Two-stage remote sensing target detection method based on target center point estimation

Abstract

The invention relates to a two-stage remote sensing target detection method based on target center point estimation. A sample library is constructed by using a remote sensing image and an annotation file of an interested category target, a two-stage remote sensing target detection network based on target center point estimation is trained, and features of the interested category target on the remote sensing image are learned. And target detection is performed on a new remote sensing image by using the trained network model, thereby realizing automatic category judgment and bounding box positioning of an interested target on the remote sensing image. According to the method, the regional suggestion network is constructed according to the spatial position distribution characteristics of the targets on the remote sensing image, and multi-category target candidate frames are directly generated. Compared with a method in which dense target candidate frames are firstly generated, then the best candidate frame is selected from the dense target candidate frames by using a non-maximum suppression method, and subsequent target identification and bounding box correction are carried out, the method of the invention has higher efficiency and precision, and is more suitable for target detection tasks of remote sensing images.

Description

technical field [0001] The invention relates to a two-stage remote sensing target detection method based on target center point estimation, which realizes automatic image positioning and recognition of interested targets in optical remote sensing images, and can be used for urban environment monitoring, land use planning, forest fire monitoring, and traffic flow management and other fields. Background technique [0002] Image object detection is a basic task in computer vision and photogrammetry. It plays an extremely important role in urban resource environment monitoring, land use planning, forest fire monitoring, traffic flow management, and object change detection. From the early traditional algorithms based on manually designed features and sliding windows to find potential targets, to the current dominant deep learning-based target detection methods, the accuracy and automation level of automatically identifying and locating targets of interest from images have been gr...

AI Technical Summary

Problems solved by technology

However, in these existing algorithms, the location distribution characteristics of targets in remote sensing images have hardly been considered

Different from the distribution of targets in natural close-range images, in remote sensing images, there is almost no overlap of targets of the same category. Therefore, the strategy of generating target candidate frames based on the dense anchor frame mechanism designed in the target detection algorithm in the field of computer vision, and the subsequent use for culling Repeated non-maximum suppression operations for candidate boxes are unnecessary for remote sensing object detection algorithms, and they even hurt the accuracy of object detectors

Images