• Journal of Multimedia Information System
• /
• v.4 no.4
• /
• pp.195-204
• /
• 2017

Mobile robots are used for years as a valuable research and educational tool in form of available open-platform designs and Do-It-Yourself kits. Rapid development and costs reduction of Unmanned Air Vehicles (UAV) and ground based mobile robots in recent years allowed researchers to utilize them as an affordable research platform. Despite of recent developments in the area of ground and airborne robotics, only few examples of Unmanned Surface Vehicle (USV) platforms targeted for research purposes can be found. Aim of this paper is to present the development of open-design USV drone with integrated multi-level control hardware architecture. Proposed catamaran - type water surface drone enables direct control over wireless radio link, separate development of algorithms for optimal propulsion control, navigation and communication with the ground-based control station. Whole design is highly modular, where each component can be replaced or modified according to desired task, payload or environmental conditions. Developed USV is planned to be utilized as a part of the system for detection and identification of marine and lake waste. Cameras mounted to the USV would record sea or lake surfaces, and recorded video sequences and images would be processed by state-of-the-art computer vision and machine learning algorithms in order to identify and classify marine and lake waste.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.3
• /
• pp.56-62
• /
• 2017

As the need for 3D spatial information increases, many local governments and related industries are establishing map-based 3D spatial information services and offering them to users. In these services, positional accuracy is one of the most important factors determining their applicability to specific tasks. This study studied the location correction method between indoor and outdoor 3D spatial information through the construction of modeling data on a BIM/GIS platform. First, we selected the sites and processed the BIM/GIS data construction with 3 steps. When connecting the BIM model including indoor spatial data and 3D texturing model based on ortho images, mismatches occurred, so we proposed a location correction method. Using the conversion algorithm, the relative coordinate-based BIM data were converted to the absolute positions and then relocated by means of the texturing data on the BIM/GIS platform.

• International Journal of Aeronautical and Space Sciences
• /
• v.17 no.2
• /
• pp.232-239
• /
• 2016

Recently, in order to increase the efficiency and mission success rate of UAVs (Unmanned Aerial Vehicles), the necessity for formation flights is increased. In general, GPS (Global Positioning System) is used to obtain the relative position of leader with respect to follower in formation flight. However, it can't be utilized in environment where GPS jamming may occur or communication is impossible. Therefore, in this study, monocular vision is used for measuring relative position. General PC-based vision processing systems has larger size than embedded systems and is hard to install on small vehicles. Thus FPGA-based processing board is used to make our system small and compact. The processing system is divided into two blocks, PL(Programmable Logic) and PS(Processing system). PL is consisted of many parallel logic arrays and it can handle large amount of data fast, and it is designed in hardware-wise. PS is consisted of conventional processing unit like ARM processor in hardware-wise and sequential processing algorithm is installed on it. Consequentially HW/SW co-designed FPGA system is used for processing input images and measuring a relative 3D position of the leader, and this system showed RMSE accuracy of 0.42 cm ~ 0.51 cm.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.1
• /
• pp.33-38
• /
• 2020

This paper proposes a technique for counting construction materials by analyzing an image acquired by a Drone. The proposed technique use drone log which includes drone and camera information, RCNN for predicting construction material type, dummy area and Photogrammetry for counting the number of construction material. The existing research has large error ranges for predicting construction material detection and material dummy area, because of a lack of training data. To reduce the error ranges and improve prediction stability, this paper increases the training data with a method of data augmentation, but only uses rotated training data for data augmentation to prevent overfitting of the training model. For the quantity calculation, we use a drone log containing drones and camera information such as Yaw and FOV, RCNN model to find the pile of building materials in the image and to predict the type. And we synthesize all the information and apply it to the formula suggested in the paper to calculate the actual quantity of material pile. The superiority of the proposed method is demonstrated through experiments.

• Journal of Advanced Navigation Technology
• /
• v.22 no.4
• /
• pp.295-301
• /
• 2018

Recently, GPS(Global Positioning System) array antenna technology is generally used and widely adopted as a national infrastructure structure and aero-vehicles for protection the GPS signal reception. Until now, the 2-dimensional planar array is universally used for its applications in the array antenna signal processing, however relatively higher altitude air vehicles such as UAV experiences additional null zones induced by low altitude GPS interferences which is located in a symmetry zone of antenna horizontal plane and this could make the receiving antenna pattern coverage reduction. In this paper, we improved 20% of the beam pattern receiving performance and 13 dB correlation value improvement by eliminating the interference mirror images.

