An evaluation of machine learning methods for speed-bump detection on a GoPro dataset

Autor(es)

Marques, Johny ^[1] ; Alves, Raulcezar ^[1] ; Oliveira, Henrique C. ^[2] ; MendonCa, Marco ^[3] ; Souza, Jefferson R. ^[1]

Afiliação do(s) autor(es)

^[1] Univ Fed Uberlandia, Fac Comp, Av Joao Naves de Avila 2121, BR-38400902 Uberlandia, MG - Brazil

^[2] Univ Estadual Campinas, Escola Engn Civil Arquitetura & Urbanismo, Rua Saturnino Brito, 224, Cidade Univ Zeferino Vaz, BR-13083889 Campinas, SP - Brazil

^[3] Univ New Brunswick, Geodesy & Geomat Engn Dept, 15 Dineen Dr, Fredericton, NB E3B 5H5 - Canada

• Tipo de documento: Artigo Científico
• Fonte: Anais da Academia Brasileira de Ciências; v. 93, n. 1 2021.
• Citações Web of Science: 0

Resumo

Abstract Every day, new applications arise relying on the use of high-resolution road maps in both academic and industrial environments. Autonomous vehicles rely on digital maps to navigate when optical sensors cannot be trusted, such as heavy rainfalls, snowy conditions, fog, and other situations. These situations increase the risks of accidents and disable the potentials of real-time mapping sensors. To tackle those problems, we present a methodology to automatically map anomalies on the road, namely speed bumps in this study, using an off-the-shelf camera (GoPro) and Machine Learning (ML) algorithms. We acquired data over a series of differently shaped speed bumps and applied three classification techniques: Naive Bayes, Multi-Layer Perceptron, and Random Forest (RF). With over 96% of classification accuracy, then RF was able to identify speed bumps on a GoPro dataset automatically. The results show a potential of the proposed methodology to be developed in surveying vehicles to produce highly-detailed maps of vertical road anomalies with a fast and accurate update rate. (AU)

• Processo FAPESP: 17/17003-3 - Desenvolvimento e avaliação de um sistema terrestre de mapeamento móvel de baixo custo para aplicações em transportes
• Beneficiário: Henrique Cândido de Oliveira
• Modalidade de apoio: Auxílio à Pesquisa - Regular