• 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.

• Korean Journal of Remote Sensing
• /
• v.38 no.2
• /
• pp.199-213
• /
• 2022

The unsupervised domain adaptation can solve the impractical issue of repeatedly collecting high-quality training data every year for annual crop classification. This study evaluates the applicability of deep learning-based unsupervised domain adaptation models for crop classification. Three unsupervised domain adaptation models including a deep adaptation network (DAN), a deep reconstruction-classification network, and a domain adversarial neural network (DANN) are quantitatively compared via a crop classification experiment using unmanned aerial vehicle images in Hapcheon-gun and Changnyeong-gun, the major garlic and onion cultivation areas in Korea. As source baseline and target baseline models, convolutional neural networks (CNNs) are additionally applied to evaluate the classification performance of the unsupervised domain adaptation models. The three unsupervised domain adaptation models outperformed the source baseline CNN, but the different classification performances were observed depending on the degree of inconsistency between data distributions in source and target images. The classification accuracy of DAN was higher than that of the other two models when the inconsistency between source and target images was low, whereas DANN has the best classification performance when the inconsistency between source and target images was high. Therefore, the extent to which data distributions of the source and target images match should be considered to select the best unsupervised domain adaptation model to generate reliable classification results.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.1
• /
• pp.25-33
• /
• 2020

Multipath routing protocols with unmanned aerial vehicles have been proposed to improve reliability in tactical ad hoc networks. Most of existing studies tend to establish the paths with multiple metrics. However, these approaches suffer from link loss and congestion problems according to the network condition because they apply same metric for both ground and air path or employ the simple weight value to combine multiple metrics. To overcome this limitation, in this study, we propose new routing metrics for path over unmanned aerial vehicles and use the multi-criteria decision making (MCDM) method to determine the weight factors between multiple metrics. For the case studies, we extend the ad-hoc on-demand distance vector protocol and propose a strategy for modifying the route discovery and route recovery procedure. The simulation results show that the proposed mechanism is able to achieve high end-to-end reliability and low end-to-end delay in tactical ad hoc networks.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.17 no.4
• /
• pp.436-447
• /
• 2014

The major elements of avionics system architecture are requirements, Real Time Operating System, message communication, memory, and data format etc. Herein describes a state-of-the-art development trend for the avionics system architecture, system requirements and data bus among the major elements of avionics system. While, domestic technology has been tried to Integrated Modular Avionics(IMA) system based on the Avionics Full Duplex Switched Ethernet(AFDX) technology during Light Attack Helicopter(LAH) project in Korea, but not yet proved as the product case in Full Scale Development Phase. The avionics system architecture considering the domestic inexperience of the IMA system architecture are suggested for the Next-generation Corps Unmanned Aircraft System.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.47 no.5
• /
• pp.358-363
• /
• 2019

If the EOIR equipment mounted on an unmanned aircraft transmits images and receives commands through a data link, there may be delays in data transmission depending on the transmission path of the data and the conditions of the ground equipment or wireless network. This increases the possibility of initial target LOCK-ON failure due to the difference between the time when the received image is viewed and the time when the image is taken. Therefore, this paper proposed a way to use frame indexes to synchronize with images, and to increase the success of target tracking by adding frame indexes to commands from the ground station.

• Telecommunications review
• /
• v.24 no.4
• /
• pp.468-480
• /
• 2014

The current-generation avionics systems are based on a federated architecture, where an electronic device runs a single software module or application that collaborates with other devices through a network. This architecture makes the internal system architecture very complicate, and gives rise to issues of Size, Weight, and Power (SWaP). In this paper, we show that the partitioning defined by ARINC 653 can efficiently deal with the SWaP issues on small unmanned aerial vehicles, where the SWaP issues are extremely severe. We especially install the integrated mission system on real hexacopter and quadcopter and perform successful flight tests. The presented software technology for integrated mission system and software consolidation methodology can provide a valuable reference for other SWaP sensitive real-time systems.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.342-342
• /
• 2020

