• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.8
• /
• pp.1908-1918
• /
• 2013

Free-view, auto-stereoscopic video service is a next generation broadcasting system which offers a three-dimensional video, images of the various point are needed. This paper proposes a method that parallelizes the algorithm for arbitrary intermediate view-point image fast generation and make it faster using General Propose Graphic Processing Unit(GPGPU) with help of the Compute Unified Device Architecture(CUDA). It uses a parallelized stereo-matching method between the leftmost and the rightmost depth images to obtain disparity information and It use data calculated disparity increment per depth value. The disparity increment is used to find the location in the intermediate view-point image for each depth in the given images. Then, It is eliminate to disocclusions complement each other and remaining holes are filled image using hole-filling method and to get the final intermediate view-point image. The proposed method was implemented and applied to several test sequences. The results revealed that the quality of the generated intermediate view-point image corresponds to 30.47dB of PSNR in average and it takes about 38 frames per second to generate a Full HD intermediate view-point image.

• Journal of IKEEE
• /
• v.25 no.2
• /
• pp.243-251
• /
• 2021

In this paper, we propose a measurement technique of indoor location based on markerless applicable to AR. The proposed technique has the following originality. The first is to extract feature points and use them to generate local patches to enable faster computation by learning and using only local patches that are more useful than the surroundings without learning the entire image. Second, learning is performed through deep learning using the convolution neural network structure to improve accuracy by reducing the error rate. Third, unlike the existing feature point matching technique, it enables indoor location measurement including left and right movement. Fourth, since the indoor location is newly measured every frame, errors occurring in the front side during movement are prevented from accumulating. Therefore, it has the advantage that the error between the final arrival point and the predicted indoor location does not increase even if the moving distance increases. As a result of the experiment conducted to evaluate the time required and accuracy of the measurement technique of indoor location based on markerless applicable to AR proposed in this paper, the difference between the actual indoor location and the measured indoor location is an average of 12.8cm and a maximum of 21.2cm. As measured, the indoor location measurement accuracy was better than that of the existing IEEE paper. In addition, it was determined that it was possible to measure the user's indoor location in real time by displaying the measured result at 20 frames per second.

• Journal of KIISE
• /
• v.44 no.9
• /
• pp.932-945
• /
• 2017

In this paper, a new hardware and software architecture for a stereo vision processing system including rectification, disparity estimation, and visualization was developed. The developed method, named LArge scale stereo matching method using Support Point Interpolation (LASPI), shows excellence in real-time processing for obtaining dense disparity maps from high quality image regions that contain high density support points. In the real-time processing of high definition (HD) images, LASPI does not degrade the quality level of disparity maps compared to existing stereo-matching methods such as Efficient LArge-scale Stereo matching (ELAS). LASPI has been designed to meet a high frame-rate, accurate distance resolution performance, and a low resource usage even in a limited resource environment. These characteristics enable LASPI to be deployed to safety-critical applications such as an obstacle recognition system and distance detection system for autonomous vehicles. A Field Programmable Gate Array (FPGA) for the LASPI algorithm has been implemented in order to support parallel processing and 4-stage pipelining. From various experiments, it was verified that the developed FPGA system (Xilinx Virtex-7 FPGA, 148.5MHz Clock) is capable of processing 30 HD ($1280{\times}720pixels$) frames per second in real-time while it generates disparity maps that are applicable to real vehicles.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.6
• /
• pp.145-155
• /
• 2013

In this paper, we proposed a $4{\times}4$ block parallel architecture of interpolation for high-performance H.264/AVC Fractional Motion Estimation in 8K UHD($7680{\times}4320$) video real time processing. To improve throughput, we design $4{\times}4$ block parallel interpolation. For supplying the $10{\times}10$ reference data for interpolation, we design 2D cache buffer which consists of the $10{\times}10$ memory arrays. We minimize redundant storage of the reference pixel by applying the Search Area Stripe Reuse scheme(SASR), and implement high-speed plane interpolator with 3-stage pipeline(Horizontal Vertical 1/2 interpolation, Diagonal 1/2 interpolation, 1/4 interpolation). The proposed architecture was simulated in 0.13um standard cell library. The gate count is 436.5Kgates. The proposed H.264/AVC Fractional Motion Estimation can support 8K UHD at 30 frames per second by running at 187MHz.

• Journal of Internet Computing and Services
• /
• v.18 no.3
• /
• pp.29-36
• /
• 2017

In these days, 3D dynamic simulation is closely related to many industries. In the past, physically-based 3D simulation was used mainly in the car crash or construction related fields, but it also plays an important role in movies or games today. Many mathematical computations are needed to represent the 3D object realistically, but it is difficult to process a large amount of calculations for simulation of application based on CPU in real-time. Recently, with the advanced graphic hardware and improved architecture, GPU can be utilized for the general purposes of computation function as well as graphic computation. Many approaches using GPU have been applied for various research fields. In this paper, we analyze the performance variation of two cloth simulation algorithms based on GPU according to the change of execution properties of GPU shaders in oder to optimize the performance of GPU-based cloth simulation. Cloth simulation is implemented by the spring centric algorithm and node centric algorithm with GPU parallel computing using compute shader of GLSL 4.3. We compare the performance of between these algorithms according to the change of the size and dimension of work group. The experiment is repeated to 10 times during 5,000 frames for each test and experimental results are provided by averaging of FPS. The experimental result shows that the node centric algorithm is executed in higher speed than the spring centric algorithm.

