• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.365-380
• /
• 2022

The target detection algorithm based on supervised learning is the current mainstream algorithm for target detection. A high-quality dataset is the prerequisite for the target detection algorithm to obtain good detection performance. The larger the number and quality of the dataset, the stronger the generalization ability of the model, that is, the dataset determines the upper limit of the model learning. The convolutional neural network optimizes the network parameters in a strong supervision method. The error is calculated by comparing the predicted frame with the manually labeled real frame, and then the error is passed into the network for continuous optimization. Strongly supervised learning mainly relies on a large number of images as models for continuous learning, so the number and quality of images directly affect the results of learning. This paper proposes a dataset STAR-24K (meaning a dataset for Space TArget Recognition with more than 24,000 images) for detecting common targets in space. Since there is currently no publicly available dataset for space target detection, we extracted some pictures from a series of channels such as pictures and videos released by the official websites of NASA (National Aeronautics and Space Administration) and ESA (The European Space Agency) and expanded them to 24,451 pictures. We evaluate popular object detection algorithms to build a benchmark. Our STAR-24K dataset is publicly available at https://github.com/Zzz-zcy/STAR-24K.

• Journal of IKEEE
• /
• v.18 no.4
• /
• pp.636-644
• /
• 2014

This paper is to technically implement the sensing platform for Home-Wellness Robot. First, self-localization technique is based on a smart home and object in a home environment, and IOT(Internet of Thing) between Home Wellness Robots. RF tag is set in a smart home and the absolute coordinate information is acquired by a object included RF reader. Then bluetooth communication between object and home wellness robot provides the absolute coordinate information to home wellness robot. After that, the relative coordinate of home wellness robot is found and self-localization through a stereo camera in a home wellness robot. Second, this paper proposed fuzzy control methode based on a vision sensor for approach object of home wellness robot. Based on a stereo camera equipped with face of home wellness robot, depth information to the object is extracted. Then figure out the angle difference between the object and home wellness robot by calculating a warped angle based on the center of the image. The obtained information is written Look-Up table and makes the attitude control for approaching object. Through the experimental with home wellness robot and the smart home environment, confirm performance about the proposed self-localization and posture control method respectively.

• Journal of Korea Multimedia Society
• /
• v.17 no.9
• /
• pp.1076-1083
• /
• 2014

We propose an emotional facial avatar that portrays the user's facial expressions with an emotional emphasis, while achieving visual and behavioral realism. This is achieved by unifying automatic analysis of facial expressions and animation of realistic 3D faces with details such as facial hair and hairstyles. To augment facial appearance according to the user's emotions, we use emotional templates representing typical emotions in an artistic way, which can be easily combined with the skin texture of the 3D face at runtime. Hence, our interface gives the user vision-based control over facial animation of the emotional avatar, easily changing its moods.

• Proceedings of the Korean Society for Quality Management Conference
• /
• 1998.11a
• /
• pp.143-155
• /
• 1998

Many leading companies know that the best quality dominates the world economy in the next 21 century and Six Sigma Program of Motorola Corporation could be considered as a typical model for it. Six Sigma Program is based on the quantitative analysis and the professional qualify manager's training. In fact, this program is a strategy to accomplish the total quality innovation by applying the standardized quality control techniques to the manufacturing or non-manufacturing operation parts. Since many companies recognized their successes and vision, leading domestic companies are very much interested in establishing and driving this program. However, they must understand the meaning of the program correctly and prepare the practicing strategy sufficiently, since there are many differences in ways to drive between other quality program such as TQM and Six Sigma Program. Otherwise, it should lead a big disappointment and another vapour of management paradigm. This study considers the concepts and features of Six Sigma Program of Motorola Corporation and suggest the effective practicing strategy, pointing out the possible problems.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.748-750
• /
• 2004

