Help Of Unmanned Aerial Vehicles Research Articles

Study of the dependence of accuracy in vehicles search on the size of the object using UAV images

Digital images are increasingly used to analyze different types of objects and their localization and classification. There are many areas for using this information; it is often employed for surveillance systems, automatic driving of vehicles, or exploration of new territories. At the same time, there are a fairly large number of neural networks that allow implementation of this functionality by training them using data sets of various types and classifications. Often, data sets created with the help of unmanned aerial vehicles are frequently used for research tasks. Such datasets allow the recognition of various types of objects without direct access to them, which allows safe exploration of different territories. The use of unmanned aerial vehicles is quite common nowadays, especially in the fields of photography and videography. Many photographers use unmanned aerial vehicles to take pictures of landscapes and use automatic tracking systems for movement. Automatic movement systems and object search systems are quite sensitive to the size of the object and the quality of the search algorithm. Because of the wide applicability of this task, as well as the small amount of initial data, the topic of our work is the study of the dependence of the accuracy of localization and classification of objects on their area in images obtained using unmanned aerial vehicles. The main subject of this study is the quality of neural networks that allow obtaining information about objects, as well as research by obtaining statistical data and a test set of data on the dependence of detection accuracy on the size of the object. The goal of this study was to obtain statistics on the accuracy of localization and classification depending on the size of the object and to determine the accuracy thresholds using the obtained statistics. The task of this study is to train common neural networks with an open architecture on a set of data obtained using unmanned aerial vehicles and to determine their characteristics, particularly the dependence of recognition accuracy on the size of the object. The expected result of the work is the threshold values of the size of the object, which are permissible for a sufficiently accurate classification and localization of objects, as well as the metrics of the quality of the work of the studied neural networks. Because of this work, conclusions are given that reflect the threshold values of object sizes, on which the recognition accuracy depends.

DEVELOPMENT OF THE DERMAL EFFECT OF PESTICIDES ON PROFESSIONAL CONTINGENTS USING INNOVATIVE 3RIVE 3D TECHNOLOGY

The skin is the most vulnerable organ when spraying pesticides on fields. Farmers are also exposed to pesticides during mixing, loading of pesticides, and when cleaning equipment and disposing of empty containers. The aim. To study and analyze the features of the risk of pesticides dermal exposure to professional contingents during treatments using the innovative 3RIVE 3D pesticide application technology. Materials and methods. The 3RIVE 3D innovative technological system of introducing was used to applicate Brigade 3Rive 3D, SC formulation. Field experiments on the study of working conditions when using the pesticide were conducted in various soil and climatic regions of Eastern Europe. Statistical processing of the results was carried out using a package of licensed statistical programs IBM SPSS StatisticsBase v.22 and MS Excel. Research results and discussion. During the conducted research, no bifenthrin contamination was found on the open skin of the operator and the tractor driver, who were processing corn crops with the Brigade 3Rive 3D, SC formulation. However, the operator's gloves were found to contain 0.025 mg of bifenthrin. Calculation of the unitless CASd value on the possibility of skin acute effects when applying the formulation showed that bifenthrin and the Brigade 3Rive 3D, SC formulation based on it are characterized by sufficient selectivity of action on the target object (CASd – 645 and 162, respectively, i.e. > 100) and a low level of danger acute dermal toxic effects for workers, which is due to low values of effective consumption rates. The real dermal risk of bifenthrin exposure when using the Brigade 3Rive3D, SC formulation was significantly lower compared to the risk of workers involved in “traditional” air treatment and treatment with unmanned aerial vehicles (UAVs) (p=0.009-0.048 according to Wilcoxon's W-criterion); in comparison with rod and fan processing – it is non-significantly lower (р=0.262-1.000). There was a similar picture in comparison with the dermal aggravated risk – significantly lower in comparison with the risk of workers involved in “traditional” air treatment and processing with the help of UAVs (p=0.009 according to Wilcoxon's W-criterion); in comparison with rod and fan treatment – non-significantly lower (р=0.262-1.000). Conclusion. It was established that the studied active substance bifenthrin and the Brigade 3Rive 3D, SC formulation based on it are characterized by sufficient selectivity of dermal action on the target object and a low probability of acute dermal effects. A higher probability of acute inhalation poisoning than dermal exposure was revealed.

