• Journal of Multimedia Information System
• /
• v.1 no.1
• /
• pp.45-53
• /
• 2014

This article describes a two wheelers detection system riding on people based on modified histogram of oriented gradients (HOG) for vision based intelligent vehicles. These features used correlation coefficient parameter are able to classify variable and complicated shapes of a two wheelers according to different viewpoints as well as human appearance. Also our system maintains the simplicity of evaluation of traditional formulation while being more discriminative. In this paper, we propose an evolutionary method trained part-based models to classify multiple view-based detection: frontal, rear and side view (within $60^{\circ}C$). Our experimental results show that a two wheelers riding on people detection system based on proposed approach leads to higher detection accuracy rate than traditional features.

• ETRI Journal
• /
• v.35 no.6
• /
• pp.1021-1028
• /
• 2013

Automatic facial expression recognition is a widely studied problem in computer vision and human-robot interaction. There has been a range of studies for representing facial descriptors for facial expression recognition. Some prominent descriptors were presented in the first facial expression recognition and analysis challenge (FERA2011). In that competition, the Local Gabor Binary Pattern Histogram Sequence descriptor showed the most powerful description capability. In this paper, we introduce hybrid facial representations for facial expression recognition, which have more powerful description capability with lower dimensionality. Our descriptors consist of a block-based descriptor and a pixel-based descriptor. The block-based descriptor represents the micro-orientation and micro-geometric structure information. The pixel-based descriptor represents texture information. We validate our descriptors on two public databases, and the results show that our descriptors perform well with a relatively low dimensionality.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.11a
• /
• pp.16-18
• /
• 2017

최근 딥 러닝의 발전으로 얼굴인식뿐만 아니라 더 세부적인 기술인 ID식별, 감정인식 등을 분류할 수 있는 알고리즘이 많이 제안되었다. 하지만 딥 러닝은 방대한 연산량을 처리해야 하기 때문에 실시간으로 영상을 구현하는 것은 한계가 있다. 본 논문은 위와 같은 문제를 개선하기 위하여 얼굴인식은 연산량이 비교적 적은 HOG알고리즘을 적용하여 전처리를 진행한다. 그 이후 ID식별 네트워크인 FaceNet과 EmotiW 2017 Challenge의 논문의 감정인식 네트워크를 Multi-Thread 기술을 적용하여 스레드를 분할 연산을 통하여 실시간으로 영상을 출력하는 알고리즘을 제안한다.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.12
• /
• pp.17-25
• /
• 2017

In this paper, we have implemented a low-cost mobile robot supporting the person tracking by detection using RGB-D cameras and ROS(Robot Operating System) framework. The mobile robot was developed based on the Kobuki mobile base equipped with 2's Kinect devices and a high performance controller. One kinect device was used to detect and track the single person among people in the constrained working area by combining point cloud data filtering & clustering, HOG classifier and Kalman Filter-based estimation successively, and the other to perform the SLAM-based navigation supported in ROS framework. In performance evaluation, the person tracking by detection was proved to be robustly executed in real-time, and the navigation function showed the accuracy with the mean distance error being lower than 50mm. The mobile robot implemented has a significance in using the open-source based, general-purpose and low-cost approach.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.42
• /
• pp.61-67
• /
• 2000

Composting of hog manure amended with sawdust trials lasted three weeks and used pilot-scale in bin composting system. Results showed that the rise temperature and carbon dioxide evolution in compost during the composting decomposition process were affected by the aeration method, pH, C/N, moisture content, bulk density and particle size distribution. No significant differences existed in biophysical properties of the composit produced from the continuous and intermittent aeration method. The intermittent aeration was very successful in compost odor control and required less time to reach stability than the continuous aeration.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.49-51
• /
• 2018