• Journal of Convergence for Information Technology
• /
• v.11 no.1
• /
• pp.118-127
• /
• 2021

In spite of various safety measures, coastal safety accidents continue to occur, so this study focused on using drones as countermeasures. Municipalities that already have coasts have begun operating unmanned multicopters for coastal safety management. In particular, by connecting an unmanned multi-copter to the currently applied smart city safety net system, it is possible to transmit real-time images of the scene in case of emergency in the coastal area to the local government safety information center. It is also expected to contribute significantly to strengthening safety management in coastal waters through a more rapid response to safety accidents. Therefore, in this paper, we propose the use of drones as an alternative to the limitations of the domestic coastal safety system by investigating the state of coastal safety accidents and analyzing the state of domestic coastal safety systems. In addition, it is expected to be a key breakthrough in the coastal area safety system by proposing a model linking the Korean K-Drone system.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.1
• /
• pp.63-73
• /
• 2021

This paper presents a algorithm for automatic target recognition robust to the influence of the flame in order to track the target by EOTS(Electro-Optical Targeting System) equipped on UAV(Unmanned Aerial Vehicle) when there is aerial target or marine target with flame at the same time. The proposed method converts infrared images of targets and flames into a gradient vector field, and applies each gradient magnitude to a polynomial curve fitting technique to extract polynomial coefficients, and learns them in a shallow neural network model to automatically recognize targets and flames. The performance of the proposed technique was confirmed by utilizing the various infrared image database of the target and flame. Using this algorithm, it can be applied to areas where collision avoidance, forest fire detection, automatic detection and recognition of targets in the air and sea during automatic flight of unmanned aircraft.

• The Journal of Engineering Geology
• /
• v.33 no.1
• /
• pp.27-37
• /
• 2023

Assessing landcreep requires long-term monitoring, because cracks and steps develop over long periods. However, long-term monitoring using wire extensometers and inclinometers is inefficient in terms of cost and management. Therefore, this study selected an area with active landcreep and evaluated the feasibility of monitoring it using imagesing from terrestrial LiDAR and drones. The results were compared with minute-by-minute data measured in the field using a wire extensometer. The comparison identified subtle differences in the accuracy of the two sets of results, but monitoring using terrestrial LiDAR and drones did generate values similar to the wire extensometer. This demonstrates the potential of basic monitoring using terrestrial LiDAR and drones, although minute-byminute field measurements are required for analyzing and predicting landcreep. In the future, precise monitoring using images will be feasible after verifying image analysis at various levels and accumulating data considering climate and accuracy.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.182-189
• /
• 2023

Depth estimation is a key technology in 3D map generation for autonomous driving of vehicles, robots, and drones. The existing sensor-based method has high accuracy but is expensive and has low resolution, while the camera-based method is more affordable with higher resolution. In this study, we propose self-attention-based unsupervised monocular depth estimation for UAV camera system. Self-Attention operation is applied to the network to improve the global feature extraction performance. In addition, we reduce the weight size of the self-attention operation for a low computational amount. The estimated depth and camera pose are transformed into point cloud. The point cloud is mapped into 3D map using the occupancy grid of Octree structure. The proposed network is evaluated using synthesized images and depth sequences from the Mid-Air dataset. Our network demonstrates a 7.69% reduction in error compared to prior studies.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.16-16
• /
• 2022

영상유속계는 영상을 이용한 비접촉식 유속계로 하천과 같은 넓은 범위의 유속 및 유량을 간편하게 측정할 수 있다는 장점이 있어 현재 국내외에서 영상유속계의 실용화 연구가 수행되고 있다. 특히 유속 및 유량을 측정하기 위해 카메라 외에 별도의 측정 장비가 필요없기 때문에 드론에 장착하여 표면유속을 측정하는 연구 또한 활발히 이루어지고 있다. 기존 드론 영상을 이용한 표면유속 측정 연구에서는 드론을 측정하고자 하는 하천 영역 위에서 정지하여 영상을 촬영하여 표면유속을 측정하고 있다. 이때 한 화면에 하폭이 다 담기지 않는 넓은 하천의 경우 촬영 위치를 옮겨서 다시 영상을 촬영하거나 하폭이 담길 때까지 비행 고도를 높여 촬영하고 있다. 하지만 촬영 위치를 옮겨 촬영하는 방식의 경우 넓은 하천을 다 담기 위해 여러 번의 촬영을 하고 이를 정합하는 과정이 필요하다는 단점이 있으며 비행 고도를 높여 촬영하는 방식의 경우 촬영 품질 저하로 인해 측정한 유속의 불확도가 크게 산정된다는 단점이 있다. 이에 본 연구에서는 드론을 이동하며 촬영한 연속적인 영상을 이용하여 하천의 표면유속을 측정하는 방법에 대한 연구를 수행하였다. 하천을 가로질러 비행하며 촬영한 드론 이동영상을 활용하면 폭이 넓은 하천의 경우도 간편하게 유속 분포를 측정할 수 있다. 이동영상을 이용하여 유속을 측정하기 위해서는 연속된 이동영상 내에서 지표면의 공통된 특징점을 찾아 흔들림 보정 알고리즘을 적용하여 유속을 산정하는 방법과 드론의 이동 속도를 이용하여 영상의 수표면 이동속도와 벡터연산을 적용하는 두가지 방법을 사용할 수 있다. 이 두가지 방법 중 영상 분석에 필요한 전처리 과정이 적고 지표면의 고정점이 필요 없는 드론의 이동속도를 이용한 벡터 연산을 적용하는 방법을 실제 흐름에 적용하였다. 측정한 수표면의 유속을 전자파표면유속계로 측정한 유속과 비교한 결과 평균 5 % 이내의 차이를 보이는 것을 확인하였다. 향후 다양한 흐름 조건과 드론의 비행속도를 변경하여 측정하는 등의 유속 측정 적용성을 검토하는 연구가 수행된다면 하폭이 넓은 하천 등 다양한 조건에서 드론 영상을 이용한 유속 측정이 가능할 것으로 기대한다.