Unmanned Aerial Vehicle Equipment Research Articles

Choosing Hyperparameter Values of the Convolution Neural Network When Solving the Problem of Semantic Segmentation of Images Obtained by Remote Sensing of the Earth’s Surface

Among the tasks solved by artificial neural networks are the tasks of analyzing objects on the images of the underlying Earth’s surface, obtained by the on-board equipment of unmanned aerial vehicle (UAV). For the solution of such problems, the convolutional neural networks (CNN), operating semantic segmentation of the received image, are widely used. In this case, the designer of such networks has to solve the difficult task of selecting hyperparameter values for them. These values’ choice is one of the most critical tasks that have to be solved when forming a CNN. Existing attempts to solve this problem are usually based on one of two approaches. The first one involves a set of experiments with different values of hyperparameters of the CNN with learning each of the network variants. These experiments are performed until a CNN with acceptable characteristics is obtained. This approach is simple to implement but does not guarantee a CNN with high performance. The second approach treats the selection of hyperparameter values in the network as an optimization problem. If this problem is successfully solved, it is possible to obtain a CNN with sufficiently high characteristics. However, this task has a significant complexity and also requires a large consumption of computing resources. Images in the form of multidimensional arrays are used as source data to analyze objects on the underlying surface. It means that CNN will contain a significant number of parameters. Accordingly, it will take considerable time to find a suitable CNN by searching for possible hyperparameter values. This paper proposes an alternative approach to the problem of selecting the hyperparameter values of CNN based on the analysis of the processes running in the network. The effectiveness of this approach is demonstrated by solving the problem of semantic segmentation of the underlying surface obtained by remote sensing of the Earth’s surface.

UAV Inspection Path Planning Based on Transmission Line Technology

With the continuous progress of human society and the rapid development of economy, the power industry closely related to human production and life is also developing rapidly. Electric power industry is also playing an increasingly important role in the development of national economy. Subsequently, transmission security becomes more and more important. However, at present, the traditional single manual line inspection has the characteristics of high labor intensity, high safety risk, high safety risk, low operation efficiency, and many deficiencies seriously restrict the intelligent transformation of transmission line operation and maintenance. Therefore, this paper proposes a new transmission line detection scheme based on unmanned aerial vehicle (UAV) detection path planning. Transmission line detection system based on UAV and ground monitoring equipment basically meets the requirements of transmission line detection. It is found that the UAV based transmission line inspection work arrangement efficiency is higher, and the fault detection rate is higher. The accuracy rate of UAV line inspection method proposed in this paper reaches 93.7%, which can effectively reduce the workload of staff and improve the work efficiency.

DEVELOPMENT OF AN ADVANCED METHOD OF VIDEO INFORMATION RESOURCE COMPRESSION IN NAVIGATION AND TRAFFIC CONTROL SYSTEMS

The Earth's aerospace monitoring (ASM) systems use state-of-the-art integrated information technologies that include radio-based detection and surveillance systems using telecommunications. One of the main tasks of ASM systems is to increase the efficiency of decision-making necessary for the timely prevention, detection, localization and elimination of crisis situations and their probable consequences. Modern conditions impose stricter requirements for efficiency, reliability and quality of the provided video data. To ensure compliance with the requirements, it is necessary to provide the appropriate capabilities of the onboard equipment. On the basis of the existing information and communication systems it is necessary to carry out: continuous or periodic assessment of a condition of objects of supervision and control; continuous (operational) collection, reception, transmission, processing, analysis and display of information resources. It is proposed to use UAVs (unmanned aerial vehicles) as a means to perform ASM tasks. The time of organizing communication sessions and delivery of information should vary from a few seconds to 2.5 hours. Untimely processing and delivery of a specific information resource in the management process leads to its obsolescence or loss of relevance, which contributes to erroneous decisions. One way to reduce time is to encode the data. To do this, it is proposed to use video compression algorithms. However, based on the analysis of the possibility of modern methods of video information compression, taking into account the specifics of the onboard equipment of the UAV, the coding problem is not completely solved. The research results show the expediency of using an improved method of video information compression to reduce the computing resources of the software and hardware complex of the onboard UAV equipment and to ensure the requirements for efficiency and reliability of data in modern threats to ASM systems as a whole.

