Research of infrared thermal imagery segmentation technology based on visible-light image

摘要

To solve the problem of infrared target recognition, by using the complementarity of visible-light image and infrared-thermal imagery, this article presents a kind of infrared thermal imagery segmentation technology. Segmenting the target edges of visible-light images, and superimposing the edge on the corresponding infrared thermal imagery, then segmenting the infrared thermal imagery by the improved weighted regions growing algorithm. After the test about relevant parameters of the infrared thermal imagery, found that contrast enhancement and entropy increase, witch making it easy to split and recognize, and human eye subjective judgment is also much easier. It put forward a new research method about infrared target recognition.