Chemical sensors on unmanned aerial vehicles: new possibilities for searching for mines and explosive devices

Increasing the effectiveness of anti-mine protection of troops, timely detection and marking of mine-explosive devices in the area, prompt informing of personnel of units operating in the area, search for methods and means that increase the reliability of the search and reduce the level of false detections, possible identification and marking of mines (explosive objects) are extremely relevant and, given the scale of demining that will need to be carried out on the territory of Ukraine after the end of hostilities, promising tasks. This can be achieved through the introduction of modern, reliable, effective, remote methods and means of searching, detecting, identifying and marking mine-explosive devices that work in real time with a fairly high speed. The purpose of the research is to justify the need to use chemical modules (equipped with a set of chemical sensors) installed on unmanned aerial vehicles for conducting engineering and reconnaissance actions for the search, detection and marking of mine-explosive devices. It has been established that the combination of unmanned aerial vehicles of the multi-rotor type with the appropriate chemical module will prevail over other means of reconnaissance of mine-explosive devices (barrages) in service and will meet such criteria as mobility, speed (operational), sensitivity, reliability, selectivity, reliability, stability. It is recommended that the chemical module include various appropriate sensors that will complement each other and cover the entire range of explosives used to equip mines and explosive objects. Chemical sensors that work on the principle of suppression of fluorescent radiation by the vapor of an explosive substance are promising. The effectiveness of demining with the help of unmanned aerial vehicles with a chemical module will depend on the probability of explosive vapors entering the chemical module's area of operation and the probability of detecting mine-explosive devices. At the same time, the equipment of unmanned aerial vehicles intended for conducting engineering reconnaissance not only with a chemical module, but also with other, additional sensors for detecting mines (explosive objects) by secondary signs will allow to increase the reliability of the search and detection of mine-explosive devices.

Опыт использования беспилотных летательных аппаратов для выявления мест размещения отходов в водоохранных зонах

Disposal of industrial and consumer waste in water protection zones of water bodies is a violation of water legislation of the Russian Federation. The use of materials obtained with the help of unmanned aerial vehicles (UAVs) significantly expands the possibilities for determining stored waste. UAVs are used for prompt identification of unauthorized waste disposal sites within the boundaries of the water protection zones of the Tsimlyansk reservoir. The paper presents the possibilities of using orthophotoplans and photo materials obtained during field surveys carried out by the Russian Research Institute for the Integrated Use and Protection of Water Resources in 2019-2021. According to the research results, the largest accumulation of solid household waste is localized in the water protection zone of large cities and villages. The largest amount of waste stored in the water protection zone is located in the Dubovsky and Tsimplansk districts of the Rostov region, as well as in the Kalachyovsky district of the Volgograd region. Dumping sites detected with the help of UAVs based on the composition of the predominant waste were divided into five groups: solid household waste, construction waste, organic waste, metal, and waste of unknown composition. Up to 42 % of landfill waste in the water protection zone of the reservoir is solid domestic waste, at least 25 % of landfill sites are construction waste and 20 % are organ waste.

Forest Flame Detection in Unmanned Aerial Vehicle Imagery Based on YOLOv5

One of the major responsibilities for forest police is forest fire prevention and forecasting; therefore, accurate and timely fire detection is of great importance and significance. We compared several deep learning networks based on the You Only Look Once (YOLO) framework to detect forest flames with the help of unmanned aerial vehicle (UAV) imagery. We used the open datasets of the Fire Luminosity Airborne-based Machine Learning Evaluation (FLAME) to train the YOLOv5 and its sub-versions, together with YOLOv3 and YOLOv4, under equal conditions. The results show that the YOLOv5n model can achieve a detection speed of 1.4 ms per frame, which is higher than that of all the other models. Furthermore, the algorithm achieves an average accuracy of 91.4%. Although this value is slightly lower than that of YOLOv5s, it achieves a trade-off between high accuracy and real-time. YOLOv5n achieved a good flame detection effect in the different forest scenes we set. It can detect small target flames on the ground, it can detect fires obscured by trees or disturbed by the environment (such as smoke), and it can also accurately distinguish targets that are similar to flames. Our future work will focus on improving the YOLOv5n model so that it can be deployed directly on UAV for truly real-time and high-precision forest flame detection. Our study provides a new solution to the early prevention of forest fires at small scales, helping forest police make timely and correct decisions.