미국과 중국 그리고 일부 유럽국가에서는 교통혼잡 해결하기 위해 2인 이상 탑승한 차량만 운행 가능한 다인승 전용차로(HOV, High Occupancy Vehicle Lanes)를 도입하여 운영하고 있다. HOV를 도입한 도시에서는 나 홀로 운행 차량이 많이 감소 되어 교통 혼잡 문제를 조금이나마 해결 할 수 있었다. 현재 HOV에서는 차량 내부의 탑승 인원수를 확인하기 위한 시스템을 사용하고 있다. 기존의 해당 시스템은 HOV에 지나간 차량을 자동으로 적외선 카메라를 통해 촬영하여 사람이 직접 검수하는 방식이다. 기존 방식은 사람이 직접 검사하는 방식이라 이를 위한 많은 인력과 시간이 소모되는 점, 그리고 사람마다 확인한 결과가 다를 수 있는 등 여러 가지 단점이 있다. 본 논문에서는 기존 HOV의 차량 내부 탑승 인원 확인 기술의 여러 단점을 극복하기 위해 Deep Learning과 Computer Vision을 이용한 새로운 기술 설계를 위한 연구한 내용을 다룬다.

• Journal of the East Asian Society of Dietary Life
• /
• v.2 no.2
• /
• pp.201-220
• /
• 1992

To analyze royal nad Chinese envoy procession, and sacrificial rite of Chinese envoy for Choson Dynasty, the author studied historic book-Youngjeob Dogam Sajechong Euigwae of Choson Dynasty(1609 year) in which Chinese envoy procession for sacrificial rite in Choson Dynasty were described. The results obtained from this study were as follows. 1. Sacrificial rite of Chinese envoy for Choson Dynasty were Yellow paper burning and performing a sacrificial rite of chinese envoy. 2. Order of Chinese envoy procession for Yellow paper burng and performint a sacrificial rite of Chinese envoy, was civil and military officers, flag procession, drum, palanquin of incense, palanquin of guneral oration, palaquin of material for guneral expenses, palanquin of rich viands and sumptuous fare and Chinese envoy. 3. Things offered in sacrifice of Yellow paper burning were fried cake made of wheat flour, honey and oil, fried gutinous rice cake, patterned savory cake, fruits, meat fish and others broil, slices of boiled beef, soup, stew, noodles, 3cups of alcohol, rice cake and water. 4. Things offered in sacrifice of performing a sacrificial rite of Chinese envoy were a cattle, a hog, a sheep, 3 cups of alcohol and etc.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.07a
• /
• pp.83-86
• /
• 2012

본 논문에서는 야간에 보행자인식의 성능 향상을 위한 효율적인 인식 방법을 제안한다. 이 논문은 야간에 차량에 비치 된 Thermal Camera를 이용하여 적외선 영상을 얻은 후, 적응적 thresholding, Histogram Equalization, Morphology Operation, Labelling, HOG및 SVM Training 방법을 사용하여 보행자의 인식율을 높이도록 하였다. 3830개의 training 영상을 사용하였으며 실험결과 우수한 인식 결과를 얻었다.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2365-2367
• /
• 2003

In this paper, we propose the RDC(Robot Design Center) for a network-based personal robot system. The RDC is developed under the new software framework for personal robots. The configuration for each modules in robot and functions of the RDC are described. The concept of standardized and modular program is presented and finally, developing procedures are proposed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.1016-1017
• /
• 2018

사물인터넷 환경에서 획득되는 상황 인지 데이터들 중에 특히 이동 객체에 대한 정보를 담은 데이터는 상황 인지의 여러 응용 분야에 매우 유용하다. 하지만, 실시간으로 보행자를 검출하게 되면 인원이 중첩되거나 보행자가 아닌 사물이 검출 되는 현상이 발생한다. 정확한 보행자 검출을 위해 사물인터넷 환경에서 얻을 수 있는 영상에서 다양한 크기와 위치의 수많은 블록들로부터 HOG를 계산하고 유의미한 블록들을 선별해서 보행자 수를 검출한다. 검출된 보행자 수는 서버에 저장되어 특정 공간의 이용자 수를 알아내는데 사용된다.