• Journal of Korea Multimedia Society
• /
• v.8 no.4
• /
• pp.461-472
• /
• 2005

In this paper, we propose face feature extraction algorithm through stereo image's matching value. The proposed algorithm detected face region by change the RGB color space of skin color information to the YCbCr color space. Applying eye-template from extracted face region geometrical feature vector of feature about distance and lean, nose and mouth between eye extracted. And, Proposed method could do feature of eyes, nose and mouth through stereo image's matching as well as 2D feature information extract. In the experiment, the proposed algorithm shows the consistency rate of 73% in distance within about 1m and the consistency rate of 52%in distance since about 1m.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.499-508
• /
• 2023

In this paper, we propose a technique to estimate the coordinates of feature points existing on a 2D planar object in the three dimensional space. The proposed method detects multiple 3D features from the image, and excludes those which are not located on the plane. The proposed technique estimates the planar homography between the planar object in the 3D space and the camera image plane, and computes back-projection error of each feature point on the planar object. Then any feature points which have large error is considered as off-plane points and are excluded from the feature estimation phase. The proposed method is archived on the basis of the planar homography without any additional sensors or optimization algorithms. In the expretiments, it was confirmed that the speed of the proposed method is more than 40 frames per second. In addition, compared to the RGB-D camera, there was no significant difference in processing speed, and it was verified that the frame rate was unaffected even in the situation that the number of detected feature points continuously increased.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.472-474
• /
• 2011

본 논문에서는 특징점 기반 색상보정을 이용한 다시점 비디오 부호화 전처리 방법을 제안 한다. 다시점 영상은 조명 및 카메라 간의 특성차이로 인해 인접 시점 간 색상차를 보인다. 이를 보정하기 위한 여러 가지 방법 중, 본 논문에서는 영상간의 대응되는 특징점들을 기반으로 상대적인 카메라의 특성을 모델링하고 이를 통해 색상을 보정하는 방법을 이용하였다. 대응되는 특징점을 추출하기 위해 Harris 코너 검출법을 사용하였고, 모델링 된 수식의 계수는 가우스-뉴튼 순환 기법으로 추정하였다. 참조 영상을 기준으로 보정해야할 타겟 영상의 색상값을 RGB 성분별로 보정했다. 테스트 영상을 가지고 실험한 결과 제안한 전처리 방법으로 보정을 하였을 경우, 전처리 과정을 거치지 않았을 때보다 화질 및 압축효율이 향상됨을 알 수 있었다. 또한 누적 히스토그램 기반의 전처리 방식과 비교했을 때, PSNR은 성분별로 0.5 dB ~ 0.8dB 정도 올랐고 Bit rate는 14% 정도 절감되는 효과를 확인 하였다.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.6
• /
• pp.66-74
• /
• 2018

Recently, there has been active studies on hand gesture recognition to increase immersion and provide user-friendly interaction in a virtual reality environment. However, most studies require specialized sensors or equipment, or show low recognition rates. This paper proposes a hand gesture recognition method using Deep Learning technology without separate sensors or equipment other than camera to recognize static and dynamic hand gestures. First, a series of hand gesture input images are converted into high-frequency images, then each of the hand gestures RGB images and their high-frequency images is learned through the DenseNet three-dimensional Convolutional Neural Network. Experimental results on 6 static hand gestures and 9 dynamic hand gestures showed an average of 92.6% recognition rate and increased 4.6% compared to previous DenseNet. The 3D defense game was implemented to verify the results of our study, and an average speed of 30 ms of gesture recognition was found to be available as a real-time user interface for virtual reality applications.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.215-217
• /
• 2021

본 논문은 3D 공간에서 사용자를 추출한 뒤, 체적 정보 분석을 통한 3D 스켈레톤(skeleton) 분석 과정을 통해 정확도 높은 다수 사용자의 위치 추적 기술에 대해 연구하였다. 이를 위하여 YOLO(You Only Look Once)를 활용하여 실시간으로 객체를 검출(Real-Time Object Detection)한 뒤 Google의 Mediapipe를 활용해 스켈레톤 추출, 스켈레톤 정규화(normalization)를 통한 스켈레톤의 크기 및 상대적 비율 계산, RGB 영상 스케일링(Scaling) 후 주요 마디 인접 영역의 RGB 색상 정보를 추출하는 방법을 통해 정확도가 개선된 높은 성능의 다중 사용자 추적 기술을 연구하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.177-179
• /
• 2021

