• 한국농림기상학회지
• /
• 제24권4호
• /
• pp.295-304
• /
• 2022

본 연구는 수수의 수확량 추정을 위해 무인기로 취득한 RGB 영상과 YOLOv5를 이용하여 수수 이삭 탐지 모델을 개발하였다. 이삭이 가장 잘 식별되는 9월 2일의 영상 중 512×512로 분할된 2000장을 이용하여 모델의 학습, 검증 및 테스트하였다. YOLOv5의 모델 중 가장 파라미터가 적은 YOLOv5s에서 mAP@50=0.845로 수수 이삭을 탐지할 수 있었다. 파라미터가 증가한 YOLOv5m에서는 mAP@50=0.844로 수수 이삭을 탐지할 수 있었다. 두 모델의 성능이 유사하나 YOLOv5s (4시간 35분)가 YOLOv5m (5시간 15분)보다 훈련시간이 더 빨라 YOLOv5s가 수수 이삭 탐지에 효율적이라고 판단된다. 개발된 모델을 이용하여 수수의 수확량 예측을 위한 단위면적당 이삭 수를 추정하는 알고리즘의 기초자료로 유용하게 활용될 것으로 판단된다. 추가적으로 아직 개발의 초기 단계를 감안하면 확보된 데이터를 이용하여 성능 개선 및 다른 CNN 모델과 비교 검토할 필요가 있다고 사료된다.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2017년도 9th Asian Crop Science Association conference
• /
• pp.46-46
• /
• 2017

We developed a rice simulation model for remote-sensing (SIMRIW-RS, Homma et al., 2007) to evaluate rice production and management on a regional scale. Here, we reports its application trial to estimate rice production in farmers' fields in Sendai, Japan. The remote-sensing data for the application was periodically obtained by multispectral camera (RGB + NIR and RedEdge) attached with unmanned air vehicle (UAV). The airborne images was 8 cm in resolution which was attained by the flight at an altitude of 115 m. The remote-sensing data was relatively corresponded with leaf area index (LAI) of rice and its spatial and temporal variation, although the correspondences had some errors due to locational inaccuracy. Calibration of the simulation model depended on the first two remote-sensing data (obtained around one month after transplanting and panicle initiation) well predicted rice growth evaluated by the third remote-sensing data. The parameters obtained through the calibration may reflect soil fertility, and will be utilized for nutritional management. Although estimation accuracy has still needed to be improved, the rice yield was also well estimated. These results recommended further data accumulation and more accurate locational identification to improve the estimation accuracy.

• 농촌계획
• /
• 제23권1호
• /
• pp.21-29
• /
• 2017

The purpose of this study is to analyze the accuracy of cultivated crop database in agricultural farm business using UAV(Unmanned Aerial Vehicle) and field survey over Daesso-myeon, Umsung-gun, Chungbuk. When comparing with agricultural farm business and cadastral maps, Daeso-myeon crop field shows 29.8%(2,030 parcels out of 6,822 parcels) is either mismatched or missing. It covers almost 19.3%($3.4km^2$ of $17.6km^2$) of total farmland. In order to solve these problems, it is necessary to prepare a multifaceted plan including cadastral map. Comparative analysis of the cultivated crop registered in the agricultural farm business and the field survey agreed only in 3,622 parcels in total 6,822 parcels whereas 3200 parcels disagree. Among these disagreed parcels 2,030(29.8%) have been confirmed as unregistered farm business entity. Accuracy of cultivated crop registered in agricultural farm business agreed in 75.6% cases. Especially the paddy field registration is more accurate that other crops. These discrepancies can lead to false payment in agricultural farm business. For exploration and analysis of regional resources, UAV images can be used together with farm business management database and cadastral map to get a clearer grasp over on-site resources and conditions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권10호
• /
• pp.5095-5111
• /
• 2019

A multi-rotor Unmanned Aerial Vehicle (UAV) system is developed to solve the manhole cover detection problem for the infrastructure maintenance in the suburbs of big city. The visible light sensor is employed to collect the ground image data and a series of image processing and machine learning methods are used to detect the manhole cover. First, the image enhancement technique is employed to improve the imaging effect of visible light camera. An imaging environment perception method is used to increase the computation robustness: the blind Image Quality Evaluation Metrics (IQEMs) are used to percept the imaging environment and select the images which have a high imaging definition for the following computation. Because of its excellent processing effect the adaptive Multiple Scale Retinex (MSR) is used to enhance the imaging quality. Second, the Single Shot multi-box Detector (SSD) method is utilized to identify the manhole cover for its stable processing effect. Third, the spatial coordinate of manhole cover is also estimated from the ground image. The practical applications have verified the outdoor environment adaptability of proposed algorithm and the target detection correctness of proposed system. The detection accuracy can reach 99% and the positioning accuracy is about 0.7 meters.

• Journal of Platform Technology
• /
• 제8권1호
• /
• pp.3-9
• /
• 2020

우리나라는 전국토의 63% 가 산림으로 이루어져 있으며, 지구의 평균 기온은 증가하고 있다. 소나무재선충병과 같은 산림재해충의 확산 방지를 위한 효과적 운영 방법으로는 선제적인 방제가 요구된다. 선제적인 방제 체계는 기상, 지형적 및 인력운영의 어려움 등으로 적시 방제에 쉽지 않다. 본 논문에서는 정보통신기술 기반으로 소형 무인항공기를 이용하여 획득한 영상을 기반으로 피해목과 고사목을 자동으로 분류하는 체계를 갖춰 신속·정확하고 효율적인 방제체계를 갖추는 모델을 제시한다. 특히 제안된 모델은 민간분야 협력을 통해 정부업무에 대한 효과적인 대응체계를 구축함으로써 무인항공기 사업 및 서비스 산업 등의 새로운 일자리 창출을 기대할 수 있다.

