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

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.

References in corpus (3)

• Weather Influence and Classification with Automotive Lidar Sensors
• A Benchmark for Lidar Sensors in Fog: Is Detection Breaking Down?
• Pixel-Accurate Depth Evaluation in Realistic Driving Scenarios

Cited by in corpus (10)

• Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Survey
• 4DenoiseNet: Adverse Weather Denoising from Adjacent Point Clouds
• A Survey on Deep Domain Adaptation for LiDAR Perception
• Energy-based Detection of Adverse Weather Effects in LiDAR Data
• Robust 3D Object Detection in Cold Weather Conditions
• Label-Efficient Semantic Segmentation of LiDAR Point Clouds in Adverse Weather Conditions
• Multi-Echo Denoising in Adverse Weather
• Detection of Condensed Vehicle Gas Exhaust in LiDAR Point Clouds
• Efficient Real-time Smoke Filtration with 3D LiDAR for Search and Rescue with Autonomous Heterogeneous Robotic Systems
• Roadmap on Signal Processing for Next Generation Measurement Systems