HSI-Road Relabeled: Surface-Aware Road-Scene Segmentation
arXiv:2609.12151v1 Announce Type: new Abstract: The HSI-Road dataset provides paired RGB and 25-channel NIR (600—960~nm) images with binary masks but no surface-level labels.~This paper introduces a manually labeled six-class taxonomy: Background, Asphalt, Concrete, Dirt, Water, and Grass, and an RGB-to-NIR registration pipeline with corresponding annotations. Six semantic-segmentation models (SSMs) are evaluated under four input configurations: original-resolution RGB (RGB_{text{ori}}), registered low-resolution RGB (RGB_{text{reg}}), NIR, and channel-stacked RGB_{text{reg}}—NIR (RGBN_{text{stk}}). The comparison quantifies the effect of spatial-resolution reduction on RGB, along with evaluation of NIR and RGBN_{text{stk}}, with results reported using per-class and mean IoU and F1 scores. RGB_{text{ori}} achieves the highest overall performance but contains 12times more pixels than the matched-resolution inputs. At the matched 192times384 resolution, RGBN_{text{stk}} outperforms NIR for all six SSMs and RGB_{text{reg}} for five of six, with the most consistent gains for the Water class. These results highlight the importance of spatial resolution while showing that NIR provides complementary information to RGB.