Comparative Run Time Analysis of LiDAR Point Cloud Processing with GPU and CPU

The Light detection and ranging (LiDAR) sensor is well known for its application in the field of surveying and autonomous vehicles. It is used for capturing the three-dimensional view of a scene. The output of the LiDAR sensor, known as point cloud, contains a large number of spatial points leading to bulky data. Any algorithm developed for this data consumes too much time, making it impractical to be used for real-time applications. Recently, Graphics Processing Units (GPUs) have been extensively used for performing the parallel operation. In this paper, we have quantitatively verified the usefulness of GPU for faster LiDAR point cloud data processing as compared to CPU. Algebraic operations were performed on LiDAR point cloud data on GPU, and the run time was found to decrease up to one-sixth as compared to Central Processing Unit (CPU).