• 한국산업융합학회 논문집
• /
• 제24권6_2호
• /
• pp.753-762
• /
• 2021

Google provides mapping services using satellite imagery, this is widely used for the study. Since about 20 years ago, research and business using drones have been expanding. Pix4D is widely used to create 3D information models using drones. This study compared the distance error by comparing the result of the road construction site with the DSM data of Google Earth and Pix4 D. Through this, we tried to understand the reliability of the result of distance measurement in Google Earth. A DTM result of 3.08 cm/pixel was obtained as a result of matching with 49666 key points for each image. The length and altitude of Pix4D and Google Earth were measured and compared using the obtained PCD. As a result, the average error of the distance based on the data of Pix4D was measured to be 0.68 m, confirming that the error was relatively small. As a result of measuring the altitude of Google Earth and Pix4D and comparing them, it was confirmed that the maximum error was 83.214m, which was measured using satellite images, but the error was quite large and there was inaccuracy. Through this, it was confirmed that there are difficulties in analyzing and acquiring data at road construction sites using Google Earth, and the result was obtained that point cloud data using drones is necessary.

• 한국지형학회지
• /
• 제28권4호
• /
• pp.1-13
• /
• 2021

In this study is aerial photos and UAV(Unmanned Aerial Vehicle) images were used to analyzed the characteristics of depositional landform changes in the Geum river channels before and after the opening gate of Gongju weir. Based on the depositional landform classification result, the main stream and the bare land occupied most of the area in all periods, and also found that the main stream, mid-channel island, and sand bar occupied a greater degree of area increase or decrease compared to other landforms in the classification items. As a result of analyzing the characteristics of depositional landform changes before and after the opening gate of Gongju weir, it is judged that the depositional landforms have changed due to the decreased water level of the Geum river after the opening of the weir, the summer rainy season and typhoons, river stabilization after the effluence of Daecheong dam, supply and deposition of river sediments and fixation of vegetation. The results derived from this study can be used as basic data for the study of river depositional landforms and the establishment of management and conservation plans for the landforms in river channels.

• ETRI Journal
• /
• 제45권5호
• /
• pp.795-810
• /
• 2023

Unmanned aerial vehicles (UAV) and ground vehicles (UGV) require advanced video analytics for various tasks, such as moving object detection and segmentation; this has led to increasing demands for these methods. We propose a zero-shot video object segmentation method specifically designed for UAV and UGV applications that focuses on the discovery of moving objects in challenging scenarios. This method employs a background memory model that enables training from sparse annotations along the time axis, utilizing temporal modeling of the background to detect moving objects effectively. The proposed method addresses the limitations of the existing state-of-the-art methods for detecting salient objects within images, regardless of their movements. In particular, our method achieved mean J and F values of 82.7 and 81.2 on the DAVIS'16, respectively. We also conducted extensive ablation studies that highlighted the contributions of various input compositions and combinations of datasets used for training. In future developments, we will integrate the proposed method with additional systems, such as tracking and obstacle avoidance functionalities.

• 한국산업융합학회 논문집
• /
• 제26권6_2호
• /
• pp.1073-1082
• /
• 2023

Thermal sensors, also called thermal infrared wavelength sensors, measure temperature based on the intensity of infrared signals that reach the sensor. The infrared signals recognized by the sensor include infrared wavelength(0.7~3.0㎛) and radiant infrared wavelength(3.0~100㎛). Infrared(IR) wavelengths are divided into five bands: near infrared(NIR), shortwave infrared(SWIR), midwave infrared(MWIR), longwave infrared(LWIR), and far infrared(FIR). Most thermal sensors use the LWIR to capture images. Thermal sensors measure the temperature of the target in a non-contact manner, and the data can be affected by the sensor's viewing angle between the target and the sensor, the amount of atmospheric water vapor (humidity), air temperature, and ground conditions. In this study, the characteristics of three thermal imaging sensor models that are widely used for observation using unmanned aerial vehicles were evaluated, and the optimal application field was determined.

• 대한임베디드공학회논문지
• /
• 제18권3호
• /
• pp.125-132
• /
• 2023

Roundabouts have strengths in traffic flow and safety but can present difficulties for inexperienced drivers. Demand to acquire and analyze drone images has increased to enhance a traffic environment allowing drivers to deal with roundabouts easily. In this paper, we propose a roundabout traffic analysis system that detects, tracks, and analyzes vehicles using a deep learning-based object detection model (YOLOv7) in drone images. About 3600 images for object detection model learning and testing were extracted and labeled from 1 hour of drone video. Through training diverse conditions and evaluating the performance of object detection models, we achieved an average precision (AP) of up to 97.2%. In addition, we utilized SORT (Simple Online and Realtime Tracking) and OC-SORT (Observation-Centric SORT), a real-time object tracking algorithm, which resulted in an average MOTA (Multiple Object Tracking Accuracy) of up to 89.2%. By implementing a method for measuring roundabout entry speed, we achieved an accuracy of 94.5%.