Remote sensing image target detection method based on anchor-free frame

Abstract

The invention provides a remote sensing image target detection method based on an anchor-free frame. The method comprises the following steps: building an anchor-free remote sensing image target detection model which comprises a feature extraction network, a feature pyramid, and an anchor-free frame detector; acquiring a remote sensing image, and performing sliding partition and segmentation to obtain small-size images; inputting the small-size images into the feature extraction network, and obtaining three feature maps with different scales by utilizing a feature pyramid structure; respectively inputting the feature maps into the anchor-frame-free detector for prediction to obtain target prediction results; designing a multi-index fusion loss function, and completing the training of the target detection model through employing the target prediction results and the multi-index fusion loss function, and obtaining a trained target detection model; and performing remote sensing image target detection by using the trained target detection model. The method has the advantages that the remote sensing image target detection model which is small in hyper-parameter quantity, low in model complexity and high in detection precision is established.

Description

technical field [0001] The invention relates to the field of object detection, in particular to an anchor frame-free remote sensing image object detection method. Background technique [0002] Most of the existing remote sensing image target detection methods adopt two methods: [0003] (1) Use the anchor frame to predict the remote sensing image target, match the anchor frame with the real frame, and select the anchor frame with the highest matching degree as the final prediction result; [0004] (2) Use the horizontal frame to mark the target of the remote sensing image, and its expression form is the coordinates of the center point and the length and width. [0005] The existing pre-defined anchor frame detector mainly uses the generated anchor frame plus offset to match the target real frame, and finally the result of predicting the bounding box is the anchor frame with the highest matching degree plus the offset of the center point. However, on remote sensing images, ...

AI Technical Summary

Problems solved by technology

[0006] In view of this, the present invention mainly solves the problem of too many hyperparameters related to the anchor frame and the multi-direction of the target in the remote sensing image target detection, and proposes a remote sensing image target detection method based on no anchor frame

Images