• Journal of Animal Science and Technology
• /
• v.63 no.2
• /
• pp.367-379
• /
• 2021

The objectives of this study were to evaluate convolutional neural network models and computer vision techniques for the classification of swine posture with high accuracy and to use the derived result in the investigation of the effect of dietary fiber level on the behavioral characteristics of the pregnant sow under low and high ambient temperatures during the last stage of gestation. A total of 27 crossbred sows (Yorkshire × Landrace; average body weight, 192.2 ± 4.8 kg) were assigned to three treatments in a randomized complete block design during the last stage of gestation (days 90 to 114). The sows in group 1 were fed a 3% fiber diet under neutral ambient temperature; the sows in group 2 were fed a diet with 3% fiber under high ambient temperature (HT); the sows in group 3 were fed a 6% fiber diet under HT. Eight popular deep learning-based feature extraction frameworks (DenseNet121, DenseNet201, InceptionResNetV2, InceptionV3, MobileNet, VGG16, VGG19, and Xception) used for automatic swine posture classification were selected and compared using the swine posture image dataset that was constructed under real swine farm conditions. The neural network models showed excellent performance on previously unseen data (ability to generalize). The DenseNet121 feature extractor achieved the best performance with 99.83% accuracy, and both DenseNet201 and MobileNet showed an accuracy of 99.77% for the classification of the image dataset. The behavior of sows classified by the DenseNet121 feature extractor showed that the HT in our study reduced (p < 0.05) the standing behavior of sows and also has a tendency to increase (p = 0.082) lying behavior. High dietary fiber treatment tended to increase (p = 0.064) lying and decrease (p < 0.05) the standing behavior of sows, but there was no change in sitting under HT conditions.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1354-1360
• /
• 2006

최근 놀라운 성장을 거듭하고 있는 지능형 로봇(Intelligent Robot) 기술은 기존의 주요 활용 분야였던 산업현장이나 연구실과 같은 전문가적 영역을 넘어서 지능형 엔터테인먼트(Entertainment)로봇이나 청소기 로봇의 예에서 볼 수 있듯이 인간의 주요 일상 생활 공간인 가정이나 공공기관의 서비스 분야로 점차 그 활용 영역을 넓혀가고 있다. 학습 보조 교사 도우미 로봇의 개발은 초등학교 교육 현장이 당면하고있는 각종 현안들을 로봇의 활용을 통해서 해결하고자하는 실용적인 목적에서 출발 했다. 이러한 관점에서 볼때 로봇 디자이너의 역할은 전체 개발 프로세스의 말단부에서 로봇 시스템의 외장(Appearance)을 마무리하는 역할을 넘어서 구체적 로봇시스템의 개발에 선행하여 학습보조 교사 도우미 로봇의 잠재적 활용 주체인 학생, 교사, 학부모의 입장에서 각 주체들의 내재적, 외재적 욕구를 효과적으로 만족 시킬 수있는 활용 시나리오(Application Scenario)를 도출, 개발 프로세스 전반에 걸쳐 각 개발 주체들에게 일관된 비젼(vision)과 이미지(image)를 제시하는것이라고 생각되었다. 본연구에서는 학습보조 교사 도우미 로봇 디자인 과제에 있어서 사용자 관찰(User Observation), 유저 다이어리(User Diary), 포커스그룹 인터뷰(F.G.I)등을 바탕으로 로봇의 역할 모델중심, 서비스 영역 중심, 초등학교 교육이념 구현 중심 등 3가지의 서로 다른 컨셉의 로봇 활용 시나리오(Application Scenario)를 제안하였다. 본 연구 결과는 현재 초기 단계에 있는 로봇 디자인 분야의 현실을 감안할때 전체 로봇 개발 프로세스내에서의 향후 산업 디자인이 수행해야 할 역할을 명확하게 보여준다는 점에서 그 의의가 있으며 관련 분야의 연구 활성화에 기여할 것으로 기대된다.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.43 no.5 s.311
• /
• pp.1-9
• /
• 2006

