| Autor: |
Joaquim Miguel, Pedro Mendonça, Agnelo Quelhas, João M. L. P. Caldeira, Vasco N. G. J. Soares |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
Information, Vol 15, Iss 7, p 389 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2078-2489 |
| DOI: |
10.3390/info15070389 |
| Popis: |
Hiking and cycling have gained popularity as ways of promoting well-being and physical activity. This has not gone unnoticed by Portuguese authorities, who have invested in infrastructure to support these activities and to boost sustainable and nature-based tourism. However, the lack of reliable data on the use of these infrastructures prevents us from recording attendance rates and the most frequent types of users. This information is important for the authorities responsible for managing, maintaining, promoting and using these infrastructures. In this sense, this study builds on a previous study by the same authors which identified computer vision as a suitable technology to identify and count different types of users of cycling and hiking routes. The performance tests carried out led to the conclusion that the YOLOv3-Tiny convolutional neural network has great potential for solving this problem. Based on this result, this paper describes the proposal and implementation of a prototype demonstrator. It is based on a Raspberry Pi 4 platform with YOLOv3-Tiny, which is responsible for detecting and classifying user types. An application available on users’ smartphones implements the concept of opportunistic networks, allowing information to be collected over time, in scenarios where there is no end-to-end connectivity. This aggregated information can then be consulted on an online platform. The prototype was subjected to validation and functional tests and proved to be a viable low-cost solution. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
|
Nepřihlášeným uživatelům se plný text nezobrazuje |
K zobrazení výsledku je třeba se přihlásit.
|
