Cone Detection using a Combination of LiDAR and Vision-based Machine Learning

TL;DR

This paper presents a cone detection system for autonomous vehicles that combines LiDAR-based candidate preselection with CNN-based image classification, enabling reliable detection at higher speeds.

Contribution

It introduces a novel fusion of LiDAR and vision data for cone detection, improving accuracy and robustness for autonomous driving applications.

Findings

Effective cone detection at higher vehicle velocities

High classification accuracy with CNNs

Potential for fully autonomous navigation around cones

Abstract

The classification and the position estimation of objects become more and more relevant as the field of robotics is expanding in diverse areas of society. In this Bachelor Thesis, we developed a cone detection algorithm for an autonomous car using a LiDAR sensor and a colour camera. By evaluating simple constraints, the LiDAR detection algorithm preselects cone candidates in the 3 dimensional space. The candidates are projected into the image plane of the colour camera and an image candidate is cropped out. A convolutional neural networks classifies the image candidates as cone or not a cone. With the fusion of the precise position estimation of the LiDAR sensor and the high classification accuracy of a neural network, a reliable cone detection algorithm was implemented. Furthermore, a path planning algorithm generates a path around the detected cones. The final system detects cones even at higher velocity and has the potential to drive fully autonomous around the cones.