sensing images. First, the image is input into the deep CNN base network to obtain the feature map; second, the deep convolutional features are input into the dense object extraction framework for region of interest extraction (RPN branch), object classification and rectangular frame regression. For the RPN branch, a high-density bias sampler is proposed to mine more samples with high density (hard samples) to improve detection performance. Soft‑NMS is adopted after the dense object extraction framework to retain more positive objects. Finally, the refined rectangular frame is output to realize the number statistics of dense objects.

Description

technical field [0001] The invention belongs to the field of high-resolution remote sensing image recognition, and particularly relates to a deep learning detection method for dense targets in remote sensing images. Background technique [0002] The rapid development of remote sensing technology can now provide a large number of high-resolution remote sensing images. Compared with low-resolution images, high-resolution remote sensing images contain more detailed spatial information, which not only brings opportunities, but also challenges the identification of remote sensing images. Recognition and analysis based on high-resolution remote sensing image technology have been used in remote sensing image target detection tasks. Among them, plastic greenhouse detection is a very important research direction. Greenhouse cultivation is the cultivation of crops such as vegetables, tobacco and fruit by creating a micro-environment. Monitoring and mapping greenhouse areas is inter...

AI Technical Summary

Problems solved by technology

However, it only works on dense targets adjoining surrounding targets

[0004] Although the above methods have greatly improved the performance of dense object detection, it is still difficult to effectively extract extremely dense objects.

Images