Estimation of Genetic Parameters and Selection of Superior Genotypes in a 12-Year-Old Clonal Norway Spruce Field Trial after Phenotypic Assessment Using a UAV

Height is a key trait in the indices applied when selecting genotypes for use in both tree breeding populations and production populations in seed orchards. Thus, measurement of tree height is an important activity in the Swedish Norway spruce breeding program. However, traditional measurement techniques are time-consuming, expensive, and often involve work in bad weather, so automatization of the data acquisition would be beneficial. Possibilities for such automatization have been opened by advances in unmanned aerial vehicle (UAV) technology. Therefore, to test its applicability in breeding programs, images acquired by a consumer-level UAV (DJI Phantom 4 Pro V2.0) system were used to predict the height and breast height diameter of Norway spruce trees in a 12-year-old genetic field trial established with 2.0 × 2.0 m initial spacing. The tree heights were also measured in the field using an ultrasonic system. Three additive regression models with different numbers of predictor variables were used to estimate heights of individual trees. On stand level, the average height estimate derived from UAV data was 2% higher than the field-measured average. The estimation of family means was very accurate, but the genotype-level accuracy, which is crucial for selection in the Norway spruce breeding program, was not high enough. There was just ca. 60% matching of genotypes in groups selected using actual and estimated heights. In addition, heritability values calculated from the predicted values were underestimated and overestimated for height and diameter, respectively, with deviations from measurement-based estimates ranging between −19% and +12%. However, the use of more sophisticated UAV and camera equipment could significantly improve the results and enable automatic individual tree detection.

Application of digital image processing for autofocusing system construction

The article states the method of autofocusing of the optoelectronic image, based on digital image processing. Some systems of autofocusing which can be used in optoelectronic equipment of unmanned aerial vehicles are considered. The method developed by authors and the program algorithm implementing it are similar to the rules of functioning of an element of the human visual system which executes an estimation of a spectrum of spatial frequencies for the realization of focusing of the image of objects which are of interest or danger and are on different distance from the observer. The best focusing is defined on the greatest width of a spectrum of spatial frequencies of the object. Such estimation allows focusing the necessary object on the observable image even in the absence of binocular vision. The method is based on the numerical analysis of a two-dimensional amplitude spectrum of the image. Results of operation of the stated method which confirm its efficiency are presented.

Advanced Techniques in As-Built Survey by using UAV Technology

As-built surveys are needed to record variations from original Engineering plans to what is actually built and the final set of drawings produced at the completion of a construction project. As-built surveys are required by many agencies to prove the location of a structure at a point in time. These are especially important for maintenance and future development of the site. To handle this task conventionally, total station was used, but it is more costly, time consuming and more skilled surveyors are required to conduct a total station survey. Purpose of this study is to investigate the Unmanned Aerial Vehicles (UAV) system for comparison of the proposed drawing of UTHM Pagoh Campus with the as-built orthomosaic images and to carry out the mapping based on imaged by UAV. Therefore, a method of mapping by UAV, the application of camera-equipped for visually monitoring construction and operation of buildings was used to collect all the information directly on the site which is on the study area. It is also to carry out the mapping based on imaged by UAV. The data collections show that method to earn all information required for this study is by using UAV equipment, Pix4D and Global Mapper software to generate the images. The result of the study is proved that the ability of the UAV in production of as-built survey mapping is can be achieved and it also ease the as-built survey work due to saving time and skilled surveyors are not required. Thus, UAV is very suitable for engineering work purposes

Design and Implementation of a Virtual Sensor Network for Smart Waste Water Monitoring.

Monitoring and analysis of open air basins is a critical task in waste water plant management. These tasks generally require sampling waters at several hard to access points, be it real time with multiparametric sensor probes, or retrieving water samples. Full automation of these processes would require deploying hundreds (if not thousands) of fixed sensors, unless the sensors can be translated. This work proposes the utilization of robotized unmanned aerial vehicle (UAV) platforms to work as a virtual high density sensor network, which could analyze in real time or capture samples depending on the robotic UAV equipment. To check the validity of the concept, an instance of the robotized UAV platform has been fully designed and implemented. A multi-agent system approach has been used (implemented over a Robot Operating System, ROS, middleware layer) to define a software architecture able to deal with the different problems, optimizing modularity of the software; in terms of hardware, the UAV platform has been designed and built, as a sample capturing probe. A description on the main features of the multi-agent system proposed, its architecture, and the behavior of several components is discussed. The experimental validation and performance evaluation of the system components has been performed independently for the sake of safety: autonomous flight performance has been tested on-site; the accuracy of the localization technologies deemed as deployable options has been evaluated in controlled flights; and the viability of the sample capture device designed and built has been experimentally tested.

Development of a Cross-Type Magnetic Coupler for Unmanned Aerial Vehicle IPT Charging Systems

Inductive power transfer (IPT) is an optimal way for the unmanned aerial vehicle (UAV) wireless charging. The magnetic coupler is the key component in the IPT system, which determines the power transmission capacity and efficiency in IPT system. Due to the particularity of UAV application, the magnetic field height should be strictly limited to avoid the damage caused by high frequency magnetic field heat the UAV's metal equipment. A cross-type magnetic coupler with receiving coil placed on UAV's one landing gear was proposed to solve this problem, but it has the possibility of making UAV fuselage imbalance. Therefore, a novel cross-type magnetic coupler is proposed to overcome its difficulties in this paper, and most of magnetic fields are restrained to be lower than UAV's landing gear height h 1 = 145mm, which will not cause damage to the UAV's equipment. And a simple and practical iterative method for designing the magnetic coupler geometry parameters is proposed, with simplification of the complex design process for the finite element analysis, improves the design efficiency. The experimental results show that the system can charge the 260W UAV normally with the system efficiency of 91.577% within the misalignment range of X-axis direction 25mm, Y-axis direction 40mm and rotation 25.

Классификация приоритетности боевых беспилотных летательных аппаратов на основе комплексной оценки

In this work, we solved the problem of obtaining estimates of the prospects combat of unmanned aerial vehicles (UAVs) according to the available estimates of a certain part of UAVs and their further clustering by the value of the complex priority indicator. A new estimation scheme is proposed that uses five known particular indicators of each assessed UAV, which, after normalizing them and determining the significance coefficients of particular indicators, were combined into a complex UAV indicator. Based on the obtained estimates of the complex indicator of each of the considered UAVs, the clustering of the set of the considered UAVs was carried out according to the belonging of the complex indicator to the intervals of its possible values from 0 to 100. One hundred or zero points can be obtained by that UAV, in which all particular indicators have respectively the best or worst values among all compared UAVs. Clustering made it possible to divide the UAVs into groups according to the principle of similarity of the tasks performed. In the Python programming language, a program was developed that implements the proposed clustering scheme, and allows to obtain estimates of objects and classify these objects according to the principle of proximity of complex indicators. This scheme allows to identify the best (and worst) UAVs in each of the UAV classes, distinguished by the commonly used clustering indicator, takeoff weight. About 14% of UAVs considered in this work were included in the best cluster in terms of complex indicator with an indicator value of at least 59 points with a maximum score of 100 points. The obtained results can be used in the development of requirements for the equipment and operation of UAVs.

Synthesis of a Radiator in the Frequency Range of 0.9…5.8 GHz

Introduction. In this work, we consider the problem of a radiator synthesis with the 50-Ohm port at the input in the frequency range of 0.9…5.8 GHz. At present, this frequency range is the most relevant for the electromagnetic environment analysis due to information exchange with the on-board equipment of unmanned aerial vehicles is most often realized in this frequency range.Objective. The main objective of this work is the synthesis of a radiator for an ultra-wideband antenna array in the frequency range of 0.9…5.8 GHz.Materials and methods. In this work, the method of full-wave electromagnetic simulation is used for the broadband radiator synthesis. The characteristics of the radiator are optimized by simulation and confirmed by experimental investigations of the radiator model. The antenna radiation pattern measurements are carried out in the anechoic chamber and standing wave ratio (SWR) is calculated by using the network analyzer.Results. A non-analytical method of the model parametric optimization considering the SWR<2 criterion and using the latest tools of the full-wave electromagnetic simulation is proposed. The examples of the designed optimized model with the final values of all parameters are reported. The calculated distributions of the electric field over the antenna, calculated radiation patterns at several frequency points, and calculated SWR of the model are presented. The radiator model is made taking into account simulation and optimization results. The measured main cross-sections of the radiation pattern and SWR of the model are shown. Conclusion. In the present work, the broadband radiator model in the frequency range of 0.9…5.8 GHz is designed. The machining and brief comparative analysis of the calculated and measured antenna characteristics is carried out and demonstrated a good agreement. The advantages of the proposed method and designed radiator model are described. The results of this work are relevant in the tasks of observation, direction finding and signals reception from unmanned aerial vehicles. Key words: ultra-wideband antenna, Vivaldi antenna, microwave range, full-wave electromagnetic simulation><2 criterion and using the latest tools of the full-wave electromagnetic simulation is proposed. The examples of the designed optimized model with the final values of all parameters are reported. The calculated distributions of the electric field over the antenna, calculated radiation patterns at several frequency points, and calculated SWR of the model are presented. The radiator model is made taking into account simulation and optimization results. The measured main cross-sections of the radiation pattern and SWR of the model are shown.Conclusion. In the present work, the broadband radiator model in the frequency range of 0.9…5.8 GHz is designed. The machining and brief comparative analysis of the calculated and measured antenna characteristics is carried out and demonstrated a good agreement. The advantages of the proposed method and designed radiator model are described. The results of this work are relevant in the tasks of observation, direction finding and signals reception from unmanned aerial vehicles.

