In the context of road perception for autonomous vehicles, short-wave infrared (SWIR) has opened up new perspectives beyond the visible spectrum, which is prone to performance degradation in harsh weather conditions like fog, rain and dust. This paper aims to analyze the feasibility of using SWIR images to enhance object detection and segmentation in such weather conditions. In our experiments, we used data obtained from three different cameras - including two SWIR technologies and a conventional visible camera - in different weather conditions. The conditions include a clear day for reference, rain at different rainfall rates, and fog at different visibility ranges. We explored the performance of several deep learning algorithms, originally trained on images from visible domain applied directly to SWIR images. Quantitative and qualitative analyses for detection and segmentation were conducted. When applied to SWIR modalities, the algorithms prove to perform comparatively to visible in the reference case and to improve detection and segmentation in harsh weather cases.

Robust perception in adverse weather conditions remains a significant challenge for autonomous vehicles. Short-wave infrared (SWIR) sensors offer specific physical properties that enable them to penetrate atmospheric disturbances like fog, rain, and snow. However, effectively combining this robustness with the textural and colour information of visible (VIS) cameras is difficult due to signal decorrelation and the limitations of static fusion schemes. To address this, we present VISWIR (Visible and SWIR Weighted Image Reconstruction), a pixel-level fusion method based on a multi-scale pyramid architecture. We introduce an automated strategy for scheduling parameters based on weather conditions using an optimisation framework. Rather than relying on static weights, our method applies offline parameter scheduling to adjust fusion hyperparameters based on the meteorological context. We focus on a multi-objective optimisation approach that maximises perceptual image quality via No-Reference Image Quality Assessment (NR-IQA) metrics. Validated in controlled environment scenarios with varying weather severities, our results confirm the potential of VISWIR as a robust, lightweight algorithmic baseline to enhance the perception capabilities of autonomous vehicles in adverse weather conditions.