• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권1호
• /
• pp.371-384
• /
• 2019

Motion perception has been tremendously improved in neuroscience and computer vision. The baseline motion perception model is mediated by the dorsal visual pathway involving the cortex areas the primary visual cortex (V1) and the middle temporal (V5 or MT) visual area. However, few works have been done on the extension of neural models to improve the efficacy and robustness of motion perception of real sequences. To overcome shortcomings in situations, such as varying illumination and large displacement, an adaptive V1-MT motion perception (Ad-V1MTMP) algorithm enriched to deal with real sequences is proposed and analyzed. First, the total variation semi-norm model based on Gabor functions (TV-Gabor) for structure-texture decomposition is performed to manage the illumination and color changes. And then, we study the impact of image local context, which is processed in extra-striate visual areas II (V2), on spatial motion integration by MT neurons, and propose a V1-V2 method to extract the image contrast information at a given location. Furthermore, we take feedback inputs from V2 into account during the polling stage. To use the algorithm on natural scenes, finally, multi-scale approach has been used to handle the frequency range, and adaptive pyramidal decomposition and decomposed spatio-temporal filters have been used to diminish computational cost. Theoretical analysis and experimental results suggest the new Ad-V1MTMP algorithm which mimics human primary motion pathway has universal, effective and robust performance.

• 대한원격탐사학회지
• /
• 제35권1호
• /
• pp.57-81
• /
• 2019

Satellite images can be integrated into a crop model to strengthen the advantages of each technique for crop monitoring and to compensate for weaknesses of each other, which can be systematically applied for monitoring inaccessible croplands. The objective of this study was to outline the productivity of paddy rice based on simulation of the yield of all paddy fields in North Korea, using a grid crop model combined with optical satellite imagery. The grid GRAMI-rice model was used to simulate paddy rice yields for inaccessible North Korea based on the bidirectional reflectance distribution function-adjusted vegetation indices (VIs) and the solar insolation. VIs and solar insolation for the model simulation were obtained from the Geostationary Ocean Color Imager (GOCI) and the Meteorological Imager (MI) sensors of the Communication Ocean and Meteorological Satellite (COMS). Reanalysis data of air temperature were achieved from the Korea Local Analysis and Prediction System (KLAPS). Study results showed that the yields of paddy rice were reproduced with a statistically significant range of accuracy. The regional characteristics of crops for all of the sites in North Korea were successfully defined into four clusters through a spatial analysis using the K-means clustering approach. The current study has demonstrated the potential effectiveness of characterization of crop productivity based on incorporation of a crop model with satellite images, which is a proven consistent technique for monitoring of crop productivity in inaccessible regions.

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1445-1456
• /
• 2018

Environment perception and three-dimensional (3D) reconstruction tasks are used to provide unmanned ground vehicle (UGV) with driving awareness interfaces. The speed of obstacle segmentation and surrounding terrain reconstruction crucially influences decision making in UGVs. To increase the processing speed of environment information analysis, we develop a CPU-GPU hybrid system of automatic environment perception and 3D terrain reconstruction based on the integration of multiple sensors. The system consists of three functional modules, namely, multi-sensor data collection and pre-processing, environment perception, and 3D reconstruction. To integrate individual datasets collected from different sensors, the pre-processing function registers the sensed LiDAR (light detection and ranging) point clouds, video sequences, and motion information into a global terrain model after filtering redundant and noise data according to the redundancy removal principle. In the environment perception module, the registered discrete points are clustered into ground surface and individual objects by using a ground segmentation method and a connected component labeling algorithm. The estimated ground surface and non-ground objects indicate the terrain to be traversed and obstacles in the environment, thus creating driving awareness. The 3D reconstruction module calibrates the projection matrix between the mounted LiDAR and cameras to map the local point clouds onto the captured video images. Texture meshes and color particle models are used to reconstruct the ground surface and objects of the 3D terrain model, respectively. To accelerate the proposed system, we apply the GPU parallel computation method to implement the applied computer graphics and image processing algorithms in parallel.

