De-Snowing Algorithm for Long-Wavelength LiDAR | IEEE Conference Publication | IEEE Xplore

De-Snowing Algorithm for Long-Wavelength LiDAR


Abstract:

Long wavelength light detection and ranging (Li-DAR) sensors have emerged as an essential component for increasing the accuracy and range of perception of autonomous vehi...Show More

Abstract:

Long wavelength light detection and ranging (Li-DAR) sensors have emerged as an essential component for increasing the accuracy and range of perception of autonomous vehicles because they employ directed lasers with wavelengths longer than 1µm. However, adverse weather conditions like fog, rain, and snow pose a major challenge. Long-wavelength lasers generally exhibit increased absorption and scattering by water-based ambient particles compared to those with short wavelengths, which reduces sensor accuracy. Filtering out ambient particles is crucial for accurately representing the surrounding environment to ensure safe navigation. Despite extensive research on filtering snow particles from LiDAR point clouds, there is little documented research on long-wavelength LiDAR. Furthermore, existing filters that can be used with long-wavelength LiDAR sensors are limited in speed and accuracy, impeding their implementation in autonomous vehicles. In this paper, we propose a Network-Adjusted Reflectance Filter (NARF), a novel two-phase, physics-informed filtering method for long-wavelength LiDAR that outperforms the state-of-the-art geometric filters in terms of both speed and accuracy. The NARF first uses a physics-based range-corrected directional reflectance (RCDR) filter for initial snow particle classification, followed by a CNN-based RestoreNet to refine the RCDR predictions. Due to the lack of open-source datasets collected from long-wavelength LiDAR systems, we use a custom experimental dataset obtained during a snow event to train and validate the proposed filter.
Date of Conference: 02-05 June 2024
Date Added to IEEE Xplore: 15 July 2024
ISBN Information:

ISSN Information:

Conference Location: Jeju Island, Korea, Republic of

Funding Agency:


I. Introduction

The autonomous vehicle industry is rapidly evolving, driving fast advancements in LiDAR sensor technology and capacity, along with steadily decreasing costs. This makes large-scale LiDAR deployment in the near future inevitable [1]. However, as a laser-based sensor, LiDAR is naturally subjected to particle light scattering physics. For vehicles, this means that ambient particles present during adverse weather, such as fog, snow, and rain droplets can potentially reduce sensor accuracy. Contamination in LiDAR measurements due to snow particles remains a challenge.

Contact IEEE to Subscribe

References

References is not available for this document.