Infrared simulation image quality evaluation method based on random forest

Abstract

The invention discloses an infrared simulation image quality evaluation method based on a random forest, and mainly solves the problem that an infrared simulation image quality evaluation result is inconsistent with human subjective perception due to lack of objective evaluation criteria and neglect of human visual features in the prior art. The method comprises the following steps: acquiring an infrared simulation image; respectively extracting pixel brightness features, structural features, shape features and texture features of the infrared simulation image; and carrying out training prediction by using a random forest regression device. The infrared simulation image quality evaluation result better conforms to visual perception of human eyes, and the evaluation result is more accurate. The method can be widely applied to the technical field of infrared image processing.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to an infrared simulation image quality evaluation method based on random forest in the technical field of infrared simulation image processing. The invention can be used to evaluate the quality of infrared simulation images. Background technique [0002] Infrared simulation image quality evaluation has important applications in image processing, simulation system verification and other fields. At present, although there are many evaluations on the simulation effect of infrared scene simulation images, it is mainly to evaluate and correct each module during the simulation process, or to verify and analyze specific targets or backgrounds according to project requirements. The simulation effect still needs expert identification and certification, and there is no objective evaluation standard. At the same time, for the evaluation of the simulated image quality, the tra...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the deficiencies of the above-mentioned prior art, and propose a method for evaluating the quality of infrared simulation images based on random forests, which is used to solve the problem that the prior art ignores human visual features and cannot summarize the overall characteristics of infrared simulation images, and artificial Assigning weights to the evaluation indicators of each feature leads to the lack of objective evaluation criteria for the quality evaluation of infrared simulation images

Images