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

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 letter, 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.

I. Introduction

Given that lidar sensors are key for autonomous driving and robotics applications, they are currently being developed by numerous companies in a wide variety of designs. Nevertheless, lidar technology is heavily challenged in adverse weather as the range measurements are highly impaired by fog, dust, snow, rain, pollution, and smog [1]–[6]. Such conditions cause erroneous point measurements in the point cloud data which arise from the reception of back-scattered light from water drops (e.g. rain or fog) or arbitrary particles in the air (e.g. smog or dust).