Optical remote sensing image detection method and device and storage medium

Abstract

The invention provides an optical remote sensing image detection method and device and a storage medium, and belongs to the field of image detection, and the method comprises the steps: dividing a plurality of optical remote sensing images, and obtaining a plurality of optical remote sensing training images and a plurality of optical remote sensing test images; respectively labeling each optical remote sensing training image to obtain an optical remote sensing labeled image; constructing a training model, and performing model training on the training model according to the plurality of optical remote sensing annotation images to obtain a to-be-tested image detection model; testing a to-be-tested image detection model according to the plurality of optical remote sensing test images to obtain an image detection model; and detecting the optical remote sensing image to be detected through the image detection model to obtain a detection result. According to the method, the target area and the background area are distinguished, the saliency map can be predicted more accurately, the accuracy of optical remote sensing image detection is improved, and a large amount of labor force and time are reduced.

Description

technical field [0001] The invention mainly relates to the technical field of image detection, in particular to an optical remote sensing image detection method, device and storage medium. Background technique [0002] Traditional salient object detection models usually rely on certain low-level features such as color contrast and background priors. With the great success of deep learning techniques in the field of computer vision, models based on fully convolutional networks have become the mainstream of salient object detection architectures. In recent years, great progress has been made in the research of saliency object detection based on natural scenes, but there are few studies on optical remote sensing images. Usually, the foreground area of ​​an optical remote sensing image is similar to the surrounding environment and has objects of different scales. [0003] At present, some salient object detection methods usually use the attention mechanism to capture the seman...

AI Technical Summary

Problems solved by technology

However, these methods fail to introduce the target boundary to define the foreground area while targeting targets of different scales, resulting in inaccurate target detection in the foreground area, which has certain difficulties in distinguishing salient targets in complex scenes

Moreover, existing deep learning-based salient object detection algorithms for optical remote sensing images focus on adopting pixel-by-pixel precise annotation, which requires a lot of labor and time

Images