The image processing community has witnessed remarkable advances in enhancing and restoring images. Nevertheless, restoring the visual quality of underwater images remains a great challenge. End-to-end frameworks might fail to enhance the visual quality of underwater images since in several scenarios it is not feasible to provide the ground truth of the scene radiance. In this work, we propose a CNN-based approach that does not require ground truth data since it uses a set of image quality metrics to guide the restoration learning process. The experiments showed that our method improved the visual quality of underwater images preserving their edges and also performed well considering the UCIQE metric.

The use of delivery services is an increasing trend worldwide, further enhanced by the COVID pandemic. In this context, drone delivery systems are of great interest as they may allow for faster and cheaper deliveries. This paper presented a navigation system that makes feasible the delivery of parcels with autonomous drones. The system generates a path between a start and a final point and controls the drone to follow this path based on its localization obtained through GPS, 9DoF IMU, and barometer. In the landing phase, information of poses estimated by a marker (ArUco) detection technique using a camera, ultrawideband (UWB) devices, and the drone’s software estimation are merged by utilizing an extended Kalman filter algorithm to improve the landing precision. A vector field-based method controls the drone to follow the desired path smoothly, reducing vibrations or harsh movements that could harm the transported parcel. Real experiments validate the delivery strategy and allow the evaluation of the performance of the adopted techniques. Preliminary results state the viability of our proposal for autonomous drone delivery.

Drones são cada vez mais usados em aplicações de logı́stica devido à sua rapidez e praticidade. Este artigo apresenta uma metodologia para a viabilização de entregas utilizando drones autônomos. Duas estratégias de planejamento de caminho são apresentadas e a localização do quadrirrotor é feita através do GPS, IMU e barômetro durante o voo. Na fase de pouso, a pose estimada por uma câmera junto a um marcador ArUco ou por dispositivos Ultrawide Band são fundidos ao GPS utilizando um Filtro de Kalman Estendido. O controle do robô é feito por uma técnica de Campos Vetoriais, de maneira que o drone convirja para a curva desejada. As estratégias de planejamento de caminho são validadas através de simulações e experimentos reais, e as diferentes técnicas de localização são comparadas. Os resultados preliminares mostram a viabilidade da utilização de drones para entregas de pacotes.

No abstract

The use of delivery services is an increasing trend worldwide, further enhanced by the COVID pandemic. In this context, drone delivery systems are of great interest as they may allow for faster and cheaper deliveries. This paper presents a navigation system that makes feasible the delivery of parcels with autonomous drones. The system generates a path between a start and a final point and controls the drone to follow this path based on its localization obtained through GPS, 9DoF IMU, and barometer. In the landing phase, information of poses estimated by a marker (ArUco) detection technique using a camera, ultra-wideband (UWB) devices, and the drone's software estimation are merged by utilizing an Extended Kalman Filter algorithm to improve the landing precision. A vector field-based method controls the drone to follow the desired path smoothly, reducing vibrations or harsh movements that could harm the transported parcel. Real experiments validate the delivery strategy and allow to evaluate the performance of the adopted techniques. Preliminary results state the viability of our proposal for autonomous drone delivery.