Abstract
Colorization of the thermal infrared image is an unsolved problem because usually there is no one-to-one relationship between an object's color and its temperature. In this paper, we propose a new colorization scheme to address this problem. We first create a coarse colorization image that maintains cross-correlation between its RGB channels. Then the matrix of shift, rotation, and scaling between the coarse colorization image and a source natural color image is constructed. Finally, the transformations act on the coarse colorization image to obtain the resultant image, which has the appearance of the source image. Experiments demonstrate the effectiveness of the new scheme and show its superiority to other state-of-the-art methods. The new scheme can be easily extended to the colorization of low illumination images and near-infrared images.
Highlights
Camera and video surveillance systems should work perfectly even in poor lighting and weather conditions
It can be seen that many details have been almost buried in the dark and color information has been completely lost in an infrared image
To test whether the inverted infrared image has the same property as the haze image or not, we compute the histogram of the intensities for the 30 inverted infrared images captured by our infrared camera
Summary
Camera and video surveillance systems should work perfectly even in poor lighting and weather conditions. A new colorization scheme is proposed to improve the quality of thermal infrared images. A series of 1D histograms or a statistic for each histogram bin makes some matches [16], [17] These methods share the limitation that the colorization quality relies heavily on the correspondence between color distribution and grayscale distribution. It renders natural images using a convolutional neural network (CNN) They annotated the SUN dataset [24], generated Scene Labels as additional features, and performed class-specific coloring better with the extracted DAISY features [25]. We propose a novel, simple and effective enhancement and colorization scheme for infrared images. Our algorithm can be extended to the low illumination image colorization and the near infrared image colorization
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have