Multi-scale Interaction for Real-time LiDAR Data Segmentation on an Embedded Platform
This addresses the need for efficient and accurate LiDAR segmentation in autonomous vehicles, representing a strong specific gain rather than an incremental improvement.
The paper tackles the problem of real-time semantic segmentation of LiDAR data for autonomous vehicles by proposing a projection-based method called Multi-scale Interaction Network (MINet), which achieves higher accuracy, fewer parameters, and faster runtime than existing methods, processing over 24 scans per second on an embedded platform.
Real-time semantic segmentation of LiDAR data is crucial for autonomously driving vehicles, which are usually equipped with an embedded platform and have limited computational resources. Approaches that operate directly on the point cloud use complex spatial aggregation operations, which are very expensive and difficult to optimize for embedded platforms. They are therefore not suitable for real-time applications with embedded systems. As an alternative, projection-based methods are more efficient and can run on embedded platforms. However, the current state-of-the-art projection-based methods do not achieve the same accuracy as point-based methods and use millions of parameters. In this paper, we therefore propose a projection-based method, called Multi-scale Interaction Network (MINet), which is very efficient and accurate. The network uses multiple paths with different scales and balances the computational resources between the scales. Additional dense interactions between the scales avoid redundant computations and make the network highly efficient. The proposed network outperforms point-based, image-based, and projection-based methods in terms of accuracy, number of parameters, and runtime. Moreover, the network processes more than 24 scans per second on an embedded platform, which is higher than the framerates of LiDAR sensors. The network is therefore suitable for autonomous vehicles.