Semantic image segmentation

Incorporating Near-Infrared Information into Semantic Image Segmentation

Recent progress in computational photography has shown that we can acquire near-infrared (NIR) information in addition to the normal visible (RGB) band, with only slight modifications to standard digital cameras. Due to the proximity of the NIR band to visible radiation, NIR images share many properties with visible images. However, as a result of the material dependent reflectionin the NIR part of the spectrum, such images reveal different characteristics of the scene. We investigate how to effectively exploit these differences to improve performance on the semantic image segmentation task. Based on a state-of-the-art segmentation framework and a novel manually segmented image database (both indoor and outdoor scenes) that contain 4-channel images (RGB+NIR), we study how to best incorporate the specific characteristics of the NIR response. We show that adding NIR leads to improved performance for classes that correspond to a specific type of material in both outdoor and indoor scenes. We also discuss the results with respect to the physical properties of the NIR response.

The dataset

Semantic Image Segmentation Using Visible and Near-Infrared Channels

Deep Semantic Segmentation Using Nir As Extra Physical Information

S. Bigdeli; S. Susstrunk 

2019 Ieee International Conference On Image Processing (Icip)


26th IEEE International Conference on Image Processing (ICIP), Taipei, TAIWAN, Sep 22-25, 2019.

p. 2439-2443

DOI : 10.1109/ICIP.2019.8803242

Semantic Image Segmentation Using Visible and Near-Infrared Channels

N. Salamati; D. Larlus; G. Csurka; S. Süsstrunk 

Lecture Notes in Computer Science


4th Workshop on Color and Photometry in Computer Vision at ECCV12, Florence, Italy, October 7-13, 2012.

p. 461-471

DOI : 10.1007/978-3-642-33868-7_46

Supplementary material

Here is the link to more qualitative results. Supplementary material