Remote sensing image target quick detection method based on rotating anchor point clustering

Abstract

The invention discloses a remote sensing image target quick detection method based on rotating anchor point clustering. The method comprises the steps: firstly designing rotating anchor points based on a k-means clustering algorithm, and obtaining a series of rotating anchor points; performing foreground and background dichotomy and coordinate coarse regression on the rotation anchor point, and combining rotation non-maximum suppression post-processing to obtain positive and negative sample information and a simplified high-quality proposal; and finally, performing multi-scale rotation RoI pooling processing on the proposal to obtain a fixed-length vector containing the region of interest RoIs, inputting the vector into a full connection layer (FC) for specific category classification and coordinate regression, and performing INMS post-processing to obtain a final detection result of the target. According to the method, the redundancy of anchor points can be effectively reduced, the detection speed and the detection precision of a remote sensing image target are improved, the algorithm is easy to implement, parameter adjustment is simple and convenient, and the method has the advantages of mathematical interpretability and the like, and has wide application prospects and good economic benefits.

Description

technical field [0001] The invention relates to a method for quickly detecting a remote sensing image target, in particular to a method for rapidly detecting a remote sensing image target based on rotation anchor point clustering, and belongs to the field of remote sensing image target detection. Background technique [0002] Since the United States launched the first Earth resources satellite in 1972, remote sensing technology has received unprecedented attention from all over the world. The remote sensing image data has the characteristics of high precision, large coverage area, and clear spectral resolution, and is favored by researchers. Object detection is an important part of the image processing field. With the continuous development of remote sensing technology, whether in the military or civilian fields, the demand for specific target detection from remote sensing images is increasing day by day. Indispensable technology. [0003] However, the rapid development of...

AI Technical Summary

Problems solved by technology

The detection method of horizontal anchor points can easily lead to missed detection in the case of dense objects, thereby reducing the detection accuracy; and the manual design of anchor points is not very specific, and the anchor point redundancy is large, which directly leads to the need to increase a large number of different sizes and widths and heights Compared with the anchor point, it is used to cover detection targets of different sizes and shapes. The training process is cumbersome to adjust parameters, which greatly limits the detection speed.

Images