Optical remote sensing image target detection method based on integrated deep convolutional network

Abstract

The invention discloses an optical remote sensing image target detection method based on an integrated deep convolutional network, and mainly solves problems in the prior art that the number of targets which are wrongly detected and a testing process is complex and tedious. The method comprises the following specific steps: (1), constructing a multi-branch deep network; (2), generating a trainingdata set containing a target area; (3), carrying out the first training of the integrated deep convolutional network; (4), generating training data sets of all regions; (5), carrying out the second training of the integrated deep convolutional network; (6), generating a test data set; (7), obtaining a test result map; (8), calculating an average precision. The method can achieve the extraction oftarget candidate frames of all no-target regions as negative samples, makes the most of the information of an optical remote sensing image, achieves the better discrimination of the target in the optical remote sensing image and a complex background, is simple in testing process, and is small in number of targets which are wrongly detected in a detection result.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to an optical remote sensing image target detection method based on an integrated deep convolution network in the technical field of target detection image processing. The invention can be used to detect ground objects such as planes and ships from optical remote sensing images. Background technique [0002] Optical remote sensing images play an irreplaceable role in national defense and civilian applications. Because the imaging mechanism is very different from visible light images, it is particularly important to study processing algorithms for the characteristics of this type of image. Target detection in optical remote sensing images is one of the important applications and basic problems of computer vision and image processing technologies in the field of remote sensing. With the continuous development and progress of remote sensing in imaging technology, optica...

AI Technical Summary

Problems solved by technology

Although this method distinguishes water areas through sea and land segmentation, it can reduce the false alarm rate and improve the accuracy of target detection, but the method still has the disadvantage that it needs to perform sea and land segmentation on optical remote sensing images, which requires region segmentation, feature Multiple steps such as extraction make the testing process complicated and cumbersome

Although this method has a good effect on natural image target detection, the disadvantage of this method is that due to the complex background of optical remote sensing images and a lot of interference information, the target detection method is directly applied to optical remote sensing images. It is easy to misdetect the background as the target, resulting in low target detection accuracy

Images