Deep Semantic Segmentation Using Nir As Extra Physical Information

Deep neural networks for semantic segmentation are most often trained with RGB color images, which encode the radiation visible to the human eyes. In this paper, we study if additional physical scene information, specifically Near-Infrared (NIR) images, improve the performance of neural networks. NIR information can be captured with conventional silicon-based cameras and provide complementary information to visible images regarding object boundaries and materials. In addition, extending the networks' input from a three to a four channel layer is trivial with respect to changes to the architecture and additional parameters. We perform experiments on several state-of-the-art neural networks trained both on RGB alone and on RGB plus NIR and show that the additional image channel consistently improves semantic segmentation accuracy over conventional RGB input even for powerful architectures.


Published in:
2019 Ieee International Conference On Image Processing (Icip), 2439-2443
Presented at:
26th IEEE International Conference on Image Processing (ICIP), Taipei, TAIWAN, Sep 22-25, 2019
Year:
Jan 01 2019
Publisher:
New York, IEEE
ISSN:
1522-4880
ISBN:
978-1-5386-6249-6
Keywords:
Laboratories:




 Record created 2020-04-17, last modified 2020-10-25


Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)