본 논문은 연속적으로 입력되는 2차원 얼굴 영상에서 얼굴의 특징 영역들을 추출하여 3차원 얼굴 모델의 표정을 실시간으로 제어하는 방법에 관한 연구이다. 2차원 얼굴 영상에서 얼굴을 추출하기 위해 Hue, Saturation 색상 값을 사용하며, 두 가지 색상 값을 이용하여 피부색과 배경색을 분리함으로써 얼굴 영역을 추출 할 수 있다. 추출 된 얼굴에서 특징 영역인 눈 코, 입술 영역 등의 일지를 각각의 영역에 적합한 추출 방법을 이용하여 추출한 뒤, 프레임 별로 영역들의 움직임을 비교함으로써 영역의 움직임 정보를 획득 할 수 있다. 이 정보를 3차원 얼굴 모델에 적용하여 2차원 동영상에서 획득된 대상의 얼굴의 표정을 3차원 얼굴 모델에 실시간으로 표현 할 수 있도록 한다.

• Journal of the Korea Safety Management & Science
• /
• v.15 no.4
• /
• pp.317-321
• /
• 2013

Due to growth of electronics and control devices, automation and situational awareness systems have been applied by automobile. Vision systems with the introduction of unmanned system were being actively developed. In this paper, the distortion in the 7-inch LCD screen for the treatment process are divided into Online and Offline processing. Offline processing based on the image signal processing and for generating LUT Online to Offline generated by processing the distortion is applied to the LUT. LUT is applied to distort the image processing in real time, so that distortion correction is made for the purpose of setting.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.379-382
• /
• 1997

This paper introduces a new vision technique for extracting roof edges of polyhedra having specularly reflecting surfaces. There have been many previous works on object recognition using edge information. But they can not be applied to specular objects since it is hard to acquire reliable camera images of specular objects. If there is a method which can extract the edges of specular objects, it is possible to apply edge-based recognition algorithms to specular objects. To acquire the reliable edge images of specular objects, scanned double pass retroreflection method is proposed, whose main physical characteristic is curvature-sensitive. This utility of the physical characteristic is motivated by the idea that roof edges can be characterized as local surfaces of high curvature. In this paper, the optical characteristics of double pass retroreflection are discussed and a series of simulation studies are performed to verify and analyze the sensor characteristics. The results from a series of simulations show the effectiveness of the proposed method.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1617-1620
• /
• 1997

This paper describes the camera caliberation based-neural network with a camera modeling that accounts for major sources of camera distortion, namely, radial, decentering, and thin prism distortion. Radial distoriton causes an inward or outward displacement of a given image point from its ideal location. Actual optical systems are subject to various degrees of decentering, that is the optical centers of lens elements are not strictly collinear. Thin prism distortion arises from imperfection in lens design and manufacturing as well as camera assembly. It is our purpose to develop the vision system for the pattern recognition and the automatic test of parts and to apply the line of manufacturing. The performance of proposed camera aclibration is illustrated by simulation and experiment.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1140-1145
• /
• 2003

Image normalization is one of the important areas in pattern recognition. Also, log-polar images are useful in the sense that their image data size is reduced dramatically comparing with conventional images and it is possible to develop faster pattern recognition algorithms. Especially, the log-polar image is very similar with the structure of human eyes. However, there are almost no researches on pattern recognition using the log-polar images while a number of researches on visual tracking have been executed. We propose an image normalization technique of log-polar images using momentums applicable for affine-invariant pattern recognition. We handle basic distortions of an image including translation, rotation, scaling, and skew of a log-polar image. The algorithm is experimented in a PC-based real-time vision system successfully.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.12 no.2
• /
• pp.127-138
• /
• 2012

In this paper, we propose a real-time virtual re-convergence hardware platform especially to reduce the visual fatigue caused by stereoscopy. Our unique idea to reduce visual fatigue is to utilize the virtual re-convergence based on the optimized disparity-map that contains more depth information in the negative disparity area than in the positive area. Our virtual re-convergence hardware platform, which consists of image rectification, disparity estimation, depth post-processing, and virtual view control, is realized in real time with 60 fps on a single Xilinx Virtex-5 FPGA chip.