This work studies a supervised learning method using 3D LiDAR data for autonomous driving applications. A system of semantic segmentation, including range image segmentation, sample generation, track-level annotation and supervised learning, is developed. The formation and content of a data sample is studied intensively to address the specialty of 3D LiDAR data, which can be represented at a Cartesian or a 2D polar coordinate system, and composed of a segment as the foreground and/or the neighborhood points as the background. A CNN-based classifier is trained to map a given sample to an object label. Qualitative and quantitative experiments show that the background information and multiple feature map fusion significantly improve the performance of the classifier.
Supervised Learning for Semantic Segmentation of 3D LiDAR Data
2019 IEEE Intelligent Vehicles Symposium (IV) ; 1491-1498
01.06.2019
3156698 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch