Figure 8 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
The increased demand for Unmanned Aerial Vehicles (UAV) has also led to higher demand for realistic and efficient UAV testing environments. The current use of simulated environments has been shown to be a relatively inexpensive, safe, and repeatable way to evaluate UAVs before real-world use. However, the use of generic environments and manually-cr...
Context in source publication
Context 1
... capabilities as a single Convolutional Neural Network (CNN) allow it to divide an image into regions and predict bounding boxes with associated probabilities for each region. YOLO v4 incorporates a ResNet backbone combined with a feature pyramid net to handle object detection (see Figure 8). ...
Similar publications
To address the ever-growing connectivity demands of wireless communications, the adoption of ingenious solutions, such as Unmanned Aerial Vehicles (UAVs) as mobile Base Stations (BSs), is imperative. In general, the location of a UAV Base Station (UAV-BS) is determined by optimization algorithms, which have high computationally complexities and pla...
Citations
... Terragen, 22 a scenery generator program, is another environment employed in the literature [180], [181]. Recently, the concept of an autonomous environment generator for UAVbased simulation based on machine learning algorithms was introduced in [182]. Based on satellite images, this approach introduced the concept of procedurally generating, scaling, and placing 3-D models to create a realistic environment. ...
... Based on satellite images, this approach introduced the concept of procedurally generating, scaling, and placing 3-D models to create a realistic environment. The interested reader can refer to papers [182] and [183] for more details on simulation environments. ...
Unmanned aerial vehicles (UAVs) are widely used platforms to carry data capturing sensors for various applications. The reason for this success can be found in many aspects: the high maneuverability of the UAVs, the capability of performing autonomous data acquisition, flying at different heights, and the possibility to reach almost any vantage point. The selection of appropriate viewpoints and planning the optimum trajectories of UAVs is an emerging topic that aims at increasing the automation, efficiency and reliability of the data capturing process to achieve a dataset with desired quality. On the other hand, 3D reconstruction using the data captured by UAVs is also attracting attention in research and industry. This review paper investigates a wide range of model-free and model-based algorithms for viewpoints and path planning for 3D reconstruction of large-scale objects. It presents a bibliography of more than 200 references to cover different aspects of the topic. The analyzed approaches are limited to those that employ a single-UAV as a data capturing platform for outdoor 3D reconstruction purposes. In addition to discussing the evaluation strategies, this paper also highlights the innovations and limitations of the investigated approaches. It concludes with a critical analysis of the existing challenges and future research perspectives.
... These type of vehicles can be useful in applications ranging from wild-fire detection [1], [2], through search and rescue [3], [4], telecommunications [5] and agriculture [6]- [8]. Moreover, in future Smart Cities these vehicles can provide efficient delivery services (goods, medications, and transplantation organs) [9], deployable mobile base stations allowing broadband hotspot connectivity (particularly suitable for occasional events and improving network coverage) [10], infrastructure inspection (buildings, bridges, tunnels, and construction sites) [11], surveillance (traffic, crowds) [12], first responder services (including earthquakes, gas leakage, and explosions) [13]- [17]. ...
... Even though there are high-resolution commercial satellites available, their images are expensive to acquire such as PlanetScope, Maxar, and Worldview. In recent years, UAVs have become more and more popular in many industries, such as 3D real-world modeling [6], communications [7], transport [8], and remote sensing. UAV remote sensing applications have attracted the interest of scientists because they are not affected by the atmosphere. ...
... The recall parameter quantifies predictions for all the positive classes, which can be achieved using Equation (5). The F-score considers the P and R parameters, thus indicating model accuracy for the given datasets, as shown in Equation (6). Finally, overall accuracy is the sum of the true positives plus true negatives divided by the total number of individuals tested, as shown in Equation (7). ...
Pedicularis has adverse effects on vegetation growth and ecological functions, causing serious harm to animal husbandry. In this paper, an automated detection method is proposed to extract Pedicularis and reveal the spatial distribution. Based on unmanned aerial vehicle (UAV) images, this paper adopts logistic regression, support vector machine (SVM), and random forest classifiers for multi-class classification. One-class SVM (OCSVM), isolation forest, and positive and unlabeled learning (PUL) algorithms are used for one-class classification. The results are as follows: (1) The accuracy of multi-class classifiers is better than that of one-class classifiers, but it requires all classes that occur in the image to be exhaustively assigned labels. Among the one-class classifiers that only need to label positive or positive and labeled data, the PUL has the highest F score of 0.9878. (2) PUL performs the most robustly to change features in one-class classifiers. All one-class classifiers prove that the green band is essential for extracting Pedicularis. (3) The parameters of the PUL are easy to tune, and the training time is easy to control. Therefore, PUL is a promising one-class classification method for Pedicularis extraction, which can accurately identify the distribution range of Pedicularis to promote grassland administration.
