CNN-Based Lidar Point Cloud De-Noising in Adverse Weather
| Autor: | Philipp Schindler, Florian Piewak, Robin Heinzler, Wilhelm Stork |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
0209 industrial biotechnology Control and Optimization Computer science Computer Vision and Pattern Recognition (cs.CV) Real-time computing Computer Science - Computer Vision and Pattern Recognition Biomedical Engineering Point cloud 02 engineering and technology 01 natural sciences law.invention Computer Science - Robotics 020901 industrial engineering & automation Artificial Intelligence law Radar Mechanical Engineering 010401 analytical chemistry Mobile robot Filter (signal processing) 0104 chemical sciences Computer Science Applications Human-Computer Interaction Data set Lidar Control and Systems Engineering Computer Vision and Pattern Recognition Robotics (cs.RO) |
| Zdroj: | IEEE Robotics and Automation Letters. 5:2514-2521 |
| ISSN: | 2377-3774 |
| DOI: | 10.1109/lra.2020.2972865 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|