Full Program »
Comparison of major LiDAR data-driven feature extraction methods for autonomous vehicles
Object detection is one of the areas of computer vision that has matured very rapidly. Nowadays, developments in this research area have been shifted towards detection of objects in point clouds. However, LiDAR data is not characterised by having consistency in relative pixel densities and introduces a third dimension, raising a set of drawbacks. The following paper presents a study on the requirements of 3D object detection for autonomous vehicles; presents an overview of the 3D object detection pipeline that generalises the operation principle of models based on point clouds; categorises the recent works on methods to extract features and summarise their performance. To the best of our knowledge this is the first survey on object feature extractors based on LiDAR, offering a guideline for future developments in this area.