• Journal of Broadcast Engineering
• /
• v.11 no.1 s.30
• /
• pp.80-90
• /
• 2006

A simple 2D gaze tracking method using single camera and Purkinje image is proposed. This method employs single camera with infrared filter to capture one eye and two infrared light sources to make reflection points for estimating corresponding gaze point on the screen from user's eyes. Single camera, infrared light sources and user's head can be slightly moved. Thus, it renders simple and flexible system without using any inconvenient fixed equipments or assuming fixed head. The system also includes a simple and accurate personal calibration procedure. Before using the system, each user only has to stare at two target points for a few seconds so that the system can initiate user's individual factors of estimating algorithm. The proposed system has been developed to work in real-time providing over 10 frames per second with XGA $(1024{\times}768)$ resolution. The test results of nine objects of three subjects show that the system is achieving an average estimation error less than I degree.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.6
• /
• pp.201-211
• /
• 2013

In this paper, we propose a hand tracking and gesture recognition system. Our system employs a depth capture device to obtain 3D geometric information of user's bare hand. In particular, we build a flexible tracking volume and restrict the hand tracking area, so that we can avoid diverse problems caused by conventional object detection/tracking systems. The proposed system computes running average of the hand position, and tracking volume is actively adjusted according to the statistical information that is computed on the basis of uncertainty of the user's hand motion in the 3D space. Once the position of user's hand is obtained, then the system attempts to detect stretched fingers to recognize finger gesture of the user's hand. In order to test the proposed framework, we built a NUI system using the proposed technique, and verified that our system presents very stable performance even in the case that multiple objects exist simultaneously in the crowded environment, as well as in the situation that the scene is occluded temporarily. We also verified that our system ensures running speed of 24-30 frames per second throughout the experiments.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.116-128
• /
• 2011

In this paper, we propose the structure of a high-performance face-detection engine that responds well to facial rotating changes using rotation transformation which minimize the required memory usage compared to the previous face-detection engine. The validity of the proposed structure has been verified through the implementation of FPGA. For high performance face detection, the MCT (Modified Census Transform) method, which is robust against lighting change, was used. The Adaboost learning algorithm was used for creating optimized learning data. And the rotation transformation method was added to maintain effectiveness against face rotating changes. The proposed hardware structure was composed of Color Space Converter, Noise Filter, Memory Controller Interface, Image Rotator, Image Scaler, MCT(Modified Census Transform), Candidate Detector / Confidence Mapper, Position Resizer, Data Grouper, Overlay Processor / Color Overlay Processor. The face detection engine was tested using a Virtex5 LX330 FPGA board, a QVGA grade CMOS camera, and an LCD Display. It was verified that the engine demonstrated excellent performance in diverse real life environments and in a face detection standard database. As a result, a high performance real time face detection engine that can conduct real time processing at speeds of at least 60 frames per second, which is effective against lighting changes and face rotating changes and can detect 32 faces in diverse sizes simultaneously, was developed.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.48 no.9
• /
• pp.22-30
• /
• 2011

Recently, the rising demand for intelligent video surveillance system leads to high-performance face recognition systems. The solution for low-resolution images acquired by a long-distance camera is required to overcome the distance limits of the existing face recognition systems. For that reason, this paper proposes a hardware design of an image resolution enhancement algorithm for real-time intelligent video surveillance systems. The algorithm is synthesizing a high-resolution face image from an input low-resolution image, with the help of a large collection of other high-resolution face images, called training set. When we checked the performance of the algorithm at 32bit RISC micro-processor, the entire operation took about 25 sec, which is inappropriate for real-time target applications. Based on the result, we implemented the hardware module and verified it using Xilinx Virtex-4 and ARM9-based embedded processor(S3C2440A). The designed hardware can complete the whole operation within 33 msec, so it can deal with 30 frames per second. We expect that the proposed hardware could be one of the solutions not only for real-time processing at the embedded environment, but also for an easy integration with existing face recognition system.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.4
• /
• pp.10-21
• /
• 2008

The present paper propose a real-time moving object recognition and tracking method using the wavelet-based neural network and invariant moments. Candidate moving region detection phase which is the first step of the proposed method detects the candidate regions where a pixel value changes occur due to object movement based on the difference image analysis between continued two image frames. The object recognition phase which is second step of proposed method recognizes the vehicle regions from the detected candidate regions using wavelet neurual-network. From object tracking Phase which is third step the recognized vehicle regions tracks using matching methods of wavelet invariant moments bases to recognized object. To detect a moving object from image sequence the candidate regions detection phase uses an adaptive thresholding method between previous image and current image as result it was robust surroundings environmental change and moving object detections were possible. And by using wavelet features to recognize and tracking of vehicle, the proposed method decrease calculation time and not only it will be able to minimize the effect in compliance with noise of road image, vehicle recognition accuracy became improved. The result which it experiments from the image which it acquires from the general road image sequence and vehicle detection rate is 92.8%, the computing time per frame is 0.24 seconds. The proposed method can be efficiently apply to a real-time intelligence road traffic surveillance system.