Resumo:
The excessive presence of potholes on the paved roads in the state of São Paulo results in a
series of problems, including traffic accidents, financial impacts, and even environmental
damage. There are various solutions addressing this issue, such as visual processing,
distance sensors (such as laser or ultrasonic), or response analysis using vibration. This
article seeks to answer the following research question: “how to develop a low-cost
embedded system based on machine learning using accelerometer and GPS capable of
identifying irregularities (potholes) in road pavements?”. To achieve this, a systematic
literature review is conducted, with the main result being a process based on the use of
accelerometers to collect vibration and the application of artificial intelligence to identify
and classify potholes on paved roads, indicating the feasibility of the process in terms of
installation practicality, cost, and comparative results found in the literature.
Keywords: Accelerometer, Pothole, Irregularity, SVM (Support Vector Machine), Edge
Computing, ThingsBoard, Internet of Things, Automatic Pothole Detection.
Referência:
GONÇALVES, Ícaro; GAVA, Vagner Luiz; CAVALCANTE, Douglas Bellomo. Identificação de buracos de vias pavimentadas utilizando acelerômetros: uma revisão sistemática. In: INTERNATIONAL CONFERENCE ON INFORMATION SYSTEMS AND TECHONLOGY MANAGEMENT VIRTUAL, 20., 2024, São Paulo. Proceedings… 31 p.
Acesso ao site do Evento para recuperar o trabalho em PDF:
https://www.tecsi.org/contecsi/index.php/contecsi/20thCONTECSI/paper/view/7295/4823
