• Journal of Korean Society of Forest Science
• /
• v.106 no.1
• /
• pp.100-109
• /
• 2017

This study was conducted for preliminary survey and management support for Pine Wood Nematode (PWN) suppression. We took areal photographs of 6 areas for a total of 2,284 ha during 2 weeks period from 15/02/2016, and produced 6 ortho-images with a high resolution of 12 cm GSD (Ground Sample Distance). Initially we classified 423 trees suspected for PWN infection based on the ortho-images. However, low accuracy was observed due to the problems of seasonal characteristics of aerial photographing and variation of forest stands. Therefore, we narrowed down 231 trees out of the 423 trees based on the initial classification, snap photos, and flight information; produced thematic maps; conducted field survey using GNSS; and detected 23 trees for PWN infection that was confirmed by ground sampling and laboratory analysis. The infected trees consisted of 14 broad-leaf trees, 5 pine trees (2 Pinus rigida), and 4 other conifers, showing PWN infection occurred regardless of tree species. It took 6 days for 2.3 men from to start taking areal photos using UAV (Unmanned Aerial Vehicle) to finish detecting PNW (Pine Wood Nematode) infected tress for over 2,200 ha, indicating relatively high efficacy.

• Journal of the Korean Society of Earth Science Education
• /
• v.10 no.1
• /
• pp.76-89
• /
• 2017

The purpose of this study is to develop a science field study area using Geumgang(Geum River), fossil origins and various geological resources in Youngdong area of Chungcheongbuk-do as educational resources; and utilize them to develop an education program to cultivate earth science and topophilia. The Youngdong sedimentary basin (Cretaceous period) has a well-developed outcrop along the Geumgang and it is therefore easy to find various geological structures, plant fossils, and dinosaur fossils. Also, it has a distinct sedimentary structure, such as mud cracks, ripple marks and cross-bedding. Science field study area(6 observation sites) were developed based on school curriculum, textbook analysis, and professional earth science education panel discussion to create a convergence education program. The result of validating the developed program showed that all the items were satisfactory ($CVR{\geq}0.88$) in the test categories. The science field study teaching-learning model was applied to actual classes. The evaluation result for class satisfaction was positive, scoring Rickert scale 4.18. The result of observation about the outdoor classroom process in the science field study area revealed that students were able to form a new image of the beautiful scenery of the Geumgang. Also, the students could gain a new understanding, concept and value of various geological objects (sandy beach, stepping-stones, dinosaur footprint fossils, sedimentary formation), which naturally allowed them to form topophilia.

• Journal of KIISE
• /
• v.42 no.5
• /
• pp.609-620
• /
• 2015

Viewers of videos are likely to absorb more information from the part of the screen that attracts visual attention. This fact has led to the visual attention models that are being used in producing and evaluating videos. In this paper, we investigate the factors that are significant to visual attention and the mathematical form of the visual attention model. We then estimated the visual attention probability using the statistical design of experiments. The analysis of variance (ANOVA) verifies that the motion velocity, distance from the screen, and amount of defocus blur affect human visual attention significantly. Using the response surface modeling (RSM), we created a visual attention score model that concerns the three factors, from which we calculate the visual attention probabilities (VAPs) of image pixels. The VAPs are directly applied to existing gradient based 3D effect perception measurement. By giving weights according to our VAPs, our algorithm achieves more accurate measurement than the existing method. The performance of the proposed measurement is assessed by comparing them with subjective evaluation as well as with existing methods. The comparison verifies that the proposed measurement outperforms the existing ones.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.4
• /
• pp.156-163
• /
• 2015

In this paper, we propose an active water level and distance measurement algorithm using a light beam pattern. On behalf of conventional water level gauge types of pressure, float-well, ultrasonic, radar, and others, recently, extensive research for video analysis based water level measurement methods is gradually increasing as an importance of accurate measurement, monitoring convenience, and much more has been emphasized. By turning a reference light beam pattern on bridge or embankment actively, we suggest a new approach that analyzes and processes the projected light beam pattern image obtained from camera device, measures automatically water level and distance between a camera and a bridge or a levee. As contrasted with conventional methods that passively have to analyze captured video information for recognition of a watermark attached on a bridge or specific marker, we actively use the reference light beam pattern suited to the installed bridge environment. So, our method offers a robust water level measurement. The reasons are as follows. At first, our algorithm is effective against unfavorable visual field, pollution or damage of watermark, and so on, and in the next, this is possible to monitor in real-time the portable-based local situation by day and night. Furthermore, our method is not need additional floodlight. Tests are simulated under indoor environment conditions from distance measurement over 0.4-1.4m and height measurement over 13.5-32.5cm.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.59-68
• /
• 2021

As artificial intelligence(AI) technologies, which have made rapid growth recently, began to be applied to the marine environment such as ships, there have been active researches on the application of CNN-based models specialized for digital videos. In E-Navigation service, which is combined with various technologies to detect floating objects of clash risk to reduce human errors and prevent fires inside ships, real-time processing is of huge importance. More functions added, however, mean a need for high-performance processes, which raises prices and poses a cost burden on shipowners. This study thus set out to propose a method capable of processing information at a high rate while maintaining the accuracy by applying Quantization techniques of a deep learning model. First, videos were pre-processed fit for the detection of floating matters in the sea to ensure the efficient transmission of video data to the deep learning entry. Secondly, the quantization technique, one of lightweight techniques for a deep learning model, was applied to reduce the usage rate of memory and increase the processing speed. Finally, the proposed deep learning model to which video pre-processing and quantization were applied was applied to various embedded boards to measure its accuracy and processing speed and test its performance. The proposed method was able to reduce the usage of memory capacity four times and improve the processing speed about four to five times while maintaining the old accuracy of recognition.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_3
• /
• pp.1965-1974
• /
• 2021

Satellite remote sensing approach can be actively used for forest monitoring. Especially, it is much meaningful to utilize Korea multi-purpose satellites, an independently operated satellite in Korea, for forest monitoring of Korea, Recently, several studies have been performed to exploit meaningful information from satellite remote sensed data via machine learning approaches. The forest information produced through machine learning approaches can be used to support the efficiency of traditional forest monitoring methods, such as in-situ survey or qualitative analysis of aerial image. The performance of machine learning approaches is greatly depending on the characteristics of study area and data. Thus, it is very important to survey the best model among the various machine learning models. In this study, the performance of deep neural network to classify artificial or natural forests was analyzed in Samcheok, Korea. As a result, the pixel accuracy was about 0.857. F1 scores for natural and artificial forests were about 0.917 and 0.433 respectively. The F1 score of artificial forest was low. However, we can find that the artificial and natural forest classification performance improvement of about 0.06 and 0.10 in F1 scores, compared to the results from single layered sigmoid artificial neural network. Based on these results, it is necessary to find a more appropriate model for the forest type classification by applying additional models based on a convolutional neural network.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.2
• /
• pp.229-238
• /
• 2019

Various wood defects occur during tree growing or wood processing. Thus, to use wood practically, it is necessary to objectively assess their quality based on the usage requirement by accurately classifying their defects. However, manual visual grading and species classification may result in differences due to subjective decisions; therefore, computer-vision-based image analysis is required for the objective evaluation of wood quality and the speeding up of wood production. In this study, the SIFT+k-NN and CNN models were used to implement a model that automatically classifies knots and analyze its accuracy. Toward this end, a total of 1,172 knot images in various shapes from five domestic conifers were used for learning and validation. For the SIFT+k-NN model, SIFT technology was used to extract properties from the knot images and k-NN was used for the classification, resulting in the classification with an accuracy of up to 60.53% when k-index was 17. The CNN model comprised 8 convolution layers and 3 hidden layers, and its maximum accuracy was 88.09% after 1205 epoch, which was higher than that of the SIFT+k-NN model. Moreover, if there is a large difference in the number of images by knot types, the SIFT+k-NN tended to show a learning biased toward the knot type with a higher number of images, whereas the CNN model did not show a drastic bias regardless of the difference in the number of images. Therefore, the CNN model showed better performance in knot classification. It is determined that the wood knot classification by the CNN model will show a sufficient accuracy in its practical applicability.