Розроблення програмного забезпечення для сегментації даних по фото та відео інформації

The object of this research is the process of perception of individual objects in photos and videos for further analysis of the situation in the city. The subject of the research is image processing for selection, classification, and further use of the obtained information about the objects in the photo. The goal is to create information technology for the segmentation of individual segments in photos and videos obtained with the help of unmanned aerial vehicles (in particular, drones) in urban scenes. Main tasks: analysis of existing methods of data segmentation; implementation of an algorithm that would perform segmentation of data by various terrain objects; software testing; and formation of research results. The following results were obtained: existing models of image segmentation were examined for limitations and shortcomings. On the basis of identified shortcomings, the requirements for the developed system were formed. During the analysis of the subject area, the main problems were identified and described and the task to be automated was determined. During the design of algorithms for solving problems, the sequence of the execution of each process was determined. The design of the software included a description of the information space of the system and the user interface. The user interface was chosen after analyzing the main types of user interfaces. To assess the quality of the data processing, existing metrics were used – IoU, pixel accuracy, and the discrepancy matrix. During testing, errors that occur during data segmentation and their causes were determined, after their elimination, the correct result of image segmentation was shown. Conclusions. The scientific novelty of the obtained results is that although there is still no segmentation method that fully satisfies all needs for the analysis of the category of images obtained by drones, the developed software allows uploading images and templates to them as benchmarks for artificial intelligence. perform segmentation and verify the correctness of this segmentation visually and using the IoU metric, the mismatch matrix. The software can be improved by automating the process of creating a reference pattern, training the model on more data, and integrating the created software into a larger system that would work directly with the drone.

Searching for the relationship between the temperature and humidity of tailings material by processing digital photographs of laboratory experiments and color models

Relevance. Tailings beach surface dries and deflates, which intensifies the dusting process, results in ecosystems disruption on the adjacent territories, and adversely impacts health of population. The use of digital photographs, including those obtained with the help of unmanned aerial vehicles, seems to be promising in terms of reagents application simplification and dusting minimization. Research objective is to determine the quantitative relationship between the temperature and humidity of tailings materials by analyzing the digital photographs of laboratory experiments using RGB and Lab methods. Methods of research. Standard equipment was used to perform a laboratory experiment to determine the temperature and humidity of tailing dump surface layer samples. Digital photographs were taken in natural light and UV light. At the first stage, the images were processed to obtain the values of the components of two color models, RGB (redness and saturation indices were calculated) and Lab (the color difference index was calculated, two standards of black and white were used). At the second stage, as a “zero” approximation, the simplest (linear) analytical dependence between temperature and humidity was studied. Results and analysis. The coefficients of calculated linear dependences are compared with the corresponding coefficients of direct experimental data processing. It is shown that in natural light: the smallest deviations for the dependence of temperature on humidity correspond to the redness index in the RGB method and the black standard in the Lab method; the smallest deviations for the dependence of humidity on temperature correspond to the saturation index in the RGB method and the black standard in the Lab method. It is shown that in UV light: the smallest deviations for the dependence of temperature on humidity correspond to the saturation index in the RGB method and the black standard in the Lab method; the smallest deviations of the dependence of humidity on temperature correspond to the redness index in the RGB method and the white standard in the Lab method. Conclusions and scope. The mentioned indices and colors of standards can be recommended when processing similar laboratory experiments and natural studies directly on the dusting site.

SAVIOR: A Sustainable Network of Vehicles with Near-Perpetual Mobility

Switching to Battery Electric Vehicles (BEV) can have a significant positive impact on our environment. However, the adoption of BEVs is vastly impeded by battery-related concerns, such as limited travel range, long charging time, high purchasing cost (battery-induced) and lack of charging stations. Additionally, it is very expensive to build a large infrastructure of fast charging stations that can cater to a full-scale BEV fleet. Alternative solutions, such as charging from the road and BEV-to-BEV stationary charge sharing, have been proposed to counteract range anxiety, but they are mostly ineffective and suffer from scalability issues. In this article, we present SAVIOR, an innovative Internet-of-Things (IoT) framework for replenishing BEV batteries on-the-go with the help of unmanned aerial vehicles (UAVs) and mobile charging stations (MoCS). This will allow rapid BEV battery replenishment, eliminating the need for BEVs to make prolonged and pre-planned halts for re-charging. We also observe that package delivery UAVs can utilize this framework to make long-distance trips with the help of mobile charging stations and BEVs. We quantitatively analyze the effectiveness of such a framework through a simulation platform that we have developed. There is a drastic improvement in the mobility of BEVs and UAVs. Through statistical analysis, we also observe that greenhouse gas emissions (even for BEVs and UAVs) can be significantly reduced by SAVIOR if the MoCS are powered by renewable energy sources (e.g., solar).

