Recent advances in artificial intelligence, control and sensing technologies have facilitated the development of autonomous Unmanned Aerial Vehicles (UAVs). Detecting humans from video input captured on-the-fly from UAVs is a critical task for ensuring flight safety, mostly handled with lightweight Deep Neural Networks (DNNs). However the detection of individual people in the case of dense crowds and/or distribution shifts (i.e., significant visual differences between the training and the test sets) is still very challenging. This paper presents AUTH-Persons, a new, annotated, publicly available video dataset, that consists of both real and synthetic footage, suitable for training and evaluating aerial-view person detection algorithms. The synthetic data were collected from 8 visually distinct photorealistic outdoor environments and they mostly contain scenes with crowded areas, where heavy occlusions and high person densities pose challenges to common detectors. This dataset is employed to evaluate the generalization performance of various state-of-the-art detection frameworks, by testing them on environments that are visually distinct from those they have been trained on. Finally, given that Non-Maximum Suppression (NMS) methods at the end of person detection pipelines typically suffer in crowded scenes, the performance of various NMS algorithms is also compared in AUTH-Persons. 

Auth-Persons: A Dataset for Detecting Humans in Crowds from Aerial Views

For a majority of remote sensing applications of unmanned aerial vehicles (UAVs), the data need to be downloaded to ground devices for processing, but this procedure cannot satisfy the demands of real-time target detection. Our objective in this study is to develop a real-time system based on an embedded technology for image acquisition, target detection, the transmission and display of the results, and user interaction while providing support for the interactions between multiple UAVs and users. This work is divided into three parts: (1) We design the technical procedure and the framework for the implementation of a real-time target detection system according to application requirements. (2) We develop an efficient and reliable data transmission module to realize real-time cross-platform communication between airborne embedded devices and ground-side servers. (3) We optimize the YOLOv4 algorithm by using the K-Means algorithm and TensorRT inference to improve the accuracy and speed of the NVIDIA Jetson TX2. In experiments involving static detection, it had an overall confidence of 89.6% and a rate of missed detection of 3.8%; in experiments involving dynamic detection, it had an overall confidence and a rate of missed detection of 88.2% and 4.6%, respectively. 

Using deep learning in an embedded system for real-time target detection based on images from an unmanned aerial vehicle: vehicle detection as a case study

The use of camera-equipped Unmanned Aerial Vehicles (UAVs, or "drones") for professional media production is already an exciting commercial reality. Currently available consumer UAVs for cinematography applications are equipped with high-end cameras and a degree of cognitive autonomy relying on artificial intelligence (AI). Current research promises to further exploit the potential of autonomous functionalities in the immediate future, resulting in portable flying robotic cameras with advanced intelligence concerning autonomous landing, subject detection/tracking, cinematic shot execution, 3D localization and environmental mapping, as well as autonomous obstacle avoidance combined with on-line motion re-planning. Disciplines driving this progress are computer vision, machine/deep learning and aerial robotics. This Tutorial emphasizes the definition and formalization of UAV cinematography aesthetic components, as well as the use of robotic planning/control methods for autonomously capturing them on footage, without the need for manual tele-operation. Additionally, it focuses on state-of-the-art Imitation Learning and Deep Reinforcement Learning approaches for automated UAV/camera control, path planning and cinematography planning, in the general context of "flying & filming".

Autonomous UAV Cinematography

Secure Communications for Autonomous Multiple-UAV Media Production

Recent advances in artificial intelligence, control and sensing technologies have facilitated the development of autonomous Unmanned Aerial Vehicles (UAVs). Detecting humans from video input captured on-the-fly from UAVs is a critical task for ensuring flight safety, mostly handled with lightweight Deep Neural Networks (DNNs). However the detection of individual people in the case of dense crowds and/or distribution shifts (i.e., significant visual differences between the training and the test sets) is still very challenging. This paper presents AUTH-Persons, a new, annotated, publicly available video dataset, that consists of both real and synthetic footage, suitable for training and evaluating aerial-view person detection algorithms. The synthetic data were collected from 8 visually distinct photorealistic outdoor environments and they mostly contain scenes with crowded areas, where heavy occlusions and high person densities pose challenges to common detectors. This dataset is employed to evaluate the generalization performance of various state-of-the-art detection frameworks, by testing them on environments that are visually distinct from those they have been trained on. Finally, given that Non-Maximum Suppression (NMS) methods at the end of person detection pipelines typically suffer in crowded scenes, the performance of various NMS algorithms is also compared in AUTH-Persons.

Cinematography with Unmanned Aerial Vehicles (UAVs) is an emerging technology promising to revolutionize media production. On the one hand, manually controlled drones already provide advantages, such as flexible shot setup, opportunities for novel shot types and access to difficult-to-reach spaces and/or viewpoints. Moreover, little additional ground infrastructure is required. On the other hand, enhanced UAV cognitive autonomy would allow both easier cinematography planning (from the Director’s perspective) and safer execution of that plan during actual filming; while integrating multiple UAVs can additionally augment the cinematic potential. In this paper, a novel multiple-UAV software/hardware architecture for media production in outdoor settings is proposed. The architecture encompasses mission planning and control under safety constraints, enhanced cognitive autonomy through visual analysis, human-computer interfaces and communication infrastructure for platform scalability with Quality-of-Service provisions. Finally, the architecture is demonstrated via a relevant subjective study on the adequacy of UAV and camera parameters for different cinematography shot types, as well as with field experiments where multiple UAVs film outdoor sports events. 

https://zenodo.org/record/6905667/files/Mademlis_MTAP_AMultipleUAVArchitectureForMediaProduction.pdf

A multiple-UAV architecture for autonomous media production

This article presents the QuantSaT-PT project, an effort to create the first Portuguese nanosatellite for space to ground quantum communication. Focused on the Attitude Determination and Control System, it describes the different elements that allow for the attainment of diverse accuracy levels required for separate mission stages. Given the harsh pointing precision necessary for establishing a quantum downlink, the implementation of this module presents a major challenge in the Cubesat field. Furthermore, the introduced architecture aims to reduce system cost by replacing the state-of-the-art star tracker with ground beacon detection.

https://upcommons.upc.edu/bitstream/2117/370611/1/SSEA_2022_322.pdf

QuantSat-PT: an attitude determination and control system architecture for QKD

—This paper describes and evaluates a surveillance system based on Wireless Sensor Networks (WSNs) and Autonomous Vehicles (AVs). Firstly, the main wireless communi- cation technologies are surveyed, resulting in the choice of the Long Range (LoRa) technology to support the communication of the sensor nodes. In order to better deal with the characteristics of the LoRa communication, a protocol is designed and tested in realistic experiments in both rural and urban settings, which allows researchers to have a comparison between manufacturer values and realistic ones. Given the intended objective of having the surveillance system applied to remote areas to detect malicious people entering private property or forest fires, autonomous vehicles are used to further enhance the detection capabilities. The overall system is implemented in ROS packages and documented for future use. In experiments at the Institute for Systems and Robotics (ISR) flying arena, the system achieved a good average tracking Root-Mean-Square- Error (RMSE) of 0.0381 m and inspected all events that crossed the motion detection sensors with a triggering delay of 133 ms.

Rita Cunha

Papers

A multiple-UAV architecture for autonomous media production

QuantSat-PT: an attitude determination and control system architecture for QKD

Development and Experimental Validation of a LoRa Wireless Sensor Network for Wildfire Surveillance