Evaluation of Polarimetric Fusion for Semantic Segmentation in Aquatic Environments
This addresses the problem of debris segmentation in water for environmental monitoring applications, but is incremental as it benchmarks existing fusion methods on a new dataset.
The paper tackles the problem of accurate segmentation of floating debris in aquatic environments, which is compromised by surface glare and changing illumination, by evaluating polarimetric fusion methods on the PoTATO dataset. Results show polarimetric cues help recover low-contrast objects and suppress false positives, raising mean IoU and lowering contour error compared to RGB inputs, though with increased computational load and risk of new false positives.
Accurate segmentation of floating debris on water is often compromised by surface glare and changing outdoor illumination. Polarimetric imaging offers a single-sensor route to mitigate water-surface glare that disrupts semantic segmentation of floating objects. We benchmark state-of-the-art fusion networks on PoTATO, a public dataset of polarimetric images of plastic bottles in inland waterways, and compare their performance with single-image baselines using traditional models. Our results indicate that polarimetric cues help recover low-contrast objects and suppress reflection-induced false positives, raising mean IoU and lowering contour error relative to RGB inputs. These sharper masks come at a cost: the additional channels enlarge the models increasing the computational load and introducing the risk of new false positives. By providing a reproducible, diagnostic benchmark and publicly available code, we hope to help researchers choose if polarized cameras are suitable for their applications and to accelerate related research.