Drones

Dealing with the trade-off challenge between computation speed and path quality has been a high-priority research area in the robotic path planning field during the last few years. Obtaining a shorter optimized path requires additional processing since iterative algorithms are adopted to keep enhancing the final optimized path. Therefore, it is a challenging problem to obtain an optimized path in a real-time manner. However, this trade-off problem becomes more challenging when planning a path for an Unmanned Aerial Vehicle (UAV) system since they operate in 3D environments. A 3D map will naturally have more data to be processed compared to a 2D map and thus, processing becomes more expensive and time-consuming. This paper proposes a new 3D path planning technique named the Sobel Potential Field (SPF) technique to deal effectively with the swiftness-quality trade-off. The rationale of the proposed SPF technique is to minimize the processing of potential field methods. Instead of applying the potential field analysis on the whole 3D map which could be a very expensive operation, the proposed SPF technique will tend to focus on obstacle areas. This is done by adopting the Sobel edge detection technique to detect the 3D edges of obstacles. These edges will be the sources of the repulsive forces while the goal point will be emitting an attractive force. Next, a proposed objective function models the strength of the attractive and repulsive forces differently to have various influences on each point on the map. This objective function is then optimized using Particle Swarm Optimization (PSO) to find an obstacle-free path to the destination. Finally, the PSO-based path is optimized further by finding linear shortcuts in the path. Testbed experimental results have proven the effectiveness of the proposed SPF technique and showed superior performance over other meta-heuristic optimization techniques, as well as popular path planning techniques such as A* and PRM. Full article

In this paper, we consider the difference in the abstraction level of features extracted by different perceptual layers and use a weighted perceptual loss-based generative adversarial network to deblur the UAV images, which removes the blur and restores the texture details of the images well. The perceptual loss is used as an objective evaluation index for training process monitoring and model selection, which eliminates the need for extensive manual comparison of the deblurring effect and facilitates model selection. The UNet jump connection structure facilitates the transfer of features across layers in the network, reduces the learning difficulty of the generator, and improves the stability of adversarial training. Full article

Arbitrary-oriented vehicle detection via aerial imagery is essential in remote sensing and computer vision, with various applications in traffic management, disaster monitoring, smart cities, etc. In the last decade, we have seen notable progress in object detection in natural imagery; however, such development has been sluggish for airborne imagery, not only due to large-scale variations and various spins/appearances of instances but also due to the scarcity of the high-quality aerial datasets, which could reflect the complexities and challenges of real-world scenarios. To address this and to improve object detection research in remote sensing, we collected high-resolution images using different drone platforms spanning a large geographic area and introduced a multi-view dataset for vehicle detection in complex scenarios using aerial images (VSAI), featuring arbitrary-oriented views in aerial imagery, consisting of different types of complex real-world scenes. The imagery in our dataset was captured with a wide variety of camera angles, flight heights, times, weather conditions, and illuminations. VSAI contained 49,712 vehicle instances annotated with oriented bounding boxes and arbitrary quadrilateral bounding boxes (47,519 small vehicles and 2193 large vehicles); we also annotated the occlusion rate of the objects to further increase the generalization abilities of object detection networks. We conducted experiments to verify several state-of-the-art algorithms in vehicle detection on VSAI to form a baseline. As per our results, the VSAI dataset largely shows the complexity of the real world and poses significant challenges to existing object detection algorithms. The dataset is publicly available. Full article

