Browsing by Author "Miguel, Joaquim"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- The development of a prototype solution for collecting information on cycling and hiking trail usersPublication . Miguel, Joaquim; Mendonça, Pedro; Quelhas, Agnelo; Caldeira, J.M.L.P.; Soares, Vasco N.G.J.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 a endance 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.
- Using computer vision to collect information on cycling and hiking trails usersPublication . Miguel, Joaquim; Mendonça, Pedro; Quelhas, Agnelo; Caldeira, J.M.L.P.; Soares, V.N.G.J.Hiking and cycling have become popular activities for promoting well-being and physical activity. Portugal has been investing in hiking and cycling trail infrastructures to boost sustainable tourism. However, the lack of reliable data on the use of these trails means that the times of greatest affluence or the type of user who makes the most use of them are not recorded. These data are of the utmost importance to the managing bodies, with which they can adjust their actions to improve the management, maintenance, promotion, and use of the infrastructures for which they are responsible. The aim of this work is to present a review study on projects, techniques, and methods that can be used to identify and count the different types of users on these trails. The most promising computer vision techniques are identified and described: YOLOv3-Tiny, MobileNet-SSD V2, and FasterRCNN with ResNet-50. Their performance is evaluated and compared. The results observed can be very useful for proposing future prototypes. The challenges, future directions, and research opportunities are also discussed.
- Utilização de técnicas de visão computacional para identificar e quantificar diferentes tipos de utilizadores de percursos cicláveis e percursos pedestresPublication . Miguel, Joaquim; Mendonça, Pedro; Caldeira, J.M.L.P.; Soares, Vasco N.G.J.Em Portugal o número de percursos cicláveis e percursos pedestres homologados tem vindo a crescer ao longo dos anos, contribuindo para valorizar territórios ao atrair um número crescente de turistas nacionais e estrangeiros para a prática de desporto na natureza. Contudo, dado que se trata de espaços de livre acesso, habitualmente não existem dados fiáveis sobre a sua taxa de utilização. Tendo em conta que, na maioria dos casos, os promotores destas infraestruturas são municípios, importa aferir o valor efetivo que estas rotas aportam aos territórios em termos turísticos, através da sua taxa de utilização. Tal valor só se efetiva através de demonstrações de utilização, realizadas com recolha de dados fiáveis. Esta apresentação centra-se num estudo que visa validar, avaliar e comparar diferentes técnicas de visão computacional para identificar e quantificar diferentes tipos de utilizadores neste tipo de percursos. Apresenta os conceitos relacionados com a temática e as soluções apontadas na literatura, discute os pontos fortes e limitações das mesmas e identifica pontos em aberto. Após esta análise, apresenta uma avaliação de desempenho das técnicas mais promissoras para solução deste problema.