Unmanned Aerial Vehicles (UAVs) are particularly interesting for covering large areas or observing regions from a privileged angle of view. However, many applications still require direct human control. The addition of visual feedback can enable these vehicles to perform tasks more autonomously. In this context, this work proposes an autonomous flight module, based on computer vision, with embedded processing, to follow a moving target in external environments. Interesting results are obtained through real tests done with a quadcopter that uses Pixhawk for low-level control and a Raspberry Pi for high-level control.
Draft measurement is a fundamental task in the maritime transport of bulk cargo, being necessary to ensure the distribution of cargo and the stability of the ship, in addition to transferring the correct amount of cargo. Therefore, the method presented on this paper was proposed with the intention of helping manual operators as well as serving as an important tool for the automation of the function. The proposal of the paper is to offer a solution capable of detecting the sets of ship's draft marks, through the training of a Haar Cascade algorithm and digital image processing, and to perform the positional control of a camera, in order to keep it centralised in the image the draft marks. The application works through a client-server architecture, in which the server is on land and the client, equipped with a camera and a microprocessor, can be installed on autonomous land or maritime vehicles, or even in fixed structures installed in strategic locations. Resumo: A medição de calados é uma tarefa fundamental no transporte marítimo de cargas a granel, sendo necessária para garantir a distribuição das cargas e a estabilidade do navio, além da transferência da quantidade correta de carga. Desta forma, o presente trabalho foi proposto com o intuito de auxiliar os trabalhadores da área bem como servir como uma importante ferramenta para automatização da função. A proposta do trabalho é oferecer uma solução capaz de detectar os conjuntos de marcas de calado de navio, através do treinamento de um algoritmo Haar Cascade e processamento digital de imagens, e realizar o controle do posicionamento de uma câmera, de modo a manter centralizada na imagem as marcas de calado. A aplicação funciona através de uma arquitetura cliente-servidor, na qual o servidor fica em terra e o cliente, equipado com uma câmera e um microprocessador, pode ser instalado em veículos autônomos terrestres ou marítimos, ou ainda em estruturas fixas instaladas em locais estratégicos.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.