The use of drones in various applications has now increased, and their popularity among the general public has increased. As a result, the possibility of their misuse and their unauthorized intrusion into important places such as airports and power plants are increasing, threatening public safety. For this reason, accurate and rapid recognition of their types is very important to prevent their misuse and the security problems caused by unauthorized access to them. Performing this operation in visible images is always associated with challenges, such as the small size of the drone, confusion with birds, the presence of hidden areas, and crowded backgrounds. In this paper, a novel and accurate technique with a change in the YOLOv4 network is presented to recognize four types of drones (multirotors, fixed-wing, helicopters, and VTOLs) and to distinguish them from birds using a set of 26,000 visible images. In this network, more precise and detailed semantic features were extracted by changing the number of convolutional layers. The performance of the basic YOLOv4 network was also evaluated on the same dataset, and the proposed model performed better than the basic network in solving the challenges. Compared to the basic YOLOv4 network, the proposed model provides better performance in solving challenges. Additionally, it can perform automated vision-based recognition with a loss of 0.58 in the training phase and 83% F1-score, 83% accuracy, 83% mean Average Precision (mAP), and 84% Intersection over Union (IoU) in the testing phase. These results represent a slight improvement of 4% in these evaluation criteria over the YOLOv4 basic model. Full article

Due to the nonlinear and asymmetric input constraints of the fixed-wing UAVs, it is a challenging task to design controllers for the fixed-wing UAV formation control. Distance-based formation control does not require global positions as well as the alignment of coordinates, which brings in great convenience for designing a distributed control law. Motivated by the facts mentioned above, in this paper, the problem of distance-based formation of fixed-wing UAVs with input constraints is studied. A low-gain formation controller, which is a generalized gradient controller of the potential function, is proposed. The desired formation can be achieved by the designed controller under the input constraints of the fixed-wing UAVs with proven stability. Finally, the effectiveness of the proposed method is verified by the numerical simulation and the semi-physical simulation. Full article

Traditional forest monitoring has been mainly performed with images or orthoimages from aircraft or satellites. In recent years, the availability of high-resolution 3D data has made it possible to obtain accurate information on canopy size, which has made the topic of canopy 3D growth monitoring timely. In this paper, forest growth pattern was studied based on a canopy point cloud (PC) reconstructed from UAV aerial photogrammetry at a daily interval for a year. Growth curves were acquired based on the canopy 3D area (3DA) calculated from a triangulated 3D mesh. Methods for canopy coverage area (CA), forest coverage rate, and leaf area index (LAI) were proposed and tested. Three spectral vegetation indices, excess green index (ExG), a combination of green indices (COM), and an excess red union excess green index (ExGUExR) were used for the segmentation of trees. The results showed that (1) vegetation areas extracted by ExGUExR were more complete than those extracted by the other two indices; (2) logistic fitting of 3DA and CA yielded S-shaped growth curves, all with correlation R² > 0.92; (3) 3DA curves represented the growth pattern more accurately than CA curves. Measurement errors and applicability are discussed. In summary, the UAV aerial photogrammetry method was successfully used for daily monitoring and annual growth trend description. Full article

A zoning approach that divides an area of interest into multiple sub-areas can be a systemic and strategic solution to safely deploy a fleet of unmanned aerial vehicles (UAVs) for package delivery services. Following the zoning approach, a UAV can be assigned to one of the sub-areas, taking sole ownership and responsibility of the sub-area. As a result, the need for collision avoidance between units and the complexity of relevant operational activities can be minimized, ensuring both safe and reliable execution of the tasks. Given that the zoning approach involves the demand-server allocation decision, the service quality to customers can also be improved by performing the zoning properly. To illuminate the benefits of the zoning approach to UAV operations from a systemic perspective, this study applies clustering techniques to derive zoning solutions under different scenarios and examines the performance of the solutions using a simulation model. The simulation results demonstrate that the zoning approach can improve the safety of UAV operations, as well as the quality of service to demands. Full article

In this paper, a design approach for simultaneous cooperative interception is presented for a scenario where the successful handover cannot be guaranteed by a single interceptor due to the target maneuver and movement information errors at the handover moment. Firstly, the concepts of the reachable interception area and predicted interception area are introduced, a performance index function is constructed, and the probability of a successful handover is described by considering the coverage of the predicted interception area. Taking the probability of successful handover as a constraint, the simultaneous cooperative interception design problem is formulated based on area coverage. Then, an area coverage optimization algorithm is presented to design the spatial distributions of the interceptors. In order to enhance the handover probability, a simultaneous cooperative interception design approach is proposed to obtain the number of interceptors and the corresponding spatial distributions. Finally, simulation experiments are carried out to validate the effectiveness of the proposed approach. Full article

