Weather Influence and Classification with Automotive Lidar Sensors

Abstract

Lidar sensors are often used in mobile robots and autonomous vehicles to complement camera, radar and ultrasonic sensors for environment perception. Typically, perception algorithms are trained to only detect moving and static objects as well as ground estimation, but intentionally ignore weather effects to reduce false detections. In this work, we present an in-depth analysis of automotive lidar performance under harsh weather conditions, i.e. heavy rain and dense fog. An extensive data set has been recorded for various fog and rain conditions, which is the basis for the conducted indepth analysis of the point cloud under changing environmental conditions. In addition, we introduce a novel approach to detect and classify rain or fog with lidar sensors only and achieve an mean union over intersection of 97.14 % for a data set in controlled environments. The analysis of weather influences on the performance of lidar sensors and the weather detection are important steps towards improving safety levels for autonomous driving in adverse weather conditions by providing reliable information to adapt vehicle behavior.

The Perception System of Intelligent Ground Vehicles in All Weather Conditions: A Systematic Literature Review

“…Reduced power would alter the signal-to-noise ratio of the lidar sensor and influence its detection threshold, which leads to degraded perception performance. In [ 114 ], the depth of lidar performance in fog is studied and the observed light is scattered by fog particles, which not only reduces the detection range dramatically, but also leads to false detections. In the same study, the fog condition showed similar performance degradation to the airborne environment.…”

Weather Classification Using an Automotive LIDAR Sensor Based on Detections on Asphalt and Atmosphere

“…These sensors use the change in the amount of vertically polarized light or its resonance frequency caused by the different phases of water to classify between ice, snow and mixtures [ 31 ]. A third alternative, and the focus of this paper, is to use advanced driver assistance systems (ADAS) sensors like visible spectrum (VIS) cameras, ultrasound, radar or LIDAR whose main purpose is the detection of static and moving objects but whose performance is affected by weather [ 32 ]. All these techniques can be used by themselves or combined to provide different levels of classification accuracy [ 30 ].…”

A Global Path Planner for Safe Navigation of Autonomous Vehicles in Uncertain Environments

“…Hsu, Tokura, Kubo, Gu, and Kamijo [30] proposed an improved GNSS positioning approach that detects the GNSS inconsistency and excludes satellites with higher errors in urban canyon environments. Numerous studies [31][32][33] have also investigated the influence of weather conditions, such as rain and fog on LiDAR, radar, and camera sensors. Moreover, Alharbi and Karimi [2] have examined sensor uncertainties affecting the safety of road users during AV navigation; they proposed five algorithms to measure and highlight the navigation accuracy attainable in challenging environmental conditions.…”