• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.1-8
• /
• 2024

We present a novel algorithm for creating 2D maps tailored for autonomous navigation within orchards. Recognizing that fruit trees in orchards are typically aligned in rows, our primary goal is to accurately detect these tree rows and project this information onto the map. Initially, we propose a simple algorithm that recognizes trees from point cloud data by analyzing the spatial distribution of points. We then introduce a method for detecting fruit tree rows based on the positions of recognized fruit trees, which are integrated into the 2D orchard map. Validation of the proposed approach was conducted using real-world orchard point cloud data acquired via LiDAR. The results demonstrate high tree detection accuracy of 90% and precise tree row mapping, confirming the method's efficacy. Additionally, the generated maps facilitate the development of natural navigation paths that align with the orchard's layout.

• Smart Structures and Systems
• /
• v.33 no.6
• /
• pp.399-414
• /
• 2024

This study discusses the long-term deformation monitoring and shape sensing of bridge girder surfaces with an automated extraction scheme for point clouds in the Region Of Interest (ROI), invariant to the position of a Light Detection And Ranging system (LiDAR). Advanced smart construction necessitates continuous monitoring of the deformation and shape of bridge girders during the construction phase. An automated scheme is proposed for reconstructing geometric model of ROI in the presence of noisy non-stationary background. The proposed scheme involves (i) denoising irrelevant background point clouds using dimensions from the design model, (ii) extracting the outer boundaries of the bridge girder by transforming and processing the point cloud data in a two-dimensional image space, (iii) extracting topology of pre-defined targets using the modified Otsu method, (iv) registering the point clouds to a common reference frame or design coordinate using extracted predefined targets placed outside ROI, and (v) defining the bounding box in the point clouds using corresponding dimensional information of the bridge girder and abutments from the design model. The surface-fitted reconstructed geometric model in the ROI is superposed consistently over a long period to monitor bridge shape and derive deflection during the construction phase, which is highly correlated. The proposed scheme of combining 2D-3D with the design model overcomes the sensitivity of 3D point cloud registration to initial match, which often leads to a local extremum.

• Journal of Korea Multimedia Society
• /
• v.10 no.2
• /
• pp.209-217
• /
• 2007

This paper proposed to a detection scheme of weather information that is a part of CCTV Images Weather Detection System using CCTV images and Temperature, Humidity. The previous Partial Weather Detection System uses how to acquire weather information using images on the Road. In the system the contrast and RGB Values using clear images are gained. This information is distributed a input images to cloud, rain, snow and fog images. That is, this information is compared the snow and the fog images for acquisition more correctness information us ing difference images and binary images. Currently, We use to environment sense system, but we suggest a new Weather Detection Algorithm to detect weather information using CCTV images. Our algorithm is designed simply and systematically to detect and separate special characteristics of images from CCTV images. and using temperature & humidity in formation. This algorithm, there is more complex to implement than how to use DB with high overhead of time and space in the previous system. But our algorithm can be implement with low cost' and can be use the system in real work right away. Also, our algorithm can detect the exact information of weather with adding in formation including temperature, humidity, date, and time. At last, this paper s how the usefulness of our algorithm.

• Convergence Security Journal
• /
• v.21 no.1
• /
• pp.191-200
• /
• 2021

Artificial intelligence technology is developing in an environment where a lot of data is produced due to the development of computing technology, a cloud environment that can store data, and the spread of personal mobile phones. Among these artificial intelligence technologies, the deep neural network provides excellent performance in image recognition and image classification. There have been many studies on image detection for forest fires and fire prevention using such a deep neural network, but studies on detection of cigarette smoking were insufficient. Meanwhile, military units are establishing surveillance systems for various facilities through CCTV, and it is necessary to detect smoking near ammunition stores or non-smoking areas to prevent fires and explosions. In this paper, by reflecting experimentally optimized numerical values such as activation function and learning rate, we did the detection of smoking pictures and non-smoking pictures in two cases. As experimental data, data was constructed by crawling using pictures of smoking and non-smoking published on the Internet, and a machine learning library was used. As a result of the experiment, when the learning rate is 0.004 and the optimization algorithm Adam is used, it can be seen that the accuracy of 93% and F1-score of 94% are obtained.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.44-55
• /
• 2022

In order to automatically provide information on fruits in agricultural related broadcasting contents, instance image segmentation of target fruits is required. In addition, the information on the 3D pose of the corresponding fruit may be meaningfully used. This paper represents research that provides information about tomatoes in video content. A large amount of data is required to learn the instance segmentation, but it is difficult to obtain sufficient training data. Therefore, the training data is generated through a data augmentation technique based on a small amount of real images. Compared to the result using only the real images, it is shown that the detection performance is improved as a result of learning through the synthesized image created by separating the foreground and background. As a result of learning augmented images using images created using conventional image pre-processing techniques, it was shown that higher performance was obtained than synthetic images in which foreground and background were separated. To estimate the pose from the result of object detection, a point cloud was obtained using an RGB-D camera. Then, cylinder fitting based on least square minimization is performed, and the tomato pose is estimated through the axial direction of the cylinder. We show that the results of detection, instance image segmentation, and cylinder fitting of a target object effectively through various experiments.

