Multi-source image target association method based on improved dictionary learning

Abstract

The invention discloses a multi-source image target association method based on improved dictionary learning, belongs to the field of information data processing, and mainly solves the problems of information loss and redundant steps caused by first identification and then association of image target association in existing multi-source information data fusion. The method comprises the steps of firstly collecting image data sets of multiple information sources for the same scene or the same target to form an original data set; carrying out unified sparse representation on the multi-source image by utilizing an improved dictionary learning method, and increasing the representation discrimination capability of dictionary set characteristics by introducing label information into an objectivefunction; and constructing a neural network to learn the sparse representation and the label information of each image to obtain a distance measurement standard between the associated target and the non-associated target, and replacing a traditional distance measurement mode to complete the establishment of an association discrimination model. The method fully utilizes the feature information of the image, avoids the step redundancy of the existing method, and has the advantages of high model generation speed, less information loss, good practical effect and the like.

Description

technical field [0001] The invention belongs to the field of intelligence data processing, relates to the generation of a target correlation discrimination model among multi-source heterogeneous images, and is suitable for the fusion processing link of multi-source intelligence information. Background technique [0002] The acquisition of image information generally has the characteristics of wide detection range, long revisit period, and poor positioning accuracy. It can be used for large-scale early warning in the early warning detection process, and the target correlation of various image information can be increased. Increase the density of measuring points, improve the update time of measurement information, and improve the positioning accuracy of targets. The target association between image information is mainly based on the correlation judgment of the feature information of the target under certain space-time constraints. In practical applications, indirect associat...

AI Technical Summary

Problems solved by technology

In practical applications, indirect association is mainly carried out. First, the target feature information is used to identify the target category and model, and then the correlation is judged according to whether the target type and model are consistent. However, this mainly has the following disadvantages: the correlation effect is too dependent on the completeness and The accuracy of the algorithm; the target feature information is identified as category information and then associated results, which increases the loss of information process

At present, most of the research on multi-source image fusion is to achieve image fusion at the pixel level to obtain more detailed information, which is convenient for further analysis, processing and understanding of the image, but it has a high impact on the temporal and spatial registration of the input image. Requirements, and the amount of calculation is large, the processing time is long, and it is difficult to meet the real-time requirements; due to the high dimensionality of feature information and the large difference in feature information of heterogeneous sources among multi-source image information, it is currently seldom done from the perspective of feature-level fusion Related research

Images