High-resolution remote sensing image weak target detection method based on deep learning

Abstract

The invention discloses a high-resolution remote sensing image weak target detection method based on deep learning. For a remote sensing image with low resolution, a small target size and fuzzy quality, the method comprises the following steps: firstly, improving the resolution of an image by adopting a WGAN-based super-resolution reconstruction method; inputting the image with the enhanced quality into a target detection framework; carrying out deep feature extraction on the image by using a residual network; fusing the extracted low-level features with the extracted high-level features; it is ensured that the fused multi-layer feature map has rich detail information and also contains high-level semantic information; and carrying out region-of-interest coarse extraction on the feature mapby using the fused multi-layer features and the region suggestion network, mapping the extracted region to the same dimension by using a region-of-interest alignment method, and carrying out subsequent target accurate classification and position refinement to obtain a final target detection result. According to the method, the weak and small target detection precision and recall rate under the conditions of low remote sensing image resolution and complex background are effectively improved.

Description

technical field [0001] The invention relates to the technical fields of video image processing and target detection, in particular to a method for detecting weak targets in high-resolution remote sensing images based on deep learning. Background technique [0002] Remote sensing earth observation technology has been improved in image space, spectrum and time resolution, and can collect multi-sensor multi-source earth observation data. Through efficient multi-source data fusion, remote sensing satellites have high-resolution, all-weather, All-day, large-scale ground observation and imaging capabilities have achieved subversive results in many fields such as military affairs, agriculture, and urban planning, providing strategic support for sustainable development issues such as climate change monitoring and environmental pollution control, and greatly promoting social development and progress. In particular, high-spatial-resolution (high-resolution) remote sensing images, alo...

AI Technical Summary

Problems solved by technology

Due to the large imaging area and long imaging distance of remote sensing images, the spatial resolution of the image is low and the image background is complex; the top-down imaging method of the satellite also makes the target easy to be blocked; and due to factors such as surface reflection and atmospheric refraction There will be some image distortion, etc.

The unique imaging method of remote sensing images makes the objects in the images small in size, low in resolution, lacks sufficient texture information, large background noise interference, and low contrast, resulting in difficult detection cases, which greatly limits remote sensing images in many fine-grained areas. field application

[0006] It can be seen that the method in the prior art has the technical problem of low detection accuracy.

Images