Robust Perceptual Night Vision in Thermal Colorization

Transforming a thermal infrared image into a robust perceptual colour Visible image is an ill-posed problem due to the differences in their spectral domains and in the objects' representations. Objects appear in one spectrum but not necessarily in the other, and the thermal signature of a single object may have different colours in its Visible representation. This makes a direct mapping from thermal to Visible images impossible and necessitates a solution that preserves texture captured in the thermal spectrum while predicting the possible colour for certain objects. In this work, a deep learning method to map the thermal signature from the thermal image's spectrum to a Visible representation in their low-frequency space is proposed. A pan-sharpening method is then used to merge the predicted low-frequency representation with the high-frequency representation extracted from the thermal image. The proposed model generates colour values consistent with the Visible ground truth when the object does not vary much in its appearance and generates averaged grey values in other cases. The proposed method shows robust perceptual night vision images in preserving the object's appearance and image context compared with the existing state-of-the-art.

[1]  Alexei A. Efros,et al.  Colorful Image Colorization , 2016, ECCV.

[2]  Mohammad Norouzi,et al.  PixColor: Pixel Recursive Colorization , 2017, BMVC.

[3]  Olivier Debeir,et al.  Multimodal Sensor Fusion In Single Thermal image Super-Resolution , 2018, ACCV Workshops.

[4]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Gregory Shakhnarovich,et al.  Learning Representations for Automatic Colorization , 2016, ECCV.

[6]  Matthew Thomas Sampson An Assessment of the Impact of Fused Monochrome and Fused Color Night Vision Displays on Reaction Time and Accuracy in Target Detection. , 1996 .

[7]  Yong Yu,et al.  Unsupervised Diverse Colorization via Generative Adversarial Networks , 2017, ECML/PKDD.

[8]  Dani Lischinski,et al.  Colorization by example , 2005, EGSR '05.

[9]  Bin Sheng,et al.  Deep Colorization , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[10]  Qian Chen,et al.  Thermal Infrared Colorization via Conditional Generative Adversarial Network , 2018, Infrared Physics & Technology.

[11]  Namil Kim,et al.  Multispectral pedestrian detection: Benchmark dataset and baseline , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Juan A. Aguilar Cavanillas The role of color and false color in object recognition with degraded and non-degraded images , 1999 .

[13]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[14]  Dani Lischinski,et al.  Colorization using optimization , 2004, ACM Trans. Graph..

[15]  Hendrik P. A. Lensch,et al.  Infrared Colorization Using Deep Convolutional Neural Networks , 2016, 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA).

[16]  Hiroshi Ishikawa,et al.  Let there be color! , 2016, ACM Trans. Graph..

[17]  Adam Nyberg Transforming Thermal Images to Visible Spectrum Images Using Deep Learning , 2018 .

[18]  Klaus Mueller,et al.  Transferring color to greyscale images , 2002, ACM Trans. Graph..

[19]  Michael Felsberg,et al.  Generating Visible Spectrum Images from Thermal Infrared , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[20]  Brian C. Lovell,et al.  TV-GAN: Generative Adversarial Network Based Thermal to Visible Face Recognition , 2017, 2018 International Conference on Biometrics (ICB).