Because most applications of vision-based object tracking demonstrate satisfactory operations only under very constrained environments that have simplifying assumptions or specific visual attributes, these approaches can't track target objects for the highly variable, unstructured, and dynamic environments like a traffic scene. An adaptive fusion framework is essential that takes advantage of the richness of visual information such as color, appearance shape and so on, especially at cluttered and dynamically changing scenes with partial occlusion[1]. This paper develops a particle filter based adaptive fusion framework and improves the robustness and adaptation of this framework by adding a new distinctive visual attribute, an image feature descriptor using SIFT (Scale Invariant Feature Transform)[2] and adding an automatic teaming scheme of the SIFT feature library according to viewpoint, illumination, and background change. The proposed algorithm is applied to track various traffic objects like vehicles, pedestrians, and bikes in a driver assistance system as an important component of the Intelligent Transportation System.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.12
• /
• pp.2312-2317
• /
• 2017

Museums are converging with digital technology to convey information to viewers in various ways. Augmented reality technology enhances virtual objects seamlessly in the real world, and provides a high sense of immersion and realism because it can use various senses of users in combination with information providing role of exhibits. However, the location-based augmented reality may cause the inaccurate registration of the virtual object with the real world due to the error of the GPS information, and the vision-based augmented reality can be enhanced at the position where the marker is placed. To solve this problem, we implemented the exhibition contents that interact with the real world by using the developed project tango. The exhibited contents were based on Lenovo Phab 2 Pro and Project Tango SDK in Unity 3D. Visitors were able to improve immersion and realism in exhibition contents, and it would be able to combine with various exhibition fields such as shopping malls as well as museums.

• The Journal of the Korea Contents Association
• /
• v.11 no.11
• /
• pp.62-69
• /
• 2011

Development of sensing technology and progress of digital media have been creating new art genre named interactive media art. digital mirror working based on convergence between computer vision technology and video art, is expressing reconstituted spectator's visual image through various mediums. From this aesthetical point and high accessibility towards spectators, many types of digital mirrors have been introducing. However, the majority of digital mirrors express visual images unrelated to degree of spectator's participation and this caused obstruction to spectator's continuous participation and interaction. This paper proposes digital mirror operated by spectator's movements read through particle system synchronized with motion detection algorithm based on analyzing image difference. This work extracted the data of spectator's movement by image processing and designed particle system changed by this data. And it expressed reconstructed spectator's image.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.751-770
• /
• 2019

Action recognition is an essential task in computer vision due to the variety of prospective applications, such as security surveillance, machine learning, and human-computer interaction. The availability of more video data than ever before and the lofty performance of deep convolutional neural networks also make it essential for action recognition in video. Unfortunately, limited crafted video features and the scarcity of benchmark datasets make it challenging to address the multi-person action recognition task in video data. In this work, we propose a deep convolutional neural network-based Effective Hybrid Learning (EHL) framework for two-person interaction classification in video data. Our approach exploits a pre-trained network model (the VGG16 from the University of Oxford Visual Geometry Group) and extends the Faster R-CNN (region-based convolutional neural network a state-of-the-art detector for image classification). We broaden a semi-supervised learning method combined with an active learning method to improve overall performance. Numerous types of two-person interactions exist in the real world, which makes this a challenging task. In our experiment, we consider a limited number of actions, such as hugging, fighting, linking arms, talking, and kidnapping in two environment such simple and complex. We show that our trained model with an active semi-supervised learning architecture gradually improves the performance. In a simple environment using an Intelligent Technology Laboratory (ITLab) dataset from Inha University, performance increased to 95.6% accuracy, and in a complex environment, performance reached 81% accuracy. Our method reduces data-labeling time, compared to supervised learning methods, for the ITLab dataset. We also conduct extensive experiment on Human Action Recognition benchmarks such as UT-Interaction dataset, HMDB51 dataset and obtain better performance than state-of-the-art approaches.

