CNN-based Lidar Point Cloud De-Noising in Adverse Weather

TL;DR

This paper introduces a CNN-based method to filter out weather-induced noise in lidar point clouds, significantly improving scene understanding in adverse weather conditions for autonomous vehicles.

Contribution

It presents the first CNN-based approach for lidar de-noising in adverse weather, demonstrating superior performance over geometric filtering methods.

Findings

Significant performance improvement over state-of-the-art geometric filtering.

Effective in heavy rain and dense fog conditions.

Large controlled dataset used for training and evaluation.

Abstract

Lidar sensors are frequently used in environment perception for autonomous vehicles and mobile robotics to complement camera, radar, and ultrasonic sensors. Adverse weather conditions are significantly impacting the performance of lidar-based scene understanding by causing undesired measurement points that in turn effect missing detections and false positives. In heavy rain or dense fog, water drops could be misinterpreted as objects in front of the vehicle which brings a mobile robot to a full stop. In this paper, we present the first CNN-based approach to understand and filter out such adverse weather effects in point cloud data. Using a large data set obtained in controlled weather environments, we demonstrate a significant performance improvement of our method over state-of-the-art involving geometric filtering. Data is available at https://github.com/rheinzler/PointCloudDeNoising.