This paper proposes a method of estimating location of a target point at which an interactive robot gazes in an indoor space. RGB images are extracted from low-cost web-cams, user head pose is obtained from the face detection (Openface) module, and geometric configurations are applied to estimate the user's gaze direction in the 3D space. The coordinates of the target point at which the user stares are finally measured through the correlation between the estimated gaze direction and the plane on the table plane.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.154-155
• /
• 2022

본 논문에서는 RGB-D 카메라 캘리브레이션의 결과를 개선하는 새로운 기법을 제안한다. 멀티 뷰 카메라 캘리브레이션은 카메라를 통해 획득한 이미지에서 특징점을 찾아 다른 카메라에서 촬영된 동일한 특징점을 기준으로 캘리브레이션을 진행하는 것이 일반적이다. 그러나 카메라를 통해 획득된 RGB-D 영상은 필연적으로 렌즈와 Depth senor에 의한 오차가 포함되기 때문에 정확한 캘리브레이션 결과를 획득하는 것은 어려운 과정이다. 본 논문에서는 이를 개선하기 위해 획득한 특징점을 기반으로 캘리브레이션을 진행한 후, 최소제곱법을 통해 각 특징점간의 거리가 최소가 되는 카메라 파라미터를 획득하여 결과를 개선하는 기법을 제안한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.1
• /
• pp.15-31
• /
• 2013

This paper proposes an intermediate image generation method for the viewer's view point by tracking the viewer's face, which is converted to a digital hologram. Its purpose is to increase the viewing angle of a digital hologram, which is gathering higher and higher interest these days. The method assumes that the image information for the leftmost and the rightmost view points within the viewing angle to be controlled are given. It uses a stereo-matching method between the leftmost and the rightmost depth images to obtain the pseudo-disparity increment per depth value. With this increment, the positional informations from both the leftmost view point and the rightmost view point are generated, which are blended to get the information at the wanted intermediate viewpoint. The occurrable dis-occlusion region in this case is defined and a inpainting method is proposed. The results from implementing and experimenting this method showed that the average image qualities of the generated depth and RGB image were 33.83[dB] and 29.5[dB], respectively, and the average execution time was 250[ms] per frame. Also, we propose a prototype system to service digital hologram interactively to the viewer by using the proposed intermediate view generation method. It includes the operations of data acquisition for the leftmost and the rightmost viewpoints, camera calibration and image rectification, intermediate view image generation, computer-generated hologram (CGH) generation, and reconstruction of the hologram image. This system is implemented in the LabView(R) environments, in which CGH generation and hologram image reconstruction are implemented with GPGPUs, while others are implemented in software. The implemented system showed the execution speed to process about 5 frames per second.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.33-41
• /
• 2004

This paper proposes a color matching 3D look-up table simplifying the complex color matching procedure between a monitor and a mobile display device. In other to perform color matching, it is necessary to process color of image in the device independent color space like CIEXYZ or CIELAB. To obtain the data of the device independent color space from that of the device dependent RGB color space, we must perform display characterizations. LCD characterization error using S-curve model is larger than tolerance error since LCD is more nonlinear than CRT. This paper improves the S-curve model to have smaller characterization error than tolerance error using the electro-optical transfer functions of X, Y, and Z value. We obtained images having higher color fidelity on mobile display devices through color matching experiments between monitor and mobile display devices. As a result of this experiments, we concluded that the color matching look-up table with 64(4${\times}$4${\times}$4) is the smallest size allowing characterization error to be acceptable.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.7
• /
• pp.634-640
• /
• 2015

This paper proposes a novel three-dimensional mapping algorithm in Omni-Directional Vision SLAM based on a fisheye image and laser scanner data. The performance of SLAM has been improved by various estimation methods, sensors with multiple functions, or sensor fusion. Conventional 3D SLAM approaches which mainly employed RGB-D cameras to obtain depth information are not suitable for mobile robot applications because RGB-D camera system with multiple cameras have a greater size and slow processing time for the calculation of the depth information for omni-directional images. In this paper, we used a fisheye camera installed facing downwards and a two-dimensional laser scanner separate from the camera at a constant distance. We calculated fusion points from the plane coordinates of obstacles obtained by the information of the two-dimensional laser scanner and the outline of obstacles obtained by the omni-directional image sensor that can acquire surround view at the same time. The effectiveness of the proposed method is confirmed through comparison between maps obtained using the proposed algorithm and real maps.