Explore the vast range of titles available.

Purpose: We consider the problem of route planning of multiple rechargeable heterogeneous UAVs with multiple trips under mission time and payload carrying constraints. The goal is to determine the types and number of UAVs to be deployed and their flying paths that minimizes the monetary cost, which is a sum of the recharging energy cost of each UAV, the UAV rental cost, and the cost of violating the mission time deadline.Design/methodology/approach: The problem is formulated as a mixed integer programming (MIP). Then, the genetic algorithm (GA) is developed to solve the model and the solutions are compared to those obtained from the exact method (Branch-and-Bound). Novel chromosome encoding and population initializations are designed, and standard procedures for crossover and mutation are adapted to this work. Test problems on grid networks and real terrains are used to evaluate the runtime efficiency and solution optimality, and the sensitivity of GA parameters is studied based on two-level factorial experiments.Findings: The proposed GA method can find optimal solutions for small problem sizes but with much less computation time than the exact method. For larger problem sizes, the exact method failed to find optimal solutions within the limits of time and disk space constraints (24 hours and 500 GB) while the GA method yields the solutions within a few minutes with as high as 49% better objective values. Also, the proposed GA method is shown to well explore the solution space based on the variation of the total costs obtained.Originality/value: The unique aspects of this work are that the model optimizes the sum of three different costs – the electricity recharging cost, the UAV rental cost, the penalty cost for mission deadline violation, and the recharging period based on the remaining energy, the payload capacity, and the heterogeneity of UAVs are incorporated into the model. The model is formulated as a mixed integer programming and the genetic algorithm is developed to solve the program. Novel chromosome encoding and population initializations are designed, and standard procedures for crossover and mutation are adapted to this work.

Applications of remote sensing using unmanned aerial vehicle (UAV) in agriculture has proved to be an effective and efficient way of obtaining field information. In this study, we validated the feasibility of utilizing multi-temporal color images acquired from a low altitude UAV-camera system to monitor real-time wheat growth status and to map within-field spatial variations of wheat yield for smallholder wheat growers, which could serve as references for site-specific operations. Firstly, eight orthomosaic images covering a small winter wheat field were generated to monitor wheat growth status from heading stage to ripening stage in Hokkaido, Japan. Multi-temporal orthomosaic images indicated straightforward sense of canopy color changes and spatial variations of tiller densities. Besides, the last two orthomosaic images taken from about two weeks prior to harvesting also notified the occurrence of lodging by visual inspection, which could be used to generate navigation maps guiding drivers or autonomous harvesting vehicles to adjust operation speed according to specific lodging situations for less harvesting loss. Subsequently orthomosaic images were geo-referenced so that further study on stepwise regression analysis among nine wheat yield samples and five color vegetation indices (CVI) could be conducted, which showed that wheat yield correlated with four accumulative CVIs of visible-band difference vegetation index (VDVI), normalized green-blue difference index (NGBDI), green-red ratio index (GRRI), and excess green vegetation index (ExG), with the coefficient of determination and RMSE as 0.94 and 0.02, respectively. The average value of sampled wheat yield was 8.6 t/ha. The regression model was also validated by using leave-one-out cross validation (LOOCV) method, of which root-mean-square error of predication (RMSEP) was 0.06. Finally, based on the stepwise regression model, a map of estimated wheat yield was generated, so that within-field spatial variations of wheat yield, which was usually seen as general information on soil fertility, water potential, tiller density, etc., could be better understood for applications of site-specific or variable-rate operations. Average yield of the studied field was also calculated according to the map of wheat yield as 7.2 t/ha.

The current paper presents a path planning method based on probability maps and uses a new genetic algorithm for a group of UAVs. The probability map consists of cells that display the probability which the UAV will not encounter a hostile threat. The probability map is defined by three events. The obstacles are modeled in the probability map, as well. The cost function is defined such that all cells are surveyed in the path track. The simple formula based on the unique vector is presented to find this cell position. Generally, the cost function is formed by two parts; one part for optimizing the path of each UAV and the other for preventing UAVs from collision. The first part is a combination of safety and length of path and the second part is formed by an exponential function. Then, the optimal paths of each UAV are obtained by the genetic algorithm in a parallel form. According to the dimensions of path planning, genetic encoding has two or three indices. A new genetic operator is introduced to select an appropriate pair of chromosome for crossover operation. The effectiveness of the method is shown by several simulations.

We present an unsupervised deep learning approach for post-disaster building damage detection that can transfer to different typologies of damage or geographical locations. Previous advances in this direction were limited by insufficient qualitative training data. We propose to use a state-of-the-art Anomaly Detecting Generative Adversarial Network (ADGAN) because it only requires pre-event imagery of buildings in their undamaged state. This approach aids the post-disaster response phase because the model can be developed in the pre-event phase and rapidly deployed in the post-event phase. We used the xBD dataset, containing pre- and post- event satellite imagery of several disaster-types, and a custom made Unmanned Aerial Vehicle (UAV) dataset, containing post-earthquake imagery. Results showed that models trained on UAV-imagery were capable of detecting earthquake-induced damage. The best performing model for European locations obtained a recall, precision and F1-score of 0.59, 0.97 and 0.74, respectively. Models trained on satellite imagery were capable of detecting damage on the condition that the training dataset was void of vegetation and shadows. In this manner, the best performing model for (wild)fire events yielded a recall, precision and F1-score of 0.78, 0.99 and 0.87, respectively. Compared to other supervised and/or multi-epoch approaches, our results are encouraging. Moreover, in addition to image classifications, we show how contextual information can be used to create detailed damage maps without the need of a dedicated multi-task deep learning framework. Finally, we formulate practical guidelines to apply this single-epoch and unsupervised method to real-world applications.

The application of spectral sensors mounted on unmanned aerial vehicles (UAVs) assures high spatial and temporal resolutions. This research focused on canopy reflectance for cultivar recognition in an olive grove. The ability in cultivar recognition of 14 vegetation indices (VIs) calculated from reflectance patterns (green520–600, red630–690 and near-infrared760–900 bands) and an image segmentation process was evaluated on an open-field olive grove with 10 different scion/rootstock combinations (two scions by five rootstocks). Univariate (ANOVA) and multivariate (principal components analysis—PCA and linear discriminant analysis—LDA) statistical approaches were applied. The efficacy of VIs in scion recognition emerged clearly from all the approaches applied, whereas discrimination between rootstocks appeared unclear. The results of LDA ascertained the efficacy of VI application to discriminate between scions with an accuracy of 90.9%, whereas recognition of rootstocks failed in more than 68.2% of cases.

In recent years, with the rapid development of unmanned aerial vehicles (UAV) technology and swarm intelligence technology, hundreds of small-scale and low-cost UAV constitute swarms carry out complex combat tasks in the form of ad hoc networks, which brings great threats and challenges to low-altitude airspace defense. Security requirements for low-altitude airspace defense, using visual detection technology to detect and track incoming UAV swarms, is the premise of anti-UAV strategy. Therefore, this study first collected many UAV swarm videos and manually annotated a dataset named UAVSwarm dataset for UAV swarm detection and tracking; thirteen different scenes and more than nineteen types of UAV were recorded, including 12,598 annotated images—the number of UAV in each sequence is 3 to 23. Then, two advanced depth detection models are used as strong benchmarks, namely Faster R-CNN and YOLOX. Finally, two state-of-the-art multi-object tracking (MOT) models, GNMOT and ByteTrack, are used to conduct comprehensive tests and performance verification on the dataset and evaluation metrics. The experimental results show that the dataset has good availability, consistency, and universality. The UAVSwarm dataset can be widely used in training and testing of various UAV detection tasks and UAV swarm MOT tasks.

In large-scale disasters, such as earthquakes and tsunamis, quick and sufficient transportation of emergency relief supplies is required. Logistics activities conducted to quickly provide appropriate aid supplies (relief goods) to people affected by disasters are known as humanitarian logistics (HL), and play an important role in terms of saving the lives of those affected. In the previous last-mile distribution of HL, supplies are transported by trucks and helicopters, but these transport methods are sometimes not feasible. Therefore, the use of unmanned aerial vehicles (UAVs) to transport supplies is attracting attention due to their convenience regardless of the disaster conditions. However, existing transportation planning that utilizes UAVs may not meet some of the requirements for post-disaster transport of supplies. Equitable distribution of supplies among affected shelters is particularly important in a crisis situation, but it has not been a major consideration in the logistics of UAVs in the existing study. Therefore, this study proposes transportation planning by introducing three crucial performance metrics: (1) the rapidity of supplies, (2) the urgency of supplies, and (3) the equity of supply amounts. We formulated the routing problem of UAVs as the multi-objective, multi-trip, multi-item, and multi-UAV problem, and optimize the problem with Q-learning (QL), one of the reinforcement learning methods. We performed reinforcement learning for multiple cases with different rewards and quantitatively evaluated the transportation of each countermeasure by comparing them. The results suggest that the model improved the stability of the supply of emergency relief supplies to all evacuation centers when compared to other models.

Here, we investigated the capabilities of a lightweight unmanned aerial vehicle (UAV) photogrammetric point cloud for estimating forest biophysical properties in managed temperate coniferous forests in Japan, and the importance of spectral information for the estimation. We estimated four biophysical properties: stand volume (V), Lorey’s mean height (HL), mean height (HA), and max height (HM). We developed three independent variable sets, which included a height variable, a spectral variable, and a combined height and spectral variable. The addition of a dominant tree type to the above data sets was also tested. The model including a height variable and dominant tree type was the best for all biophysical property estimations. The root-mean-square errors (RMSEs) for the best model for V, HL, HA, and HM, were 118.30, 1.13, 1.24, and 1.24, respectively. The model including a height variable alone yielded the second highest accuracy. The respective RMSEs were 131.74, 1.21, 1.31, and 1.32. The model including a spectral variable alone yielded much lower estimation accuracy than that including a height variable. Thus, a lightweight UAV photogrammetric point cloud could accurately estimate forest biophysical properties, and a spectral variable was not necessarily required for the estimation. The dominant tree type improved estimation accuracy.

Three-dimensional (3D) modeling of tsunami events is intended to promote tsunami safety. However, the developed 3D modeling methods based on Computational Fluid Dynamics and photorealistic particle visualization have some weaknesses, such as not being similar to the original environment, not measuring the wave’s end point, and low image accuracy. The method for 3D modeling of tsunamis that results from this research can fulfil those weaknesses because it has advantages, such as being able to predict the end point of waves, similar to the original environment, and the height and area of inundation. In addition, the method produces more detailed and sharper spatial data. Modeling in this research is conducted using Agisoft Metashape Professional software to a produce 3D orthomosaic from pictures taken with Unmanned Aerial Vehicle (UAV) technique or drone (photogrammetry), and 3ds max software is used for wave simulation. We take a sample of an area in Cilacap, Indonesia that was impacted by the 2006 southwest coast tsunamis and may be vulnerable to future big megathrust earthquakes and tsunamis. The results could be used to provide several benefits, such as the creation of evacuation routes and the determination of appropriate locations for building shelters.

Disturbances in forest ecosystems are expected to increase by the end of the twenty-first century. An understanding of these disturbed areas is critical to defining management measures to improve forest resilience. While some studies emphasize the importance of quick salvage logging, others emphasize the importance of the deadwood for biodiversity. Unmanned aerial vehicle (UAV) remote sensing is playing an important role to acquire information in these areas through the structure-from-motion (SfM) photogrammetry process. However, the technique faces challenges due to the fundamental principle of SfM photogrammetry as a passive optical method. In this study, we investigated a UAV video-based technology called full motion video (FMV) to identify fallen and snapped trees in a windthrow area. We compared the performance of FMV and an orthomosaic, created by the SfM photogrammetry process, to manually identify fallen and snapped trees, using a ground survey as a reference. The results showed that FMV was able to identify both types of damaged trees due to the ability of video to deliver better context awareness compared to the orthomosaic, although providing lower position accuracy. In addition to its processing being simpler, FMV technology showed great potential to support the interpretation of conventional UAV remote sensing analysis and ground surveys, providing forest managers with fast and reliable information about damaged trees in windthrow areas.