... After the Matlab tests were validated, the source code was translated to Python and the Gazebo 3D robotics simulator was used to test the algorithm in a more realistic environment provided by this simulator. This simulator was chosen due to the following facts [22][23][24] To simulate an indoor environment, a warehouse was created in Gazebo with a length of 200 m, width of 100 m and height of 25 m, as shown in Figure 3. The UAV is being navigated using the proposed algorithm or other considered algorithms for comparison. ...
This work addresses one of the major challenges in the field of Unmanned Aerial Vehicles (UAVs), which is related to UAV navigation in 3‐dimensional indoor environments. This topic is highly relevant due to limited‐to‐no availability of satellite signals that are usually the main sources used to govern the movement of UAVs in outdoor environments. Instead, the algorithm proposed in this work resorts to terrestrial radio measurements between the UAV and a set of stationary reference points to accomplish accurate navigation. The radio measurements are first exploited to give origin to range information that is used to calculate intersection points between a suitable subset of spheres, which serve as a coarse estimate of the UAV's position. From the intersection points, both azimuth and elevation angle estimates are obtained at each reference point. Finally, by taking advantage of estimated bearing information and applying simple geometry, the localisation problem is formulated according to the Weighted Least Squares (WLS) criterion and solved in closed form. The authors’ simulation results show good performance of the proposed approach, matching or even outperforming the state‐of‐the‐art methods in terms of localisation accuracy with significantly lower computational complexity.
... For simulating such applications it is recommended to use a flight simulator providing realistic environment renderings and a high-performance physics engine likes Gazebo, FlightGear, X-Plane, and MORSE. Accordingly, [60], proposed a new testbed utilizing machine learning algorithms to autonomously generate 3D models to provide a realistic environment for UAVs. [61], used Gazebo to test their vision and inertial integrated navigation method for UAV. ...
During the last decade, Unmanned Aerial Vehicles (UAVs) gained wide attention and are integrated into diverse systems and deployed into many contexts. The need to assess the UAVs’ performances, impacts of applications, routing protocols, mobility as well as other features in a network is necessary. However, conducting real experiments within UAV-based systems and particularly with multi-UAV-based systems can be extremely costly and complex. To fill this gap simulators, emulators, and frameworks are used to evaluate the performance and viability of UAV-based systems with lower cost and in a short period. Accordingly, researchers and software engineers developed several simulators and co-simulators dedicated to the performance evaluations of UAV-based systems. In this regard, this investigation highlights and identifies the most suitable simulators, co-simulators, emulators, and frameworks for UAV flights and management. Both the tools dedicated to mono-UAV-based systems and the tools dedicated to multi-UAV-based systems are pinpointed. In this paper, the goals, the requirements, the strengths, and the limitations of each studied tool are detailed. Besides that, a UAV simulators catalog is provided. It includes guidelines that will be useful for researchers and help them to identify and to select the adequate tools for UAVs performance analysis that meet their needs.
... Terragen 8, a scenery generator program, is another environment employed in the literature Martin et al., 2015). Recently, the concept of an autonomous environment generator for UAV-based simulation based on machine learning algorithms is introduced in (Nakama et al., 2021). Based on satellite images, this approach introduced the concept of procedurally generating, scaling, and placing 3D models to create a realistic environment. ...
... Based on satellite images, this approach introduced the concept of procedurally generating, scaling, and placing 3D models to create a realistic environment. The interested reader can refer to (Hentati et al., 2018;Nakama et al., 2021) for more details on simulation environments. Discussion and future trends Although much work and progress are observable in the field of viewpoint and path planning, existing algorithms are far from the last word on this topic, and there is plenty of exciting work left to do. ...
