Real-Time Road Segmentation Using LiDAR Data Processing on an FPGA

TL;DR

This paper introduces an FPGA-based CNN approach for real-time LiDAR data processing to improve road segmentation accuracy and speed for autonomous vehicles.

Contribution

It presents a novel FPGA hardware design that accelerates LiDAR-based road segmentation using CNNs, achieving real-time performance with high accuracy.

Findings

Processing each LiDAR scan in 16.9ms

Achieved high accuracy on KITTI benchmarks

Outperformed previous real-time methods

Abstract

This paper presents the FPGA design of a convolutional neural network (CNN) based road segmentation algorithm for real-time processing of LiDAR data. For autonomous vehicles, it is important to perform road segmentation and obstacle detection such that the drivable region can be identified for path planning. Traditional road segmentation algorithms are mainly based on image data from cameras, which is subjected to the light condition as well as the quality of road markings. LiDAR sensor can obtain the 3D geometry information of the vehicle surroundings with very high accuracy. However, it is a computational challenge to process a large amount of LiDAR data at real-time. In this work, a convolutional neural network model is proposed and trained to perform semantic segmentation using the LiDAR sensor data. Furthermore, an efficient hardware design is implemented on the FPGA that can process each LiDAR scan in 16.9ms, which is much faster than the previous works. Evaluated using KITTI road benchmarks, the proposed solution achieves high accuracy of road segmentation.