Deep Reinforcement Learning for Aerial Data Collection in Hybrid-Powered NOMA-IoT Networks

With the help of unmanned aerial vehicle (UAV), remote terminals that out of wireless coverage can be connected to the Internet of Things (IoT) networks. Currently, the IoT relies on a large number of low-cost wireless sensors with limited energy supply to realize ubiquitous monitoring and intelligent control. The hybrid-powered networks composed of wireless-powered communication (WPC) terminal and solar-powered UAV can solve the energy supply problem of the IoT networks, and the nonorthogonal multiple access (NOMA) technique can solve the massive access problem of IoT terminals. Exploiting these benefits, we investigate joint UAV 3-D trajectory design and time allocation for aerial data collection in hybrid-powered NOMA-IoT networks. To maximize the total fair network throughput, we jointly consider energy limitation, Quality of Service (QoS) requirements, and flight conditions. The problem is nonconvex and time-dimension coupled which is intractable to solve by traditional optimization methods. Therefore, we develop a deep reinforcement learning (DRL) algorithm called fair communication is accomplished by trajectory design and time allocation (FC-TDTA), which uses the deep deterministic policy gradient (DDPG) as its basis. Simulation results show that our proposed algorithm performs better than benchmarks in fair throughput maximization. The proposed FC-TDTA algorithm can make the UAV: 1) fly in appropriate direction and speed, so that the UAV can arrive at the charging station before the energy runs out and 2) conduct WPC energy transmission and data collection to achieve fair communication.

Testing the Agreement Between a Traditional and UAV-Based Method for Quantifying Skips in Suboptimal Cotton Stands

Highlights Agreement in the mean difference between the traditional and the UAV-based method only occurred in poor stands. Effects of different sampling sizes between methods were evident in mediocre-to-good stand assessments. Abstract. When suboptimal cotton stands occur, growers face the decision to accept or reject the stand. The replanting decision is difficult because the tradeoffs associated with replanting expenditures and reduced yields are difficult to objectively assess. Traditional methods like visual assessments and manual counts of cotton stands are commonly used to support a replanting decision. Typically, manual counts of skip size and frequency will provide more accurate assessments of the stand than visual assessments, but they are cumbersome to conduct and may not provide clear evidence that a replant is needed. Still, manual counts are popular among cotton farmers and the scientific community. Skip counts generated with the help of unmanned aerial vehicles (UAV) are less popular among cotton growers but provide more coverage and a larger sampling size across a given field. Therefore, UAVs have the potential to overcome the limitations associated with traditional methods. The motivation behind this study is to inform readers if manual methods can still be used for accurate decision-making regarding the replanting decision. More specifically, we study the interchangeability, or agreement, between a manual and a UAV-based method using Bland-Altman plots. Each method quantified skips greater than or equal to 0.91 m at different sampling sizes. Treatment plots varied in their stand counts, skip size, and skip frequency. Agreement between both methods was only found in the lowest stand treatment, where skips of large sizes were predominant. Conversely, methods disagreed in the higher stand where skips greater than or equal to 0.91 m were scarce. Keywords: Agriculture, Altman, Bland, Drone, Gaps, Precision, Remote, Sensing, UAS.

