• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.1
• /
• pp.17-25
• /
• 2023

As the range of use of urban unmanned aerial vehicles (UAV) expands, it is necessary to operate UAVs efficiently because of its limited battery capacity. For this, it is required to find the optimal flight profile with various simulations. Therefore, it is important to predict the power and energy consumption of the UAV battery. In this paper, we analyzed the relationship between the speed and acceleration of the UAV and power consumption during the flight. Then, we derived a linear model, which is easily utilized. In addition, we also derived an accurate power consumption model based on deep neural network learning. To find the efficient model, we used learning data as 1) the GPS 3-axis velocity and acceleration data, 2) the IMU 3-axis velocity only, and 3) the IMU 3-axis velocity and acceleration data. The final model shows 5.86% error rate for power consumption and 1.50% error rate for the cumulative energy consumption.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.4
• /
• pp.1392-1413
• /
• 2022

In order to meet the rapid development of the unmanned aerial vehicle (UAV) communication needs, cooperative spectrum sensing (CSS) helps to identify unused spectrum for the primary users (PU). However, multi-UAV mode (MUM) requires the large communication resource in a cognitive UAV network, resulting in a severe decline of spectrum efficiency (SE) and energy efficiency (EE) and increase of energy consumption (EC). On this account, we extend the traditional 2D spectrum space to 3D spectrum space for the UAV network scenario and enable UAVs to proceed with spectrum sensing behaviors in this paper, and propose a novel multi-slot mode (MSM), in which the sensing slot is divided into multiple mini-slots within a UAV. Then, the CSS process is developed into a composite hypothesis testing problem. Furthermore, to improve SE and EE and reduce EC, we use the sequential detection to make a global decision about the PU channel status. Based on this, we also consider a truncation scenario of the sequential detection under the sensing delay constraint, and further derive a closed-form performance expression, in terms of the CSS performance and cooperative efficiency. At last, the simulation results verify that the performance and cooperative efficiency of MSM outperforms that of the traditional MUM in a low EC.

• Journal of Korea Water Resources Association
• /
• v.51 no.4
• /
• pp.335-346
• /
• 2018

A vast amount of riverine spatial dataset have recently become available, which include hydrodynamic and morphological survey data by advanced instrumentations such as ADCP (Acoustic Doppler Current Profiler), transect measurements obtained through building various river basic plans, riverine environmental and ecological data, optical images using UAVs, river facilities like multi-purposed weir and hydrophilic sectors. In this regard, a standardized data model has been subsequently required in order to efficiently store, manage, and share riverine spatial dataset. Given that riverine spatial dataset such as river facility, transect measurement, time-varying observed data should be synthetically managed along specified river network, conventional data model showed a tendency to maintain them individually in a form of separate layer corresponding to each theme, which can miss their spatial relationship, thereby resulting in inefficiency to derive synthetic information. Moreover, the data model had to be significantly modified to ingest newly produced data and hampered efficient searches for specific conditions. To avoid such drawbacks for layer-based data model, this research proposed a relational data model in conjunction with river network which could be a backbone to relate additional spatial dataset such as flowline, river facility, transect measurement and surveyed dataset. The new data model contains flexibility to minimize changes of its structure when it deals with any multi-dimensional river data, and assigned reach code for multiple river segments delineated from a river. To realize the newly developed data model, Seom river was applied, where geographic informations related with national and local rivers are available.

• Journal of Digital Convergence
• /
• v.15 no.8
• /
• pp.195-202
• /
• 2017

Unmanned Aerial Vehicles (UAV) have mostly been used for military purposes but with the progress in ICT and reduced manufacturing costs, they are increasingly used for various private services. UAVs are expected to carry out autonomous flying in the future. In order to carry out complex tasks, swarm flights are essential. Although the swarm flights has been researched a lot due to its different network and infrastructure from the existing UAV system, There are still not enough study on security threats and requirements for the secure swarm flights. In this paper, to solve these problems, UAV autonomous flight technology is defined based on US Army Corps of Engineers (USACE) and Air Force Research Laboratory (AFRL), and swarm flights and security threat about it are classified. And then we defined and compared security requirements according to security threats of each swarm flights so as to contribute to the development of secure UAC swarm flights in the future.

• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.3
• /
• pp.23-29
• /
• 2019

Conventional crack detection methods have a problem of consuming a lot of labor, time and cost. To solve these problems, an automatic detection system is needed to detect cracks in images obtained by using vehicles or UAVs(unmanned aerial vehicles). In this paper, we have studied road crack detection with unmanned aerial photographs. Aerial images are generated through preprocessing and labeling to generate morphological information data sets of cracks. The generated data set was applied to the mask R-CNN model to obtain a new model in which various crack information was learned. Experimental results show that the cracks in the proposed aerial image were detected with an accuracy of 73.5% and some of them were predicted in a certain type of crack region.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.381-392
• /
• 2021

In this study, we perform deep learning-based object detection analysis on eight types of buildings defined by the digital map topography standard code, leveraging images taken with UAV (Unmanned Aerial Vehicle). Image labeling was done for 509 images taken by UAVs and the YOLO (You Only Look Once) v5 model was applied to proceed with learning and inference. For experiments and analysis, data were analyzed by applying an open source-based analysis platform and algorithm, and as a result of the analysis, building objects were detected with a prediction probability of 88% to 98%. In addition, the learning method and model construction method necessary for the high accuracy of building object detection in the process of constructing and repetitive learning of training data were analyzed, and a method of applying the learned model to other images was sought. Through this study, a model in which high-efficiency deep neural networks and spatial information data are fused will be proposed, and the fusion of spatial information data and deep learning technology will provide a lot of help in improving the efficiency, analysis and prediction of spatial information data construction in the future.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.351-363
• /
• 2023

Visual structural inspections are an inseparable part of post-earthquake damage assessments. With unmanned aerial vehicles (UAVs) establishing a new frontier in visual inspections, there are major computational challenges in processing the collected massive amounts of high-resolution visual data. We propose twin deep learning models that can provide accurate high-resolution structural components and damage segmentation masks efficiently. The traditional approach to cope with high memory computational demands is to either uniformly downsample the raw images at the price of losing fine local details or cropping smaller parts of the images leading to a loss of global contextual information. Therefore, our twin models comprising Trainable Resizing for high-resolution Segmentation Network (TRS-Net) and DmgFormer approaches the global and local semantics from different perspectives. TRS-Net is a compound, high-resolution segmentation architecture equipped with learnable downsampler and upsampler modules to minimize information loss for optimal performance and efficiency. DmgFormer utilizes a transformer backbone and a convolutional decoder head with skip connections on a grid of crops aiming for high precision learning without downsizing. An augmented inference technique is used to boost performance further and reduce the possible loss of context due to grid cropping. Comprehensive experiments have been performed on the 3D physics-based graphics models (PBGMs) synthetic environments in the QuakeCity dataset. The proposed framework is evaluated using several metrics on three segmentation tasks: component type, component damage state, and global damage (crack, rebar, spalling). The models were developed as part of the 2^nd International Competition for Structural Health Monitoring.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.34 no.3
• /
• pp.283-290
• /
• 2016

Even though existing methods for orthophoto production in traditional photogrammetry are effective in large areas, they are inefficient when dealing with change detection of geometric features and image production for short time periods in small areas. In recent years, the UAV (Unmanned Aerial Vehicle), equipped with various sensors, is rapidly developing and has been implemented in various ways throughout the geospatial information field. The data and imagery of specific areas can be quickly acquired by UAVs at low costs and with frequent updates. Furthermore, the redundancy of geospatial information data can be minimized in the UAV-based orthophoto generation. In this paper, the orthophoto and DEM (Digital Elevation Model) are generated using a standard low-end UAV in small sloped areas which have a rather low accuracy compared to flat areas. The RMSE of the check points is σ_H = ±0.12 m on a horizontal plane and σ_V = ±0.09 m on a vertical plane. As a result, the maximum and mean RMSE are in accordance with the working rule agreement for the airborne laser scanning surveying of the NGII (National Geographic Information Institute) on a 1/500 scale digital map. Through this study, we verify the possibilities of the orthophoto generation in small slope areas using general-purpose low specification UAV rather than a high cost surveying UAV.