No abstract

In recent decades, self-driving has been a topic of wide interest for Artificial Intelligence and the Automotive Industry. The irregularities detection on road surfaces is a task with great challenges. In developing countries, it is very common to find un-marked speed bumps on road surfaces which reduce the security and stability of self-driving cars. The existing techniques have not completely solved the speed bump detection without a well-marked signaling. The main contribution of this work is the design of a methodology that use a pre-trained convolutional neural network and supervised automatic classification, by using the analysis of elevations on surfaces through stereo vision, for detect well-marked and no well-marked speed bumps to improve existing techniques.

No abstract

A current challenge for autonomous vehicles is the detection of irregularities on road surfaces in order to prevent accidents; in particular, speed bump detection is an important task for safe and comfortable autonomous navigation. There are some techniques that have achieved acceptable speed bump detection under optimal road surface conditions, especially when signs are well-marked. However, in developing countries it is very common to find unmarked speed bumps and existing techniques fail. In this paper a methodology to detect both marked and unmarked speed bumps is proposed, for clearly painted speed bumps we apply local binary patterns technique to extract features from an image dataset. For unmarked speed bump detection, we apply stereo vision where point clouds obtained by the 3D reconstruction are converted to triangular meshes by applying Delaunay triangulation. A selection and extraction of the most relevant features is made to speed bump elevation on surfaces meshes. Results obtained have an important contribution and improve some of the existing techniques since the reconstruction of three-dimensional meshes provides relevant information for the detection of speed bumps by elevations on surfaces even though they are not marked.