scholarly journals Visual Object Detection For Autonomous UAV Cinematography

2020 ◽  
Vol 1 ◽  
pp. 6
Author(s):  
Fotini Patrona ◽  
Paraskevi Nousi ◽  
Ioannis Mademlis ◽  
Anastasios Tefas ◽  
Ioannis Pitas
Keyword(s):  
Unmanned Aerial Vehicles ◽  
State Of The Art ◽  
Limited Resource ◽  
High Accuracy ◽  
Limited Resources ◽  
Visual Object ◽  
Trade Off ◽  
The Past ◽  
Art Object ◽  
Aerial Vehicles

The popularization of commercial, battery-powered, camera-equipped, Vertical Take-off and Landing (VTOL) Unmanned Aerial Vehicles (UAVs) during the past decade, has significantly affected aerial video capturing operations in varying domains. UAVs are affordable, agile and flexible, having the ability to access otherwise inaccessible spots. However, their limited resources burden computation cinematography techniques on operating with high accuracy and real-time speed on such devices. State-of-the-art object detectors and feature extractors are, thus, studied in this work, aiming to find a trade-off between performance and speed that will allow UAV exploitation for intelligent cinematography purposes. Experimental evaluation on three newly introduced datasets of rowing boats, cyclists and parkour athletes is performed and evidence is provided that even limited-resource autonomous UAVs can indeed be used for cinematography applications.

Development on Fault Detection and Diagnosis of Unmanned Aerial Vehicles

2014 ◽  
Vol 494-495 ◽  
pp. 861-864
Author(s):  
Yi Peng Zhang ◽  
Ke Cai Cao
Keyword(s):  
Fault Detection ◽  
Unmanned Aerial Vehicles ◽  
Unmanned Aerial Vehicle ◽  
State Of The Art ◽  
Fault Detection And Diagnosis ◽  
The Past ◽  
Aerial Vehicles ◽  
Aerial Vehicle ◽  
Detection And Diagnosis

The reliability of unmanned aerial vehicles (UAVs) has caught the attention of many researchers in the past decades. This paper presents a review on the development and important issues of state-of-the-art researches in the field of fault detection and diagnosis (FDD) techniques. Faults on an individual unmanned aerial vehicle or a group of unmanned aerial vehicles are considered for providing an overall picture of fault detection and diagnosis approaches.

Trend Analysis of Unmanned Aerial Vehicles (UAVs) Research Published in the HFES Proceedings

2018 ◽  
Vol 62 (1) ◽  
pp. 1067-1071
Author(s):  
Salim A. Mouloua ◽  
James Ferraro ◽  
Mustapha Mouloua ◽  
P.A. Hancock
Keyword(s):  
Human Factors ◽  
Unmanned Aerial Vehicles ◽  
Unmanned Aerial Vehicle ◽  
Supervisory Control ◽  
Research Trends ◽  
Government Agencies ◽  
The Past ◽  
Human Factors And Ergonomics ◽  
Aerial Vehicles ◽  
Aerial Vehicle

The present study was designed to examine the research trends in the literature focusing on Human Factors issues relevant to Unmanned Aerial Vehicle (UAV) systems. As these UAV technologies continue to proliferate with increasing autonomy and supervisory control requirements, it is crucial to evaluate the current and emerging research trends across the generations. This paper reviews the research trends of 228 papers matching our search criteria. The search retained only relevant and complete papers published over the past thirty years (1988-2017) in the Proceedings of the Human Factors and Ergonomics Society. Results were tabulated, graphed, and discussed based on research categories, topic areas, authors’ affiliation, and sources of funding. Results showed a substantial increase in the number of articles in the last two decades, with most papers driven by academic institutions and military and government agencies.

scholarly journals State of the Art and Problems of Defeat of Low, Slow and Small Unmanned Aerial Vehicles

2018 ◽  
Vol 13 (2) ◽  
Author(s):  
Dudush ◽  
Tyutyunnik ◽  
Trofymov ◽  
Bortnovs’kiy ◽  
Bondarenko
Keyword(s):  
Unmanned Aerial Vehicles ◽  
State Of The Art ◽  
Aerial Vehicles

scholarly journals COMPARISON OF UAV LIDAR ODOMETRY OF ROTATING AND FIXED VELODYNE PLATFORMS

