Generating Visible Spectrum Images from Thermal Infrared
| Autor: | Amanda Berg, Michael Felsberg, Jörgen Ahlberg |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Computer science
business.industry Color image 02 engineering and technology 010501 environmental sciences 01 natural sciences Luminance Convolutional neural network Grayscale Visualization Transformation (function) Datorseende och robotik (autonoma system) Teknik och teknologier Darkness 0202 electrical engineering electronic engineering information engineering Chrominance Engineering and Technology RGB color model 020201 artificial intelligence & image processing Computer vision Artificial intelligence business Computer Vision and Robotics (Autonomous Systems) 0105 earth and related environmental sciences |
| Zdroj: | CVPR Workshops |
| ISSN: | 2160-7508 |
| DOI: | 10.1109/cvprw.2018.00159 |
| Popis: | Transformation of thermal infrared (TIR) images into visual, i.e. perceptually realistic color (RGB) images, is a challenging problem. TIR cameras have the ability to see in scenarios where vision is severely impaired, for example in total darkness or fog, and they are commonly used, e.g., for surveillance and automotive applications. However, interpretation of TIR images is difficult, especially for untrained operators. Enhancing the TIR image display by transforming it into a plausible, visual, perceptually realistic RGB image presumably facilitates interpretation. Existing grayscale to RGB, so called, colorization methods cannot be applied to TIR images directly since those methods only estimate the chrominance and not the luminance. In the absence of conventional colorization methods, we propose two fully automatic TIR to visual color image transformation methods, a two-step and an integrated approach, based on Convolutional Neural Networks. The methods require neither pre- nor postprocessing, do not require any user input, and are robust to image pair misalignments. We show that the methods do indeed produce perceptually realistic results on publicly available data, which is assessed both qualitatively and quantitatively. Print on Demand(PoD) ISSN: 2160-7508. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|