Speed Bump Detection Using Point Cloud Data

Abstract

Abstract Accurate detection of speed bumps is essential to ensure comfort and safe navigation in autonomous vehicles. Most existing speed bump detection methods depend on image-based techniques. However, identifying speed bumps in images can be challenging, especially when visibility is reduced due to poor lighting or weather conditions or when the speed bumps are not clearly marked. To address these limitations, this paper proposes a method for detecting speed bumps using point cloud data acquired by mobile laser scanning (MLS). Point clouds allow for detecting speed bumps solely based on their geometry, regardless of visual markings on the speed bumps. The proposed method aims to accurately detect speed bumps while overcoming challenges posed by noisy and irregular real-world data. A feature set of geometric features is created to describe the speed bumps and the surrounding flat road surface. This feature set is used as input for machine learning classifiers, which are fine-tuned and combined into an ensemble model. Elevation differences between the potential speed bumps and the surrounding road surface are analysed during post-processing to discard false positives. Different road segments across Trondheim, Norway, consisting of 89 speed bumps, are used to evaluate the proposed method. Experimental results show that the proposed method achieves a recall of 92.2% and a precision of 89.3%, demonstrating the method’s ability to correctly identify speed bumps in challenging real-world conditions.