Unmanned aerial vehicles (UAVs) are widely used platforms to carry data capturing sensors for various applications. The reason for this success can be found in many aspects: the high maneuverability of the UAVs, the capability of performing autonomous data acquisition, flying at different heights, and the possibility to reach almost any vantage point. The selection of appropriate viewpoints and planning the optimum trajectories of UAVs is an emerging topic that aims at increasing the automation, efficiency and reliability of the data capturing process to achieve a dataset with desired quality. On the other hand, 3D reconstruction using the data captured by UAVs is also attracting attention in research and industry. This review paper investigates a wide range of model-free and model-based algorithms for viewpoint and path planning for 3D reconstruction of large-scale objects. The analyzed approaches are limited to those that employ a single-UAV as a data capturing platform for outdoor 3D reconstruction purposes. In addition to discussing the evaluation strategies, this paper also highlights the innovations and limitations of the investigated approaches. It concludes with a critical analysis of the existing challenges and future research perspectives.
... The introduction of virtual reality and augmented reality technologies has increased the demand for three-dimensional (3D) models [1][2][3][4][5][6][7][8]. Among the various 3D modeling techniques, unmanned aerial vehicle (UAV) photogrammetry has the advantages of time and cost efficiency [1,[4][5][6][7][8][9][10][11][12][13]. ...
... The introduction of virtual reality and augmented reality technologies has increased the demand for three-dimensional (3D) models [1][2][3][4][5][6][7][8]. Among the various 3D modeling techniques, unmanned aerial vehicle (UAV) photogrammetry has the advantages of time and cost efficiency [1,[4][5][6][7][8][9][10][11][12][13]. ...
... The 3D modeling procedure using UAVs can be divided into the following three main parts: Flight planning, flight and image acquisition, and image processing. Several studies on each process have been conducted to obtain a low-cost, high-precision 3D model [1,4,14,15]. Studies on optimal path planning to obtain a high-quality 3D model have been conducted in the flight planning section [16][17][18][19][20][21][22]. ...
In unmanned aerial vehicle (UAV) photogrammetry, the qualities of three-dimensional (3D) models, including ground sample distance (GSD) and shaded areas, are strongly affected by flight planning. However, during flight planning, the quality of the output cannot be estimated, as it depends on the experience of the operator. Therefore, to reduce the time and cost incurred by repetitive work required to obtain satisfactory quality, a simulator, which can automatically generate a route, acquire images through simulation, and analyze the shaded areas without real flight, has been required. While some simulators have been developed, there are some limitations. Furthermore, evaluating the performance of the simulator is difficult owing to the lack of a validation method. Therefore, to overcome the limitations, target functions, which can plan flights and can detect shaded areas, were set, developed, and validated in this study. As a result, a simulator successfully planned a flight and detected shaded areas. In this way, the simulator was validated to determine the applicability of its performance. Furthermore, the outputs of this study can be applied to not only UAV photogrammetry simulators but also other 3D modeling simulators.
... The simulation environment was constructed under the open-source Gazebo 3D robotics simulator due to its compatibility and straightforward integration with ROS [84][85][86][87]. The UAV and landing base station models were added to the Gazebo simulator, as can be seen in Figure 18. ...
This work proposes a fully integrated ecosystem composed of three main components with a complex goal: to implement an autonomous system with a UAV requiring little to no maintenance and capable of flying autonomously. For this goal, was developed an autonomous UAV, an online platform capable of its management and a landing platform to enclose and charge the UAV after flights. Furthermore, a precision landing algorithm ensures no need for human intervention for long-term operations.
... In order to simulate the algorithms proposed in this article, the open-source Gazebo 3D robotics simulator was chosen due to three important factors[57]-[59]: ...
This work addresses the problem of unmanned aerial vehicle (UAV) navigation in indoor environments. Due to unavailability of satellite signals, the proposed algorithm takes advantage of terrestrial radio measurements between the UAV and a set of stationary reference points, from which it extracts range information, as well as odometry by means of inertial sensors, such as accelerometer. On the one hand, based on maximum a posteriori (MAP) criterion, the range information and accumulated knowledge throughout the UAV’s movement are employed to derive a generalized trust region sub-problem (GTRS), that is solved exactly via bisection procedure. On the other hand, by using the UAV’s transform in relation to the world, another position estimation is obtained by employing odometry. Finally, the two position estimates are combined through a Kalman filter (KF) to enhance the positioning accuracy and obtain the final UAV’s position estimation. The UAV is then navigated to a desired destination, by simply calculating the velocity components in the shortest path. Our results show that the proposed algorithm is robust to various model parameters for high precision (HP) UAV sensors, achieving reasonably good positioning accuracy. Besides, the results corroborate that the proposed algorithm is suitable for real-time applications, consuming (on average) only 21 ms to estimate the UAV position.