There are many challenges that impact the current referral network for Tuberculosis (TB) sputum specimens in Mozambique. In some cases, health facilities are remote and the road infrastructure is poor and at times impassable, leading to delays in laboratory specimen transportation and long turn-around times for results. Drone transportation is a promising solution to reduce transportation time and improve access to laboratory diagnostics if the sample quality is not compromised during transport. This study evaluated the impact of drone transportation on the quality of TB sputum specimens with suspected Mycobacterium tuberculosis. 156 specimens were collected at five (5) health centers and sent to the Instituto Nacional de Saúde (INS) National TB Reference Laboratory. Specimens were then equally divided into two aliquots; one to be transported on land and the other by air using a drone. Control and study group specimens were processed using the NALC-NaOH method. Agreement between sample and control specimens was acceptable, indicating that drone transportation did not affect the quality of TB specimens. The authors recommend additional studies to validate drone transportation of TB specimens over a longer period of time to give further confidence in the adoption of drone delivery in Mozambique. Full article

Disasters are crisis circumstances that put human life in jeopardy. During disasters, public communication infrastructure is particularly damaged, obstructing Search And Rescue (SAR) efforts, and it takes significant time and effort to re-establish functioning communication infrastructure. SAR is a critical component of mitigating human and environmental risks in disasters and harsh environments. As a result, there is an urgent need to construct communication networks swiftly to help SAR efforts exchange emergency data. UAV technology has the potential to provide key solutions to mitigate such disaster situations. UAVs can be used to provide an adaptable and reliable emergency communication backbone and to resolve major issues in disasters for SAR operations. In this paper, we evaluate the network performance of UAV-assisted intelligent edge computing to expedite SAR missions and functionality, as this technology can be deployed within a short time and can help to rescue most people during a disaster. We have considered network parameters such as delay, throughput, and traffic sent and received, as well as path loss for the proposed network. It is also demonstrated that with the proposed parameter optimization, network performance improves significantly, eventually leading to far more efficient SAR missions in disasters and harsh environments. Full article

The cooperation of multiple unmanned aerial vehicles (Multi-UAV) can effectively solve the area coverage problem. However, developing an online multi-UAV coverage approach remains a challenge due to energy constraints and environmental dynamics. In this paper, we design a comprehensive framework for area coverage with multiple energy-limited UAVs in dynamic environments, which we call MCTA (Multi-UAV Coverage through Two-step Auction). Specifically, the online two-step auction mechanism is proposed to select the optimal action. Then, an obstacle avoidance mechanism is designed by defining several heuristic rules. After that, considering energy constraints, we develop the reverse auction mechanism to balance workload between multiple UAVs. Comprehensive experiments demonstrate that MCTA can achieve a high coverage rate while ensuring a low repeated coverage rate and average step deviation in most circumstances. Full article

Crop seedling detection is an important task in the seedling stage of crops in fine agriculture. In this paper, we propose a high-precision lightweight object detection network model based on a multi-activation layer and depth-separable convolution module to detect crop seedlings, aiming to improve the accuracy of traditional artificial intelligence methods. Due to the insufficient dataset, various image enhancement methods are used in this paper. The dataset in this paper was collected from Shahe Town, Laizhou City, Yantai City, Shandong Province, China. Experimental results on this dataset show that the proposed method can effectively improve the seedling detection accuracy, with the F1 score and mAP reaching 0.95 and 0.89, respectively, which are the best values among the compared models. In order to verify the generalization performance of the model, we also conducted a validation on the maize seedling dataset, and experimental results verified the generalization performance of the model. In order to apply the proposed method to real agricultural scenarios, we encapsulated the proposed model in a Jetson logic board and built a smart hardware that can quickly detect seedlings. Full article