ANALYSIS OF THE FEATURES OF THE USE UNMANNED AERIAL VEHICLES BY THE ARMED FORCES OF THE RUSSIAN FEDERATION DURING A FULL-SCALE ARMED INVASION

The use of unmanned aerial vehicles allows the countries that use them to significantly reduce the loss of manpower and equipment during the combat mission and at the same time significantly increase the effectiveness of the use of high-precision and conventional means of destruction. The greatest experience in the use of unmanned aerial vehicles was acquired by countries that are actually advanced in terms of military technology (in particular, the USA, Israel, Turkey, etc.), which took an active part in armed conflicts in the Middle East, the North Caucasus, etc. In addition, in modern conditions, the threat of uncontrolled spread of the use of unmanned aerial vehicles of a light class, which can be used for the purpose of carrying out terrorist acts on important state and military facilities, is growing. Unmanned aerial vehicles have become so important to success on the battlefield that they are sometimes used by the military to destroy enemy drones. In addition, it is with the help of unmanned aerial vehicles that one side receives the coordinates of military targets and command posts of the opposite side, which are subsequently destroyed by accurate artillery strikes. In the article, based on the analysis of modern wars and armed conflicts, combat experience and features of the use of unmanned aerial vehicles of the armed forces of the russian federation, an analysis of unmanned aerial vehicles for typical tasks, in particular, conducting reconnaissance, adjusting fire, striking and electronic warfare, was carried out. In particular, the conducted analysis indicates a tendency to increase the scale of use of unmanned aerial vehicles by the armed forces of the russian federation in conditions of a full-scale armed conflict (not excluded due to the end of stocks of high-precision missiles), in contrast to the experience of the combat use of individual unmanned aerial vehicles in the East of the country and the expansion of the range of tasks.

İnsansız Hava Araçlarının Orman Yolu Projelerinde Kullanımı

Road networks are accepted as a criterion showing the level of development of countries. Undoubtedly, the role of highways in facilitating human life is quite important. However, road routes involve high cost land surveying studies that can pass through areas with various land use types and cover.For forest road routes to be built in forest areas, points representing the land surface can be obtained by various measurement methods (remote sensing, photogrammetry and terrestrial measurement techniques). Depending on the land structure and cover, difficulties are encountered in the determination of spatial points with terrestrial measurement techniques. In this study, as an alternative to the terrestrial measurement technique, 341 m long forest road excavation and filling calculations were carried out with the help of Unmanned Aerial Vehicle (UAV) photogrammetry. Photo pairs taken from different heights (50 m, 75 m and 100 m) with real-time kinematics (RTK) GPS UAV were processed with Agisoft to produce a point cloud. The point cloud data obtained by digital photogrammetry and land measurement methods were carried out in NetCAD environment for the excavation and filling calculations for the same road route. Between the two methods, in the 50 m, 75 m and 100 m measurements of the UAV obtained by ground measurement; In the calculation of the UAV 50m measurement amount, 0.27% in the total excavation amount and 1.08% difference in the total filling amount, 2.51% in the total excavation amount and 5.22% in the total filling amount in the calculation of the UAV 75 m measurement amount, and the total difference in the UAV 100m measurement amount in the calculation of the UAV 50m measurement amount. A difference of 3.13% in the amount of excavation and 2.53% in the total amount of filling was determined. These results show that UAV photogrammetry is very effective in forest road projects and in calculating the amount of earthwork volume in mountainous terrain.

A Robust Faster R-CNN Model with Feature Enhancement for Rust Detection of Transmission Line Fitting.

Rust of transmission line fittings is a major hidden risk to transmission safety. Since the fittings located at high altitude are inconvenient to detect and maintain, machine vision techniques have been introduced to realize the intelligent rust detection with the help of unmanned aerial vehicles (UAV). Due to the small size of fittings and disturbance of complex environmental background, however, there are often cases of missing detection and false detection. To improve the detection reliability and robustness, this paper proposes a new robust Faster R-CNN model with feature enhancement mechanism for the rust detection of transmission line fitting. Different from current methods that improve feature representation in front end, this paper adopts an idea of back-end feature enhancement. First, the residual network ResNet-101 is introduced as the backbone network to extract rich discriminative information from the UAV images. Second, a new feature enhancement mechanism is added after the region of interest (ROI) pooling layer. Through calculating the similarity between each region proposal and the others, the feature weights of the region proposals containing target object can be enhanced via the overlaying of the object’s representation. The weight of the disturbance terms can then be relatively reduced. Empirical evaluation is conducted on some real-world UAV monitoring images. The comparative results demonstrate the effectiveness of the proposed model in terms of detection precision and recall rate, with the average precision of rust detection 97.07%, indicating that the proposed method can provide an reliable and robust solution for the rust detection.

A Privacy-Preserved Internet-of-Medical-Things Scheme for Eradication and Control of Dengue Using UAV.