• 대한지역사회영양학회지
• /
• 제24권4호
• /
• pp.290-299
• /
• 2019

Objectives: This study examined the nutrition teachers' and parents' recognition of environmentally-friendly agricultural products (EAPs) used in school foodservice. Methods: A questionnaire survey was given to 128 school foodservice nutrition teachers in Seongnam and 189 parents from Oct. 16 to Oct. 31, 2018 at Seongnam in Gyeonggi province. The survey included information on the recognition, satisfaction, and improvement of EAPs, and the results of the two groups were compared. Results: A comparison of the recognition of EAPs showed that nutrition teachers knew more about the EAPs and local government support in school foodservice than the parents. On the other hand, the parents were more aware than the nutrition teachers in that children have a higher affinity for EAPs than for general agricultural products in the school foodservice. A comparison of the level of satisfaction with the EAPs by nutrition teachers and parents revealed the nutrition teachers to be significantly more satisfied than parents in terms of the color, taste and nutrition of EAPs. Among the items that should be provided with EAPs, more than 50% of each group of nutrition teachers and parents answered that vegetables must be provided first. Some 70.9% of nutrition teachers and 84.5% of parents were aware of the certification standards of EAPs. The nutrition teachers had showed a slightly higher score than the parents in the certification system (3.51 vs. 3.25). In terms of improving the EAPs, 36.2% of nutrition teachers answered a reasonable price preferentially, whereas 56.4% of parents answered maintaining quality. In the expected effects of using EAPs, 57.9% of nutrition teachers answered an improvement of parents' satisfaction on the school foodservice. On the other hand, 38.0% of parents answered an improvement of children' satisfaction on school foodservice. Conclusions: Nutrition teachers and parents need to be educated on the certification systems that would enhance the trust in EAPs.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.180-182
• /
• 2022

절도, 폭행, 성범죄 등과 같은 각종 범죄들이 증가에 대응하기 위하여, 각 지자체에서 CCTV를 설치하고, 비상대응을 위해 24시간 관제센터를 운영하고 관리하고 있다. CCTV 관제센터에서 현장의 위험 상황을 감지하면, 경찰이나 119와 연계하여 대응하고 즉각 처리하고 있다. 하지만, 사람이 관리하는 것이다 보니 대응 속도가 변칙적이고 사후 처리에 중점적으로 활용되고 있는 것이 현실이다. 따라서, 인공지능 LED 안내판을 통해 현장에서 긴급상황을 알리고, 행인의 도움을 받거나 사고가 발생하기 전경고의 기능을 하도록 한다. 본 논문에서는 인공지능 algorithm을 반영하여 LED 안내판의 조명 색을 바꾸거나 소리를 내는 등 경고시스템을 설계하고 연구한다. 본 연구를 통해 치안 및 사회 안전에 기여하려고 한다.

• 수완나부미
• /
• 제2권2호
• /
• pp.1-28
• /
• 2010

This paper offers a brief introduction to Vietnamese folk paintings. The discussion compares Vietnamese folk paintings with the Korean folk painting tradition. Among the main purposes of this paper is the exploration of directions for future research on Vietnamese folk paintings. Vietnamese folk paintings, although extensively influenced by their Chinese tradition of minjian nianhua (folk New Year pictures), form an independent tradition, reflecting the local lifestyle and religious practices of Vietnam. However, compared to Korea or Japan, China remains the dominant source of influence for Vietnamese folk paintings. They were either created using a combination of painting and woodblock printing techniques, which was also the case with minjian nianhua, or using multicolor woodblock printing techniques. In cities like Hang Chong, the combination of painting and woodblock printing techniques was used mainly, following the customary practice in Yangliuqing in Tianjin, China, in which colors were added to the drawing printed from the woodblock. Meanwhile, folk paintings produced in rural areas such as Dong Ho are wholly color woodblock prints, similar to minjian nianhua from Yangjiabu in Weifang. In Lang Sinh, simple drawings, intended for casual purposes, were also created using the combination of woodblock printing and painting techniques. Folk paintings produced in cities and rural areas were distinct from each other, not just in techniques, but also in terms of style and theme. Vietnamese folk paintings show a certain degree of thematic similarity with Joseon folk paintings. This is mainly due to the fact that the two countries' folk paintings developed and evolved in parallel with their Chinese counterparts, minjian nianhua. Also noteworthy is the fact that Vietnamese folk paintings, while they share the simplicity and candidness of Joseon folk paintings, are at the same time somewhat more decorative than the latter. For best results, future research on Vietnamese folk paintings should be conducted together with research on minjian nianhua. Traditional pigments constitute an important area of research in this field. Attention should be also paid to the religious paintings of ethnic minorities in Vietnam, as they are discovered in the future.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.6-8
• /
• 2022

딥러닝을 활용한 객체 인식으로 이미지를 사용하는 많은 시스템에서 기존에 제공하던 방식을 넘어서 다양한 솔루션이 제공되고 있다. 많은 연구를 통하여 그 활용성을 입증하고 있으며, 실제 관제 시스템에서는 이를 사용하여 사람의 업무를 더욱 편리하게 하는 등 가능성을 보여주고 있다. 하지만, 하드웨어에 집중된 성능에 따라 모델의 개발도 일부 한계를 맞이하고 있으며 새롭게 업데이트되지 못한 많은 모델의 사용과 추가적 활용에 따른 용이성이 떨어지고 있다. 본 논문에서는 기존의 정형화된 객체 인식의 결괏값 이후에 인식된 국소 이미지 데이터의 HSV 색상 히스토그램을 통한 학습과 가중치를 활용하여 색상의 감성적 영역 및 객체의 추가적 정보를 제공하여 활용도와 정확성을 높일 방법을 제안한다.

• Animal Bioscience
• /
• 제36권11호
• /
• pp.1738-1746
• /
• 2023

Objective: The aim of this study was to investigate quality characteristics of reduced-salt, low-fat pork sausage (PS) using pre-rigor muscle and sea tangle extract (STE) to reduce salt level of sausages during refrigerated storage. Methods: Pork ham was prepared with pre-rigor and post-rigor muscle from the local market. Sausages using post-rigor muscle were manufactured with the 1.5% of salt content, and samples with pre-rigor muscle were processed by different salt concentrations (0.8%). Accordingly, PSs were prepared in 4 treatments (REF, PS with 1.5% of salt using post-rigor muscle; CTL, PS with 0.8% of salt using pre-rigor muscle; TRT1, PS with 0.8% of salt and 5% of STE using pre-rigor muscle; TRT2, PS with 0.8% of salt and 10% of STE using pre-rigor muscle). For the evaluation of quality characteristics and shelf-life of reduced-salt PS, pH and color values, cooking loss (%), expressible moisture (%), textural properties, lipid oxidation (thiobarbituric reactive substances), protein denaturation (volatile basic nitrogen), and microbiological analysis (total plate counts and Enterobacteriaceae counts) were determined. Results: The pH and temperature of pre-rigor raw pork ham were higher than those of post-rigor pork ham. Hardness of TRT2 was higher than that of REF or CTL. TRT2 had higher gumminess and chewiness than CTL. TRT1 and TRT2 had lower volatile basic nitrogen than CTL. Total plate counts of TRT2 were lower than those of CTL. Expressible moisture values of TRT1 and TRT2 were similar to those of REF. The addition of STE into PS improved functional properties and shelf-life of PS. Conclusion: Reduced-salt PS containing pre-rigor muscle and STE had similar functional properties to those of regular-salt ones, while containing approximately 47% less salt compared to regular-salt level.