Efficient and quick yield prediction is of great significance for ensuring world food security and crop breeding research. The rapid development of unmanned aerial vehicle (UAV) technology makes it more timely and accurate to monitor crops by remote sensing. The objective of this study was to explore the method of developing a novel yield index (YI) with wide adaptability for yield prediction by fusing vegetation indices (VIs), color indices (CIs), and texture indices (TIs) from UAV-based imagery. Six field experiments with 24 varieties of rice and 21 fertilization methods were carried out in three experimental stations in 2019 and 2020. The multispectral and RGB images of the rice canopy collected by the UAV platform were used to rebuild six new VIs and TIs. The performance of VI-based YI (MAPE = 13.98%) developed by quadratic nonlinear regression at the maturity stage was better than other stages, and outperformed that of CI-based (MAPE = 22.21%) and TI-based (MAPE = 18.60%). Then six VIs, six CIs, and six TIs were fused to build YI by multiple linear regression and random forest models. Compared with heading stage (R² = 0.78, MAPE = 9.72%) and all stage (R² = 0.59, MAPE = 22.21%), the best performance of YI was developed by random forest with fusing VIs + CIs + TIs at maturity stage (R² = 0.84, MAPE = 7.86%). Our findings suggest that the novel YI proposed in this study has great potential in crop yield monitoring. Full article

Low-altitude flight in mountainous terrains is a difficult flight task applied in both military and civilian fields. The helicopter has to maintain low altitude to realize search and rescue, reconnaissance, penetration, and strike operations. It contains complex environment perception, multilevel decision making, and multi-objective flight control; thus, flight is currently mainly conducted by human pilots. In this work, a control framework is implemented to realize autonomous flight for unmanned helicopter operations in an unknown mountainous environment. The identification of targets and threats is introduced using a deep neural network. A 3D vector field histogram method is adopted for local terrain avoidance based on airborne Lidar sensors. In particular, we propose an intuitive direct-viewing method to judge and change the visibilities of the helicopter. On this basis, a finite state machine is built for decision making of the autonomous flight. A highly realistic simulation environment is established to verify the proposed control framework. The simulation results demonstrate that the helicopter can autonomously complete flight missions including a fast approach, threat avoidance, cover concealment, and circuitous flight operations similar to human pilots. The proposed control framework provides an effective solution for complex flight tasks and expands the flight control technologies for high-level unmanned helicopter operations. Full article

In recent years, the increasing number of unmanned aerial vehicles (UAVs) in the low-altitude airspace have not only brought convenience to people’s work and life, but also great threats and challenges. In the process of UAV detection and tracking, there are common problems such as target deformation, target occlusion, and targets being submerged by complex background clutter. This paper proposes an anti-occlusion UAV tracking algorithm for low-altitude complex backgrounds by integrating an attention mechanism that mainly solves the problems of complex backgrounds and occlusion when tracking UAVs. First, extracted features are enhanced by using the SeNet attention mechanism. Second, the occlusion-sensing module is used to judge whether the target is occluded. If the target is not occluded, tracking continues. Otherwise, the LSTM trajectory prediction network is used to predict the UAV position of subsequent frames by using the UAV flight trajectory before occlusion. This study was verified on the OTB-100, GOT-10k and integrated UAV datasets. The accuracy and success rate of integrated UAV datasets were 79% and 50.5% respectively, which were 10.6% and 4.9% higher than those of the SiamCAM algorithm. Experimental results show that the algorithm could robustly track a small UAV in a low-altitude complex background. Full article