• Journal of the Korean earth science society
• /
• v.39 no.1
• /
• pp.53-66
• /
• 2018

The information of surface reflectance ($R_{sfc}$) is important for the heat balance and the environmental/climate monitoring. The $R_{sfc}$ sensitivity to error-induced variables for the Geostationary Environment Monitoring Spectrometer (GEMS) retrieval from geostationary-orbit satellite observations at 300-500 nm was investigated, utilizing polar-orbit satellite data of the MODerate resolution Imaging Spectroradiometer (MODIS) and Ozone Mapping Instrument (OMI), and the radiative transfer model (RTM) experiment. The variables in this study can be cloud, Rayleigh-scattering, aerosol, ozone and surface type. The cloud detection in high-resolution MODIS pixels ($1km{\times}1km$) was compared with that in GEMS-scale pixels ($8km{\times}7km$). The GEMS detection was consistent (~79%) with the MODIS result. However, the detection probability in partially-cloudy (${\leq}40%$) GEMS pixels decreased due to other effects (i.e., aerosol and surface type). The Rayleigh-scattering effect in RGB images was noticeable over ocean, based on the RTM calculation. The reflectance at top of atmosphere ($R_{toa}$) increased with aerosol amounts in case of $R_{sfc}$<0.2, but decreased in $R_{sfc}{\geq}0.2$. The $R_{sfc}$ errors due to the aerosol increased with wavelength in the UV, but were constant or slightly decreased in the visible. The ozone absorption was most sensitive at 328 nm in the UV region (328-354 nm). The $R_{sfc}$ error was +0.1 because of negative total ozone anomaly (-100 DU) under the condition of $R_{sfc}=0.15$. This study can be useful to estimate $R_{sfc}$ uncertainties in the GEMS retrieval.

• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.6
• /
• pp.43-53
• /
• 2019

In recent years, there have been many cases of damage to indoor air hazardous materials, and major damage due to the lack of quick action. In this regard, the system is intended to establish for sending push messages to the user's mobile when the concentration of hazardous substances is exceeded. This system extracts data with IoT system such as Arduino and Raspberry Pi and then constructs database through MongoDB and MySQL in cloud computing system. The database is imported through the application server using NodeJS and sent to the application for visualization. Also, when receiving signals about a dangerous situation in IoT system, push message is sent using Google FCM library. Mobile application is developed using Android Web view, and page to enter Web view is developed using HTML5 (HTML, Javascript CSS). The application of this system enables real-time monitoring of indoor air-dangerous substances. In addition, real-time information on indoor/outdoor detection location and concentration can be sent to the user's mobile in case of a risk situation, which can be expected to help the user respond quickly.

• Journal of Korean Society for Geospatial Information Science
• /
• v.24 no.1
• /
• pp.81-87
• /
• 2016

It is important to analyze the exact damage information for fast recovery when natural disasters cause damage on river-side facilities such as dams, bridges, embankments etc. In this study, we shows the method to effectively damage analysis plan using UAV(Unmanned aerial vehicle) images and accuracy assessment of it. The UAV images are captured on area near the river-side facilities and the core methodology for damage analysis are image matching and change detection algorithm. The result(point cloud) from image matching is to construct 3-dimensional data using by 2-dimensional images, it extracts damage areas by comparing the height values on same area with reference data. The results are tested absolute locational precision compared by post-processed aerial LiDAR data named reference data. The assessment analysis test shows our matching results 10-20 centimeter level precision if external orientation parameters are very accurate. This study shows suggested method is very useful for damage analysis in a large size structure like river-side facilities. But the complexity building can't apply this method, it need to the other method for damage analysis.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.507-513
• /
• 2021

GPR (Ground Penetrating RADAR) is a sensor that inspects the pavement state of roads, sinkholes, and underground pipes. It is widely used in road management. MMS (Mobile Mapping System) creates a detailed and accurate road map of the road surface and its surroundings. If both types of data are built in the same area, it is efficient to construct both ground and underground spatial information at the same time. In addition, since it is possible to grasp the road and important facilities around the road, the location of underground pipelines, etc. without special technology, an intuitive understanding of the site is also possible, which is a useful tool in managing the road or facilities. However, overseas equipment to which this latest technology is applied is expensive and does not fit the domestic situation. LiDAR (Light Detection And Raging) and GNSS/INS (Global Navigation Satellite System / Inertial Navigation System) were synchronized in order to replace overseas developed equipment and to secure original technology to develop domestic equipment in the future, and GPR data was also synchronized to the same GNSS/INS. We developed software that performs georeferencing using the location and attitude information from GNSS/INS at the time of acquiring synchronized GPR data. The experiments were conducted on the road site by dividing the open sky and the non-open sky. The road and surrounding facilities on the ground could be easily checked through the 3D point cloud data acquired through LiDAR. Georeferenced GPR data could also be viewed with a 3D viewer along with point cloud data, and the location of underground facilities could be easily and quickly confirmed through GPR data.

• Journal of the Korean Geotechnical Society
• /
• v.37 no.11
• /
• pp.107-118
• /
• 2021

Scan-to-BIM can be precisely mod eled by measuring structures with Light Detection And Ranging (LiDAR) and build ing a 3D BIM (Building Information Modeling) model based on it, but has a limitation in that it consumes a lot of manpower, time, and cost. To overcome these limitations, studies are being conducted to perform semantic segmentation of 3D point cloud data applying deep learning algorithms, but studies on how segmentation result changes depending on learning data are insufficient. In this study, a parametric study was conducted to determine how the size and track type of railroad tunnels constituting learning data affect the semantic segmentation of railroad tunnels through deep learning. As a result of the parametric study, the similar size of the tunnels used for learning and testing, the higher segmentation accuracy, and the better results when learning through a double-track tunnel than a single-line tunnel. In addition, when the training data is composed of two or more tunnels, overall accuracy (OA) and mean intersection over union (MIoU) increased by 10% to 50%, it has been confirmed that various configurations of learning data can contribute to efficient learning.