2020 ◽  
Vol XLIII-B1-2020 ◽  
pp. 527-534
Author(s):  
M. L. Tazir ◽  
N. Seube
Keyword(s):  
Unmanned Aerial Vehicles ◽  
Three Dimensional ◽  
High Accuracy ◽  
Field Of View ◽  
Direct Access ◽  
Refresh Rate ◽  
Additional Degree ◽  
Aerial Vehicles ◽  
3D Information ◽  
Axis Passing

Abstract. Three-dimensional LiDAR rangefinders are increasingly integrated into unmanned aerial vehicles (UAV), due to their direct access to 3D information, their high accuracy and high refresh rate, and their tendency to be lightweight and cheaper. However, all commercial LiDARs can only offer a limited vertical resolution. To cope with this problem, a solution can be to rotate the LiDAR on an axis passing through its center, adding an additional degree of freedom and allowing more overlap, which significantly enlarges the sensor scope and allows having a complete spherical field of view (FOV). In this paper, we explore this solution in detail for drone’s context, while making comparisons between the rotating and fixed configurations for a Multi-Layers LiDAR (MLL) of type Velodyne Puck Lite. We investigate its impact on the LiDAR Odometry (LO) process by comparing the resulting trajectories with the data of the two configurations, as well as, qualitative comparisons, of the resulting maps.

scholarly journals Energy-aware Coverage Path Planning for Unmanned Aerial Vehicles

2020 ◽  
Author(s):  
Tauã Cabreira ◽  
Lisane Brisolara ◽  
Paulo Ferreira Jr.
Keyword(s):  
Energy Consumption ◽  
Path Planning ◽  
Unmanned Aerial Vehicles ◽  
Partial Information ◽  
State Of The Art ◽  
Energy Aware ◽  
Coverage Path Planning ◽  
Aerial Vehicles ◽  
Novel Approaches ◽  
Grid Based

Coverage Path Planning (CPP) problem is a motion planning subtopic in robotics, where it is necessary to build a path for a robot to explore every location in a given scenario. Unmanned Aerial Vehicles (UAV) have been employed in several applications related to the CPP problem. However, one of the significant limitations of UAVs is endurance, especially in multi-rotors. Minimizing energy consumption is pivotal to prolong and guarantee coverage. Thus, this work proposes energy-aware coverage path planning solutions for regular and irregular-shaped areas containing full and partial information. We consider aspects such as distance, time, turning maneuvers, and optimal speed in the UAV’s energy consumption. We propose an energy-aware spiral algorithm called E-Spiral to perform missions over regular-shaped areas. Next, we explore an energy-aware grid-based solution called EG-CPP for mapping missions over irregular-shaped areas containing no-fly zones. Finally, we present an energy-aware pheromone-based solution for patrolling missions called NC-Drone. The three novel approaches successfully address different coverage path planning scenarios, advancing the state-of-the-art in this area.

scholarly journals I Am Guessing You Can't Recognize This: Generating Adversarial Images for Object Detection Using Spatial Commonsense (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13789-13790 ◽  
Author(s):  
Anurag Garg ◽  
Niket Tandon ◽  
Aparna S. Varde
Keyword(s):  
Object Detection ◽  
Domain Adaptation ◽  
State Of The Art ◽  
High Accuracy ◽  
Target Domain ◽  
Commonsense Knowledge ◽  
Detection Model ◽  
Art Object ◽  
Smart Mobility ◽  
Research Questions

Can we automatically predict failures of an object detection model on images from a target domain? We characterize errors of a state-of-the-art object detection model on the currently popular smart mobility domain, and find that a large number of errors can be identified using spatial commonsense. We propose øurmodel , a system that automatically identifies a large number of such errors based on commonsense knowledge. Our system does not require any new annotations and can still find object detection errors with high accuracy (more than 80% when measured by humans). This work lays the foundation to answer exciting research questions on domain adaptation including the ability to automatically create adversarial datasets for target domain.

Sign in / Sign up

Export Citation Format

Share Document