• Journal of Korea Multimedia Society
• /
• v.9 no.11
• /
• pp.1435-1444
• /
• 2006

We present an effective and real-time face detection method based on Principal Component Analysis(PCA) and Support Vector Machines(SVMs). We extract simple Haar-like features from training images that consist of face and non-face images, reinterpret the features with PCA, and select useful ones from the large number of extracted features. With the selected features, we construct a face detector using an SVM appropriate for binary classification. The face detector is not affected by the size of a training data set in a significant way, so that it showed 90.1 % detection rates with a small quantity of training data. it can process 8 frames per second for $320{\times}240$ pixel images. This is an acceptable processing time for a real-time system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.10
• /
• pp.2321-2330
• /
• 2015

A variety of studies for indoor positioning are now being in progress due to the limit of GPS that becomes obsolete in the room. However, most of them are based on private wireless networks and the situation is difficult to commercialize them since they are expensive in terms of installation and maintenance costs, non-real-time, and not accurate. This paper applies the mark recognition algorithm used in existing augmented reality applications to the indoor vehicle positioning application. It installs floor marks on the ground, performs the perspective transformation on it and decodes the internal data of the mark and, as a result, it obtains an absolute coordinate. Through the geometric analysis, it obtains current position (relative coordinates) of a vehicle away from the mark and the heading direction of the vehicle. The experiment results show that when installing the marks every 5 meter, an error under about 30 cm occurred. In addition, it is also shown that the mark recognition rate is 43.2% of 20 frames per second at the vehicle speed of 20km/h. Thus, it is thought that this idea is commercially valuable.

• Journal of Broadcast Engineering
• /
• v.18 no.2
• /
• pp.149-158
• /
• 2013

In this paper, we propose a new system which can generate digital holograms for natural color scene. The system consists of both a camera system for capturing images and softwares(SWs) for various image processings. The camera system uses a vertical rig with a depth and a RGB camera and a cold mirror which has the different transmittance according to wavelength for obtaining images with the same view point. The S/W is composed by the engines for processing and servicing the captured images and computer-generated hologram (CGH) for generating digital holograms using general-purpose computing on graphics processing unit (GPGPU). Each algorithm was implemented using C/C++ and CUDA languages, and all engines were integrated in LabView environment. The proposed system can generate 10 digital holographic frames per second using about 6K light sources.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.11C
• /
• pp.1029-1039
• /
• 2009

In this paper, the existing disparity aquisition algorithms were analyzed, on the bases of which a disparity generation technique that is superior in accuracy to the generation time was proposed. Basically it uses a pixel-by-pixel motion estimation technique. It has a merit of possibility of a high-speed operation. But the motion estimation technique has a disadvantage of lower accuracy because it depends on the similarity of the matching window regardless of the distribution characteristics of the texture in an image. Therefore, an enhanced technique to increase the accuracy of the disparity is required. This paper introduced a variable-sized window matching technique for this requirement. By the proposed technique, high accuracies could be obtained at the homogeneous regions and the object edges. A hardware to generate disparity image was designed, which was optimized to the processing speed so that a high throughput is possible. The hardware was designed by Verilog-HDL and synthesized using Hynix $0.35{\mu}m$ CMOS cell library. The designed hardware was operated stably at 120MHz using Cadence NC-VerilogTM and could process 15 frames per second at this clock frequency.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.57-64
• /
• 2009

This paper presents the hardware implementation of the pyramidal KLT(Kanade-Lucas-Tomasi) feature tracker. Because of its high computational complexity, it is not easy to implement a real-time KLT feature tracker using general-purpose processors. A hardware implementation of the pyramidal KLT feature tracker using FPGA(Field Programmable Gate Array) is described in this paper with emphasis on 1) adaptive adjustment of threshold in feature extraction under diverse lighting conditions, and 2) modification of the tracking algorithm to accomodate parallel processing and to overcome memory constraints such as capacity and bandwidth limitation. The effectiveness of the implementation was evaluated over ones produced by its software implementation. The throughput of the FPGA-based tracker was 30 frames/sec for video images with size of $720{\times}480$.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.5
• /
• pp.112-120
• /
• 2013