The high demand for distilled agave products reduces wild populations. The use of geospatial technologies such as unmanned aerial vehicles (UAVs) offer enormous benefits in spatial and temporal resolution and lower costs than traditional direct field observation techniques for natural resource monitoring. The objective was to estimate the green biomass (Wt) of Agave durangensis Gentry using high-resolution images obtained by a UAV in Nombre de Dios, Durango. Random sampling was performed in the agave area. A Pearson correlation analysis was performed, followed by a regression analysis. The results showed that NDVI was the most correlated (r = 0.65). The regression analysis showed that the model obtained explains 59% (RMSE = 32.06 kg) of the total variability in the estimation of green biomass (Wt) of agave using images derived from the UAV. The best estimate was achieved with B1, B2, NDVI, GNDVI, EVI2, and SAVI as predictor variables. High-resolution images were shown to be a tool for estimating Wt of Agave durangensis Gentry. Full article

Recently, unmanned aerial vehicles (UAVs), also known as drones, have come in a great diversity of several applications such as military, construction, image and video mapping, medical, search and rescue, parcel delivery, hidden area exploration, oil rigs and power line monitoring, precision farming, wireless communication and aerial surveillance. The drone industry has been getting significant attention as a model of manufacturing, service and delivery convergence, introducing synergy with the coexistence of different emerging domains. UAVs offer implicit peculiarities such as increased airborne time and payload capabilities, swift mobility, and access to remote and disaster areas. Despite these potential features, including extensive variety of usage, high maneuverability, and cost-efficiency, drones are still limited in terms of battery endurance, flight autonomy and constrained flight time to perform persistent missions. Other critical concerns are battery endurance and the weight of drones, which must be kept low. Intuitively it is not suggested to load them with heavy batteries. This study highlights the importance of drones, goals and functionality problems. In this review, a comprehensive study on UAVs, swarms, types, classification, charging, and standardization is presented. In particular, UAV applications, challenges, and security issues are explored in the light of recent research studies and development. Finally, this review identifies the research gap and presents future research directions regarding UAVs. Full article

A hybrid model-based and data-driven framework is proposed in this paper for autonomous coastline surveillance using an unmanned aerial vehicle. The proposed approach comprises three individual neural network-assisted modules that work together to estimate the state of the target (i.e., shoreline) to contribute to its identification and tracking. The shoreline is first detected through image segmentation using a Convolutional Neural Network. The part of the segmented image that includes the detected shoreline is then fed into a CNN real-time optical flow estimator. The position of pixels belonging to the detected shoreline, as well as the initial approximation of the shoreline motion, are incorporated into a neural network-aided Extended Kalman Filter that learns from data and can provide on-line motion estimation of the shoreline (i.e., position and velocity in the presence of waves) using the system and measurement models with partial knowledge. Finally, the estimated feedback is provided to a Partitioned Visual Servo tracking controller for autonomous multirotor navigation along the coast, ensuring that the latter will always remain inside the onboard camera field of view. A series of outdoor comparative studies using an octocopter flying along the shoreline in various weather and beach settings demonstrate the effectiveness of the suggested architecture. Full article

The rapid growth of data traffic due to the demands of new services and applications poses new challenges to the wireless network. Unmanned aerial vehicles (UAVs) can be a solution to support wireless networks during congestion, especially in scenarios where the region has high traffic peaks due to the temporal and spatial flow of users. In this paper, an intelligent machine-learning-based system is proposed to deploy UAV base stations (UAV-BS) to temporarily support the mobile network in regions suffering from the congestion effect caused by the high density of users. The system includes two main steps, the load prediction algorithm (LPA) and the UAV-BSs clustering and positioning algorithm (UCPA). In LPA, the load history generated by the mobile network is used to predict which macrocells are congested. In UCPA, planning is performed to calculate the number of UAV BSs needed based on two strategies: naïve and optimized, in addition to calculating the optimal positioning for each device requested to support the overloaded macrocells. For prediction, we used two models, generalized regression neural networks (GRNN) and random forest, and the results showed that both models were able to make accurate predictions, and the random forest model was better with an accuracy of over 85%. The results showed that the intelligent system significantly reduced the overhead of the affected macrocells, improved the quality of service (QoS), and reduced the probability of blocking users, as well as defined the preventive scheduling for the UAV BSs, which benefited the scheduling and energy efficiency. Full article