Dengue is a mosquito-borne viral infection, found in tropical and sub-tropical climates worldwide, mostly in urban and semi-urban areas. Countries like Pakistan receive heavy rains annually resulting in floods in urban cities due to poor drainage systems. Currently, different cities of Pakistan are at high risk of dengue outbreaks, as multiple dengue cases have been reported due to poor flood control and drainage systems. After heavy rain in urban areas, mosquitoes are provided with a favorable environment for their breeding and transmission through stagnant water due to poor maintenance of the drainage system. The history of the dengue virus in Pakistan shows that there is a closed relationship between dengue outbreaks and a rainfall. There is no specific treatment for dengue; however, the outbreak can be controlled through internet of medical things (IoMT). In this paper, we propose a novel privacy-preserved IoMT model to control dengue virus outbreaks by tracking dengue virus-infected patients based on bedding location extracted using call data record analysis (CDRA). Once the bedding location of the patient is identified, then the actual infected spot can be easily located by using geographic information system mapping. Once the targeted spots are identified, then it is very easy to eliminate the dengue by spraying the affected areas with the help of unmanned aerial vehicles (UAVs). The proposed model identifies the targeted spots up to 100%, based on the bedding location of the patient using CDRA.

Application of UAV and CSPI Matrix for Roof Inspection at Dewan Sultan Ibrahim and Dewan Tunku Mahkota Ismail UTHM

Roof inspections are simply inspections to determine the roof integrity, durability, and long life of roofs before they need to be replaced. Besides, the hazards presented by these features bring problems to roof inspectors as they face difficulty in performing rooftop inspection due to its high roof structure. The purpose of this study is to access defective buildings with visual inspection with the help of Unmanned Aerial Vehicle (UAV), to classify roof building conditions using the CSP1 Matrix as a method of assessment and ultimately acquire the results of the roof condition between the two main chambers of Universiti Tun Hussein Onn Malaysia. The two main chambers were elected in the UTHM area namely the Sultan Ibrahim Hall (DSI) and Tungku Mahkota Ismail Hall (DTMI). The main equipment used is UAV while Condition Survey Protocol 1(CSP1) Matrix is a method for building inspections to analyze the assessment of building roof conditions and to identify the significance of defective buildings detected for each main hall. From the analysis, there are 20 and 21 defects for DSI and DTMI that have been recorded, respectively. The overall roof condition is calculated where for DSI is 2.3 (Green) while DTMI is 4.29 (Green) which indicates that the state of the building for DSI and DTMI is in a fair condition (score 1-4). The total defects recorded in these studies for both halls are 41 defects.

Оценка структуры и состояния молодняков с использованием беспилотных летательных аппаратов и наземным методом

The article presents the data on the composition and condition of mixed young forests, obtained using unmanned aerial vehicles and the classical land technique. The plotting of the forest area was carried out by quadcopters. The land technique was used to assess the composition and condition of young stands, undergrowth and live ground cover on10 m2 circular plots. At each object, 48 discount areas were laid. The objects of study are young stands of natural and artificial origin. It was established that young growths of natural origin were formed in the 7 hectares cutover plots in 2006. They include pine, spruce, birch, aspen and alder. Spruce plantations were created in 2012 on an area of 12 hectares. It is shown that the understories and small undergrowth are not visible from a quadcopter, while the classical method gives the detailed characteristics. Additional characteristics of young forests obtained with the help of unmanned aerial vehicles are given. It is shown that the results obtained by the two methods are consistent, the error in the main characteristics does not exceed 10%. The combination of the two methods gives more complete information on the forest area. However, each of the methods used has its own advantages and disadvantages.