최근 소형 무인비행장치(UAV; unmaned aerial vehicle)인 드론을 이용한 신산업 육성 및 지원에 관한 관심도가 높아지고 있다. 국외에서는 이미 드론을 이용한 농업관리와 물류배송, 공공부문 모니터링 등 다양한 산업 분야의 드론 이용을 적극 장려하고 있다. 드론 이용에 관한 관심도가 높아짐에 따라 국내외적으로 드론 응용 관련 기술 개발과 연구가 활발하게 진행되고 있지만, 국내에서는 환경모니터링과 시설물 점검 등 일부 제한적으로 활용되고 있다. 국내에서는 2024년까지 드론 응용서비스로 확장되는 산업 변화에 대응, DNA(Data, Network, AI) 기술을 접목한 새로운 개방형 플랫폼 구축을 목표로 기술개발 및 산업 육성을 촉진하고 있다. 이러한 국내 기술 개발 방향에 맞추어 드론과 첨단기술을 이용한 하천조사와 관련해 드론을 연계한 하천관리 플랫폼 개발의 필요성이 높아지고 있다. 본 연구에서는 드론 기반 하천조사 및 모니터링 수행을 위한 하천관리 운영플랫폼 개발을 목표로 국내외 요소기술을 분석하고 기술수준을 조사했다. 특히, 드론 기반 하천관리에 필요한 임무를 영역별로 분리해 요소기술 기반의 플랫폼 서비스를 정의하고 하천관리 부문 개방형 플랫폼 구축을 위한 시스템 구성 및 운영에 필요한 요소기술을 선정했다. 최종적으로 선정된 플랫폼 서비스와 요소기술을 기초로 시스템 적용방안을 검토하고 하천관리 운영플랫폼 구축을 위한 시스템 아키텍처를 정의 및 설계했다.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.784-791
• /
• 2022

Tack coat is a thin layer of asphalt between the existing pavement and asphalt overlay. During construction, insufficient tack coat layering can later cause surface defects such as slippage, shoving, and rutting. This paper proposed a method for tack coat inspection improvement using an unmanned aerial vehicle (UAV) and deep learning neural network for automatic non-uniform assessment of the applied tack coat area. In this method, the drone-captured images are exploited for assessment using a combination of Mask R-CNN and Grey Level Co-occurrence Matrix (GLCM). Mask R-CNN is utilized to detect the tack coat region and segment the region of interest from the surroundings. GLCM is used to analyze the texture of the segmented region and measure the uniformity and non-uniformity of the tack coat on the existing pavements. The results of the field experiment showed both the intersection over union of Mask R-CNN and the non-uniformity measured by GLCM were promising with respect to their accuracy. The proposed method is automatic and cost-efficient, which would be of value to state Departments of Transportation for better management of their work in pavement construction and rehabilitation.

• Journal of Animal Science and Technology
• /
• v.65 no.6
• /
• pp.1254-1269
• /
• 2023

This study aims to predict the change in corn share according to the grazing of 20 gestational sows in a mature corn field by taking images with a camera-equipped unmanned air vehicle (UAV). Deep learning based on convolutional neural networks (CNNs) has been verified for its performance in various areas. It has also demonstrated high recognition accuracy and detection time in agricultural applications such as pest and disease diagnosis and prediction. A large amount of data is required to train CNNs effectively. Still, since UAVs capture only a limited number of images, we propose a data augmentation method that can effectively increase data. And most occupancy prediction predicts occupancy by designing a CNN-based object detector for an image and counting the number of recognized objects or calculating the number of pixels occupied by an object. These methods require complex occupancy rate calculations; the accuracy depends on whether the object features of interest are visible in the image. However, in this study, CNN is not approached as a corn object detection and classification problem but as a function approximation and regression problem so that the occupancy rate of corn objects in an image can be represented as the CNN output. The proposed method effectively estimates occupancy for a limited number of cornfield photos, shows excellent prediction accuracy, and confirms the potential and scalability of deep learning.

• Smart Structures and Systems
• /
• v.33 no.4
• /
• pp.313-323
• /
• 2024

Deterioration of buildings is one of the biggest problems in modern society, and the importance of a safety diagnosis for old buildings is increasing. Therefore, most countries have legal maintenance and safety diagnosis regulations. However, the reliability of the existing safety diagnostic processes is reduced because they involve subjective judgments in the data collection. In addition, unstructured tasks increase rework rates, which are time-consuming and not cost-effective. Therefore, This paper proposed the method that can calculate the safety grade of deterioration automatically. For this, a DNN structure is generated by using existing precision inspection data and precision safety diagnostic data, and an objective building safety grade is calculated by applying status evaluation data obtained with a UAV, a laser scanner, and reverse engineering 3D models. This automated process is applied to 20 old buildings, taking about 40% less time than needed for a safety diagnosis from the existing manual operation based on the same building area. Subsequently, this study compares the resulting value for the safety grade with the already existing value to verify the accuracy of the grade calculation process, constructing the DNN with high accuracy at about 90%. This is expected to improve the reliability of aging buildings in the future, saving money and time compared to existing technologies, improving economic efficiency.