• Smart Media Journal
• /
• v.11 no.4
• /
• pp.9-18
• /
• 2022

Recently, research and system using AI is rapidly increasing in various fields. Smart farm using artificial intelligence and information communication technology is also being studied in agriculture. In addition, data-based precision agriculture is being commercialized by convergence various advanced technology such as autonomous driving, satellites, and big data. In Korea, the number of commercialization cases of facility agriculture among smart agriculture is increasing. However, research and investment are being biased in the field of facility agriculture. The gap between research and investment in facility agriculture and open-air agriculture continues to increase. The fields of fruit trees and plant factories have low research and investment. There is a problem that the big data collection and utilization system is insufficient. In this paper, we are proposed the system for determining the fruit tree growth stage using a deep learning-based object detection model. The system was proposed as a hybrid app for use in agricultural sites. In addition, we are implemented an object detection function for the fruit tree growth stage determine.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.67-71
• /
• 2024

Mo Youzhi (1811-1871) was a famous scholar, poet and calligrapher in the late Qing Dynasty. Mo Youzhi's life was rich in experience and broad vision, especially during his ten years in the Shogunate of the Tsengoku Domain, and he made friends with many political and cultural elites. Mo Youzhi is talented and diligent, and has a good relationship with celebrities from all walks of life at that time, so that his talents have been fully demonstrated. In the Qing Dynasty, the study of calligraphy became the absolute dominant force in the world of calligraphy, and the first great prosperity occurred after the Qin and Han dynasties. In accordance with the times, Mo Youzhi devotes himself to learning, takes into account the calligraphy, and goes out on his own path. Moe's work seal, li, kai, line, especially fine seal. Based on its Lishu, this paper expounds its typical style and atypical style respectively, and also discusses the relationship between its Lishu and other fonts. Finally, the author briefly summarizes the significance of Li Shu for the creation of contemporary Li Shu.In the course of discussion, always based on calligraphy ink, consult the relevant literature, combined with Mo Youzhi's life experience, try to be objective and fair, the listed points of view can be based on.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.3
• /
• pp.278-287
• /
• 2013

Modern information technologies continue to provide industries with new and improved methods. With the rapid development of Machine to Machine (M2M) communication, a smart container supply chain management is formed based on high performance sensors, computer vision, Global Positioning System (GPS) satellites, and Globle System for Mobile (GSM) communication. Existing supply chain management has limitation to real time container tracking. This paper focuses on the studies and implementation of real time container chain management with the development of the container identification system and automatic alert system for interrupts and for normal periodical alerts. The concept and methods of smart container modeling are introduced together with the structure explained prior to the implementation of smart container tracking alert system. Firstly, the paper introduces the container code identification and recognition algorithm implemented in visual studio 2010 with Opencv (computer vision library) and Tesseract (OCR engine) for real time operation. Secondly it discusses the current automatic alert system provided for real time container tracking and the limitations of those systems. Finally the paper summarizes the challenges and the possibilities for the future work for real time container tracking solutions with the ubiquitous mobile and satellite network together with the high performance sensors and computer vision. All of those components combine to provide an excellent delivery of supply chain management with outstanding operation and security.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.13 no.4
• /
• pp.91-100
• /
• 2010

Existing traffic safety studies have focused on identifying the relationship among roadway crashes, highway design and incremental weather condition such as rainy/ice weather. However, it is hard to find researches that studied the effect of sun glare on traffic safety although there are abundant evidences demonstrating that fatal traffic crashes are attributed to the sun glare. Affecting drivers'vision particularly during the morning or the evening time when the sun positions close to the horizon, sun glare directly deteriorate drivers'judgmental capability. In this paper, we numerically analyze the effect of sun glare on the drivers'vision in time and space domains. Applied to the roadways around St Louis area in the United States, the GIS based simulation analysis identifies the time of day in a year and the segments of highways that are potentially influenced by the sun glare. This study evidentially confirms the fact that roadway bounded for West and East directions have longer time influenced by sun glare particularly during Spring and Fall season than other roadways. The computational result provides risky time periods of day at intersections or pedestrian crossings where the sun glare potentially endangers traffic safety, which be utilized to reduce the crashes due to the sun glare.