ПІДВИЩЕННЯ ШВИДКОСТІ АНАЛІЗУ ЗОБРАЖЕНЬ, ОТРИМАНИХ ІЗ БЕЗПІЛОТНОГО ЛІТАЛЬНОГО АПАРАТУ

Carrying out long-term search and rescue missions, intelligence, surveillance and reconnaissance, which are carried out with the help of unmanned aerial vehicles (UAVs) overload the operator and reduce the effectiveness of solving the assigned tasks, up to the point of making their implementation impossible. The paper proposes the concept of increasing the speed of the human-machine system based on information obtained from images transmitted in real time by video cameras installed on a platform moving relative to the UAV, by mean of the intelligent controlsystem of this platform.Thus, the image from the main video camera with a wide viewing angle is divided into rectangular sections (zones), which size is determined by the viewing angle (zoom) necessary for the operator to make the final decision. The software system of the lower level, evaluating the video frame, determines and marks the areas in which the object of interest may be present. Increasing the focal length and focusing (i.e., zooming the image), as well as positioning the main camera is carried out for the area where the probability of the presence of the candidate object is the greatest. In another variant, a separate spot camera with a reduced and fixed field of view is aimed at the yaw and pitch angles, which requires that this camera be directly suspended on a gyro-stabilized platform, where a block of other sensors is installed, including the main video camera.An example of modeling the electric drive of a spot camera by the yaw angle is given and further steps are determined for the development of subsystems of three levels: software (recognition), hardware (scaling and positioning), human-machine (coordination of information flows). To improve the dynamic characteristics in comparison with the basic proportional-integral laws, it is proposed to use quasi-optimal algorithms for regulating electric drives.

Investigation of 3D models acquired with UAV oblique images

The concept of oblique image acquisition entered the literature long after the overhead photogrammetric acquisition techniques. The oblique image acquisition technique is applied to model the edge surfaces of buildings that cannot be obtained with vertical (nadir) image acquisition and eliminate the problems that arise in the orthorectification of high-rise buildings in urban areas. Oblique image acquisition by Unmanned Aerial Vehicles (UAV) independent of aerial photogrammetry is considered possible with unique flight plans. How convenient oblique image acquisition with the help of UAVs is and how it affects the final product is a popular topic studied by researchers. In this study, oblique image acquisition was performed using a rotary-wing UAV (Parrot ANAFI) whose camera can move 180°. With the help of the 3D models obtained, the building was drawn in vector and evaluated to scale. As a result, it has been understood that almost all structural deficiencies in the final products can be eliminated by oblique images. However, it has been revealed that there is still a need for other methods for structures that do not have patterns, such as flat walls.

A Novel 3D Node Deployment Inspired by Dusty Plasma Crystallization in UAV-Assisted Wireless Sensor Network Applications.

With the rapid progress of hardware and software, a wireless sensor network has been widely used in many applications in various fields. However, most discussions for the WSN node deployment mainly concentrated on the two-dimensional plane. In such a case, some large scale applications, such as information detection in deep space or deep sea, will require a good three dimensional (3D) sensor deployment scenario and also attract most scientists’ interests. Excellent deployment algorithms enable sensors to be quickly deployed in designated areas with the help of unmanned aerial vehicles (UAVs). In this paper, for the first time, we present a three dimensional network deployment algorithm inspired by physical dusty plasma crystallization theory in large-scale WSN applications. Four kinds of performance evaluation methods in 3D space, such as the moving distance, the spatial distribution diversion, system coverage rate, and the system utilization are introduced and have been carefully tested.Furthermore, in order to improve the performance of the final deployment, we integrated the system coverage rate and the system utilization to analyze the parameter effects of the Debye length and the node sensing radius. This criterion attempts to find the optimal sensing radius with a fixed Debye length to maximize the sensing range of the sensor network while reducing the system redundancy. The results suggest that our 3D algorithm can quickly complete an overall 3D network deployment and then dynamically adjust parameters to achieve a better distribution. In practical applications, engineers may choose appropriate parameters based on the sensor’s hardware capabilities to achieve a better 3D sensor network deployment. It may be significantly used in some large-scale 3D WSN applications in the near future.

Generalized Net Model of Forest Zone Monitoring by UAVs

The paper presents a generalized net (GN) model of the process of terrain observation with the help of unmanned aerial vehicles (UAVs) for the prevention and rapid detection of wildfires. Using a GN, the process of monitoring a zone (through a UAV, which is further called a reconnaissance drone) and the localization of forest fires is described. For a more indepth study of the terrain, the reconnaissance drone needs to coordinate with a second UAV, called a specialized drone, so that video and sensory information is provided to the supervising fire command operational center. The proposed GN model was developed to assist in the decision-making process related to the coordination of the operation of both UAVs under dynamically changing terrain circumstances, such as those related to preventing or quickly containing wildfires. It describes the stages (transitions), logical determinants (transition predicate matrices), and directions of information flow (token characteristics) within the process of localization of fires using the pair of reconnaissance and specialized drones.