In this paper, we propose high-performance H.264/AVC CAVLC encoder for UD video real time processing. Statistical values are obtained in one cycle through the parallel arithmetic and logical operations, using non-zero bit stream which represents zero coefficient or non-zero coefficient. To encode codeword per one cycle, we remove recursive operation in level encoding through parallel comparison for coefficient and escape value. In oder to implement high-speed circuit, proposed CAVLC encoder is designed in two-stage {statical scan, codeword encoding} pipeline. Reducing the encoding table, the arithmetic unit is used to encode non-coefficient and to calculate the codeword. The proposed architecture was simulated in 0.13um standard cell library. The gate count is 33.4Kgates. The architecture can support Ultra Definition Video ($3840{\times}2160$) at 100 frames per second by running at 100MHz.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.827-829
• /
• 2016

In this paper, in order to achieve the user's convenience in golf putting during practice, to provide a method of tracking the golf ball using a high speed camera. This is recently, it is to analyze so that you can hit a golf putting part of the leisure sport to enjoy a lot of people accurately. The proposed method, the pixel when using a common USB camera is blurred, since the golf ball detection rate is low and using a high-speed camera capable of measuring up to per second 380 frames. First, by using the Hough transform after pretreatment, to detect a golf ball. Movement path by using the information subsequently detected golf ball, calculating the moving distance and angle. The proposed method result of applying, improved travel route detection rate of the golf ball is improved, the accuracy of the moving distance and angle.

• Journal of Digital Convergence
• /
• v.11 no.7
• /
• pp.157-163
• /
• 2013

In this paper, we propose a vision and depth information based real-time hand gesture interface method using finger joint estimation. For this, the areas of left and right hands are segmented after mapping of the visual image and depth information image, and labeling and boundary noise removal is performed. Then, the centroid point and rotation angle of each hand area are calculated. Afterwards, a circle is expanded at following pattern from a centroid point of the hand to detect joint points and end points of the finger by obtaining the midway points of the hand boundary crossing and the hand model is recognized. Experimental results that our method enabled fingertip distinction and recognized various hand gestures fast and accurately. As a result of the experiment on various hand poses with the hidden fingers using both hands, the accuracy showed over 90% and the performance indicated over 25 fps. The proposed method can be used as a without contacts input interface in HCI control, education, and game applications.

• Journal of IKEEE
• /
• v.16 no.4
• /
• pp.349-355
• /
• 2012

Information technology improves convenience, safety, and performance of automobiles. Recently, a lot of algorithms are studied to provide safety and environment information for driving, and lane detection algorithm is one of them. In this paper, we propose a lane detection algorithm that reduces the amount of calculation by reducing region of interest (ROI) after preprocessing. The proposed algorithm reduces the area of ROI a lot by determining the candidate regions near lane boundaries as V-ROI so that the amount of calculation is reduced. In addition, the amount of calculation can be maintained almost the same regardless of the resolutions of the input images by compressing the images since the lane detection algorithm does not require high resolution. The proposed algorithm is implemented using C++ and OpenCV library and is verified to work at 30 fps for realtime operation.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.12
• /
• pp.1445-1452
• /
• 2013

In this paper, we propose a real-time algorithm for estimating the relative position of a person with respect to a robot (camera) using a monocular camera. The algorithm detects the head and shoulder regions of a person using HOG (Histogram of Oriented Gradient) feature vectors and an SVM (Support Vector Machine) classifier. The size and location of the detected area are used for calculating the relative distance and angle between the person and the camera on a robot. To increase the speed of the algorithm, we use a GPU and NVIDIA's CUDA library; the resulting algorithm speed is ~ 15 Hz. The accuracy of the algorithm is compared with the output of a SICK laser scanner.