Natural color night vision realization method based on single band infrared image

Abstract

The invention provides a natural color night vision realization method based on a single band infrared image. The method is characterized by providing a characteristic vector which is based on multi-scale and spatial context information and used for analyzing pixel points. The method comprises the following steps of: training a characteristic-vector-based natural color model by adopting a sample study method first; and then, establishing the color distribution of an infrared night vision image by using the trained natural color model to realize a process of automatic colorization. The method has the advantages that: the method can work in a single band infrared image wherein a conventional night vision image colorization method cannot work, and the single band infrared image can be endowed with natural color automatically so as to improve the accuracy and the efficiency of target identification and scene understanding. The method can be applied to various types of civil and military systems such as a night driving assisting system of a vehicle, a video monitoring system, a military target tracking and identifying system and the like.

Description

technical field [0001] The invention relates to a method for realizing color night vision images. Background technique [0002] Infrared imaging technology can change the surface temperature distribution of the target that the human eye cannot directly see into an image that represents the surface temperature distribution of the target that the human eye can see. It is widely used in various military and civilian night vision systems such as monitoring and investigation. . [0003] The standard display for infrared imaging is a monochrome, often grayscale image. However, with the deepening of the understanding of the human visual perception system, scientific research has shown that the color representation of night vision images is significantly better than the monochrome representation of night vision images in terms of helping observers to identify targets. Further scientific research has shown that night vision images that are close to the natural color of the scen...

AI Technical Summary

Problems solved by technology

However, because infrared images are different from low-light images, they have the characteristics of lack of texture information, low contrast, small gray scale changes, and blurred images. The method in this document cannot be applied to the color night vision of infrared images.

Images