Analyzing the Cross-Sensor Portability of Neural Network Architectures for LiDAR-based Semantic Labeling
This addresses the problem of sensor-specific adaptation in LiDAR-based semantic labeling for applications like autonomous driving, offering a more portable solution as LiDAR hardware evolves rapidly, though it is incremental in improving existing methods.
The paper tackles the challenge of transferring neural network architectures across different LiDAR sensor types for semantic labeling, proposing a new CNN architecture that improves portability by 10 percentage points in IoU score compared to a state-of-the-art reference method.
State-of-the-art approaches for the semantic labeling of LiDAR point clouds heavily rely on the use of deep Convolutional Neural Networks (CNNs). However, transferring network architectures across different LiDAR sensor types represents a significant challenge, especially due to sensor specific design choices with regard to network architecture as well as data representation. In this paper we propose a new CNN architecture for the point-wise semantic labeling of LiDAR data which achieves state-of-the-art results while increasing portability across sensor types. This represents a significant advantage given the fast-paced development of LiDAR hardware technology. We perform a thorough quantitative cross-sensor analysis of semantic labeling performance in comparison to a state-of-the-art reference method. Our evaluation shows that the proposed architecture is indeed highly portable, yielding an improvement of 10 percentage points in the Intersection-over-Union (IoU) score when compared to the reference approach. Further, the results indicate that the proposed network architecture can provide an efficient way for the automated generation of large-scale training data for novel LiDAR sensor types without the need for extensive manual annotation or multi-modal label transfer.