Colorizing single band intensified nightvision images
article
We present a method to give single band intensified nightvision imagery a natural day-time color appearance. For input, the method requires a true color RGB source image and a grayscale nightvision target image. The source and target image are both transformed into a perceptually decorrelated color space. In this color space a best matching source pixel is deter mined for each pixel of the target image. The matching criterion uses the first order statistics of the luminance distribution in a small window around the source and target pixels. Once a best matching source pixel is found, its chromaticity values are assigned (transferred) to the target pixel while the original luminance value of the target pixel is retained. The only requirement of the method is that the compositions of the source and target scenes resemble each other.
Topics
Intensified imageryColourfalse colourColour visionColor transferFalse colorIntensified imageryNightvisionCamerasColor image processingGlobal positioning systemImage segmentationImage sensorsLightMathematical transformationsMatrix algebraObject recognitionPattern matchingStatistical methodsColor transferFalse colorIntensified imageryNightvisionColor vision
TNO Identifier
13459
Source
Displays, 26, pp. 15-21.
Pages
15-21
Files
To receive the publication files, please send an e-mail request to TNO Repository.