Enhancing biologically inspired swarm behavior: Metaheuristics to foster the optimization of UAVs coordination in target search

Recent miniaturization in Unmanned Aerial Vehicles (UAVs) technology encourages the use of many small UAVs for search missions in unknown environments, provided that the autonomous and adaptive coordination logic can be effective. In this research field, biologically inspired metaheuristics have been proposed to mimics swarms, flocks, and other coordination schemas. The design and management of such systems is a research challenge when considering (i) combination and optimization of multiple metaheuristics and (ii) enhancements of biologically inspired metaheuristic through technological advances. In this paper the swarm coordination of UAVs employed in target search is based on flocking and stigmergy, to provide robust formation control and dynamic environmental information sharing, respectively. The design of both metaheuristics takes into account UAVs equipment, and the coordination logic is adapted to the mission by means of a differential evolutionary algorithm. This algorithm optimizes the aggregated structural parameters of all metaheuristics to allow the most efficient coordination with respect to the mission environment. Some possible enhancements of stigmergy are studied by simulating target search tasks on synthetic and real-world scenarios.

UAVs for coastal surveying

UAVs (Unmanned Aerial Vehicles or “drones”) for routine survey applications at the coast have come of age, and are no longer ‘the latest thing’ more suited to the specialist researcher or amateur enthusiast. Off-the-shelf, survey-grade UAV equipment, data processing and analysis tools are now readily available to practicing coastal engineers, managers and researchers. Within the regulatory constraints that determine their use in many countries, UAVs provide an efficient and cost-effective survey tool for topographic mapping and measurement in the coastal zone. At the practical level, the specialist training required to operate off-the-shelf UAV suited to coastal surveying is now comparable in time and degree of difficulty to learning how to use the equivalent survey capabilities of professional hand-held RTK-GPS equipment. While incremental improvements to both the flight technology and data processing will no doubt continue to occur, from the coastal practitioner's perspective, no more step changes in UAV technology or ease of useability are required. In particular, survey-grade UAVs that incorporate internal RTK-GPS for high accuracy positioning and requiring a single operator only to safely deploy in the field, remove the need for separate and time-consuming on-ground surveying of ground control points (GCPs), previously required during post-deployment data processing. A coastal engineering application of UAV is used here to exemplify the practical use and potential benefits of this now mature survey technology. Over the past 2years, rapid post-storm deployment of UAV surveying has been successfully integrated into an established coastal monitoring program spanning 4 decades at Narrabeen Beach, Australia. This has extended the scope of this program to include detailed measurements of dune and beachface erosion spanning the full 3.5km long embayment at a spatial scale and temporal resolution that were previously unfeasible. For both the researcher and practicing coastal engineer, UAVs now provide a practical option for routine coastal surveying.

Analysis and Design of Electromagnetic Compatibility Techniques for Unmanned Aerial Vehicle Power in Aeromagnetic Survey

—The reason why the measurement precision of the aeromagnetic data cannot be as high as that of the aeromagnetic instruments is due to the level of magnetic interference of an unmanned aerial vehicle. Through the analysis of electromagnetic interference sources of unmanned aerial vehicles and the working characteristics of optical pumping magnetometers, this article intends to optimize the switch mode power supply circuit. Ripple coefficient of output voltage is reduced to 0.2%, the magnitude spectrum of the near-field radiation is decreased by 10 dB and the conduction emission is below 20 dB. The electromagnetic compatibility of unmanned aerial vehicle equipment and the measurement precision of the optical pumping magnetometers are greatly improved.

Analysis of Active Clamp Forward Converter of UAV <sup></sup>

The Forward Switch mode power supply is good selection for power supplies of Unmanned Aerial Vehicle (UAV). Compared with the conventional forward converter, there is one auxiliary switch in the active clamp forward converter to recycle the energy stored in the transformer leakage in order to minimize the voltage stress of the main switch. The power system is designed and the operation characteristics of the active switching power supply are revealed by analysis a typical second-order system in this paper. Active Clamp Forward Converter reduce the generation of EMI, the EMC of UAV equipment is greatly improved. The results of the analysis are verified by SPICE simulation.

RUNWAY DETECTING AND TRACKING OF AN UNMANNED AERIAL LANDING VEHICLE BASED ON VISION

When a monocular vision-based unmanned aerial vehicle (UAV) is flown to the final approach to intercept the glide slope, the position and orientation of the airport runway in the image must be detected accurately for a host of suitable procedures to be followed. The approaching marking on the runway is showed as some white spots of high intensity as well as the complicated backgrounds. In our paper, we use pin-hole perspective principle, the constraint condition of the rectangle in inertial space, the front shot constraint condition of the target, as well as the clustering algorithm to identify the runway and output its position and orientation in image space. The results of the experiments show that by this algorithm, even from a place far away from the runway with marks being unclear, effective detection is possible. After all, single-frame detection errors exist, so we extend the basic runway-detection algorithm to the runway tracking. A full filtering strategy using particle filter can guard against potentially catastrophic results and improve the detection rate. Apparently, the whole algorithm of our paper can be treated as a special vision sensor for landing equipment of UAV.