11 June 2015 Colored three-dimensional reconstruction of vehicular thermal infrared images
Author Affiliations +
Enhancement of vehicular night vision thermal infrared images is an important problem in intelligent vehicles. We propose to create a colorful three-dimensional (3-D) display of infrared images for the vehicular night vision assistant driving system. We combine the plane parameter Markov random field (PP-MRF) model-based depth estimation with classification-based infrared image colorization to perform colored 3-D reconstruction of vehicular thermal infrared images. We first train the PP-MRF model to learn the relationship between superpixel features and plane parameters. The infrared images are then colorized and we perform superpixel segmentation and feature extraction on the colorized images. The PP-MRF model is used to estimate the superpixel plane parameter and to analyze the structure of the superpixels according to the characteristics of vehicular thermal infrared images. Finally, we estimate the depth of each pixel to perform 3-D reconstruction. Experimental results demonstrate that the proposed method can give a visually pleasing and daytime-like colorful 3-D display from a monochromatic vehicular thermal infrared image, which can help drivers to have a better understanding of the environment.
© 2015 Society of Photo-Optical Instrumentation Engineers (SPIE)
Shaoyuan Sun, Shaoyuan Sun, Henry Leung, Henry Leung, Zhenyi Shen, Zhenyi Shen, } "Colored three-dimensional reconstruction of vehicular thermal infrared images," Optical Engineering 54(6), 063102 (11 June 2015). https://doi.org/10.1117/1.OE.54.6.063102 . Submission:

Back to Top