• Journal of Digital Convergence
• /
• v.17 no.1
• /
• pp.159-168
• /
• 2019

The purpose of this study is to propose a strategy for creating an advertisement for Corporate Social Responsibility(CSR) based on the strategy of selecting an advertisement model in order to efficiently execute the advertisement of CSR. Data were analyzed by regression analysis. The results of this study are as follows: First, it is found that the value-relevance factors of the model are important regardless of the theme of CSR. In the economic field, the reliability of the model is important. But, the attractiveness of the model was more important in the environmental field. Second, it is effective to select a model with high value-relevance when selecting CSR advertising model. But, in the case of an expert, it is effective to select not only value addition, but also attractive and reliable models. Third, when producing CSR ads using emotional messages, it is important to consider the value and reliability of the advertising model. But, it is important to select the model considering the importance of the value and attractiveness of the advertisement model when producing the CSR advertisement using the informational message. It was found that it is very important to select a model that has a high relevance to the image of the social responsibility subject and the advertisement model when producing the social responsibility advertisement.

• Journal of Korean Neurosurgical Society
• /
• v.62 no.4
• /
• pp.414-421
• /
• 2019

Objective : To evaluate 3-dimensional magnetic resonance imaging (MRI) of Kambin's safe zone to calculate maximum cannula diameter permissible for safe percutaneous endoscopic lumbar discectomy. Methods : Fifty 3D MRIs of 19 males and 31 females (mean, 47 years) were analysed. Oblique, axial and sagittal views were used for image analysis. Three authors calculated the inscribed circle (cannula diameter) individually, within the neural (original) and bony Kambin's triangle in oblique views, disc heights on sagittal views and root to facet distances at upper and lower end plate levels on axial views and their averages were taken. Results : The mean root to facet distances at upper end plate level measured on axial sections increased from $3.42{\pm}3.01mm$ at L12 level to $4.57{\pm}2.49mm$ at L5S1 level. The mean root to facet distances at lower end plate level measured on axial sections also increased from $6.07{\pm}1.13mm$ at L12 level to $12.9{\pm}2.83mm$ at L5S1 level. Mean maximum cannula diameter permissible through the neural Kambin's triangle increased from $5.67{\pm}1.38mm$ at L12 level to $9.7{\pm}3.82mm$ at L5S1 level. The mean maximum cannula diameter permissible through the bony Kambin's triangle also increased from $4.03{\pm}1.08mm$ at L12 level to $6.11{\pm}1mm$ at L5S1 level. Only 2% of the 427 bony Kambin's triangles could accommodate a cannula diameter of 8mm. The base of the bony Kambin's triangle taken in oblique view (3D MRI) was significantly higher than the root to facet distance at lower end plate level taken in axial view. Conclusion : The largest mean diameter of endoscopic cannula passable through "bony" Kambin's triangle was distinctively smaller than the largest mean diameter of endoscopic cannula passable through "neural" Kambin's triangle at all levels. Although proximity of exiting root to the facet joint is always taken into consideration before PELD procedure, our 3D MRI based anatomical study is the first to provide actual maximum cannula dimensions permissible in this region.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.203-215
• /
• 2019

As hyperspectral sensors that can be mounted on drones are developed, it is possible to acquire hyperspectral imagery with high spatial and spectral resolution. Although the importance of atmospheric correction has been reduced since imagery of drones were acquired at a low altitude,studies on the conversion process from raw data to spectral reflectance should be done for studies such as estimating the concentration of surface materials using hyperspectral imagery. In this study, a vicarious radiometric calibration and an atmospheric correction algorithm based on atmospheric radiation transfer model were applied to hyperspectral data of drone and the results were compared and analyzed. The vicarious calibration method was applied to an empirical line calibration using the spectral reflectance of a tarp made of uniform material. The atmospheric correction algorithm used ATCOR-4 based Modran-5 that was widely used for the atmospheric correction of aerial hyperspectral imagery. As a result of analyzing the RMSE of the difference between the reference reflectance and the correction, the vicarious calibration using the tarp in a single period of hyperspectral image was the most accurate, but the atmospheric correction was possible according to the application purpose of using hyperspectral imagery. If the correction process of normalized spectral reflectance is carried out through the additional vicarious calibration for imagery from multiple periods in the future, accurate analysis using hyperspectral drone imagery will be possible.