• 대한두경부종양학회지
• /
• 제40권1호
• /
• pp.49-53
• /
• 2024

Dermatofibrosarcoma protuberans (DFSP) is a rare soft tissue sarcoma, with an incidence of about 0.8% to 5% per million people per year, accounting for 1% of soft tissue sarcomas. In its early stage, DFSP is typically found as a violet or pinkish macule or patch, and it can develop into a palpable mass with ulceration or bleeding. The standard treatment for DFSP is wide local excision of the tumor with a 2- to 3-cm negative margin, and radiation therapy or chemotherapy can be conducted with surgical treatment. A 35-year-old man had a palpable mass on the left side of his occipital scalp without color change, ulceration, or bleeding, which typically are present in malignancy. A magnetic resonance imaging (MRI) scan showed a 3-cm homogenous enhanced mass without adhesion between the scalp and the mass. Unexpectedly, a biopsy revealed the round mass to be DFSP. A wide excision and rotation of the scalp flap were performed. The patient recovered without any complications and received adjuvant radiotherapy at a dose of 60 Gray (Gy) for six weeks. There was no recurrence through six months of follow-up. Here we report this unique case of DFSP with atypical presentation.

• 한국학교보건학회지
• /
• 제14권1호
• /
• pp.131-143
• /
• 2001

The primary aim of this dissertation is to contribute to the improvement of methods in physical examination by providing quality information for the current school system and advice for improving status. Present status, controversial points and possible remedies in physical examination were analyzed on a frequency and percentage basis. An $x^2$-test was used to verify the statistics between the results from the examination and each variable. In case of multiple categories of variables, an $x^2$ cs was adopted. Chronological data as well as both total and sampling physical examination data verified the statistics using an $x^2$-test. This thesis is based both on the data from middle school health care specialists in Gyunggi Province and on the analysis of physical examinations reported from local schools to the municipal education agency from 1997 to 1999. The results of the study are as follows: First, according to the survey, only 29.0% of the total schools had their school doctors examine all the students while most of the educational institutions failed to implement the whole process of physical examination on the list. It also turned out that the more students the schools have, the lower the rate of implementation of physical examination by school doctors(p=0.014). Second, the average time a school doctor spends for checkup turned out to be approximately 1.7 minutes per student This means that the quality of the physical examination is not guaranteed in the process. Third, 47.7% of those surveryed say that a dental examination was performed, each taking 21.24 seconds on average. In addition, it shows that some 31.5% wanted to have a task force team for dental checkups at the local health center. Given the fact that dental caries among students is progressively on the rise, the dental health centers that are now set up in some elementary schools should be expanded to cover the whole educational institution in order to raise awareness of the importance of dental care. Fourth, 48.5% of those surveyed say that a comprehensive physical examination should be adopted to promote the health of high schoolers. Since it takes a lot of public funds to implement a comprehensive method, it is essential to make sure that in-depth studies should be based on the frequency and methods of physical examination. Fifth, regarding such diseases among 3rd year middle school students in 1999, statistics shows that there was a slight difference in the prevalence rate of color blindness, and allergic diseases for male students ; and color blindness, hearing disturbance and allergic disease for female students. For those items, however, it is too little to say that there is a significant difference and accordingly it is assumed to be a problem of the measuring process. Sixth, the result of analysis on the sample physical examination and the total physical examination of the year 1999 shows as follows: For male students in the 3rd year of middle school, a slight difference appeared to those students in 11 items including eye problems and eye disease, otitis media, tonsillar hypertrophy, spinal shape, respiratory urinary allergic disease and other abnormal diseases(p<0.05). Particularly, the prevalence rate between students with and without disease was shown to be two times more in the following: eye problems, otitis media, tonsill hypertrophy, allergic diseases, etc. For female students in the 3rd year, prevalence rate showed little difference in 14 items(p<0.05). For items including eye problem, otitis media, tonsill hypertrophy, allergic disease, etc. it was shown that the rate was two times more between students with and without diseases. Physical examinations under the current school system are not producing any fundamental results for the health of the students. Methods and results are not trustworthy. Accordingly, a drastic overhaul of the current practices is needed in frequency, methods and items on the list in order to promote the health of the students. Cost-benefit studies as well as political considerations to ensure the development of efficient methods for physical examination are urgently needed at this moment.