• Journal of Electrical Engineering and Technology
• /
• 제12권5호
• /
• pp.2067-2078
• /
• 2017

In this paper, a new face tracking algorithm is proposed. The CamShift (Continuously adaptive mean SHIFT) algorithm shows unstable tracking when there exist objects with similar color to that of face in the background. This drawback of the CamShift is resolved by the proposed algorithm using Kinect's pixel-by-pixel depth information and the skin detection method to extract candidate skin regions in HSV color space. Additionally, even when the target face is disappeared, or occluded, the proposed algorithm makes it robust to this occlusion by the feature point matching. Through experimental results, it is shown that the proposed algorithm is superior in tracking performance to that of existing TLD (Tracking-Learning-Detection) algorithm, and offers faster processing speed. Also, it overcomes all the existing shortfalls of CamShift with almost comparable processing time.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.605-606
• /
• 2008

The distance detection system receives stereo video input through 2 CCD cameras. Using a decoder, the image is changed to the YCbCr4:2:2 format and only the Y signal is saved in the 4*256*8bit shift register of the Dual-Port SRAM. As a result of the matching procedure, the Depth value, which is the distance information, is saved in SRAM, and the Depth Map is made and output to the TFT-LCD screen.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2006년도 한국컴퓨터종합학술대회 논문집 Vol.33 No.1 (A)
• /
• pp.403-405
• /
• 2006

Boolean 회로는 parallel 알고리즘을 위한 단순하면서도 실제적인 모델이다. Chung & Lee은 Boolean 회로 모델에서 볼록 이분할 그래프를 위한 최대 매칭을 찾는 O($log^2n+logn$ loglogn logb)depth와 $O(bn^3)$ size의 알고리즘을 제시하였다. 본 논문에서는 prefix compulsion 및 ASCEND, odd-even-merge의 방법을 이용하여 이를 개선한 O($log^2n$ logb) depth, O($bn^2$ logn) size의 최대 매칭 알고리즘을 제시한다.

• 반도체디스플레이기술학회지
• /
• 제9권2호
• /
• pp.123-126
• /
• 2010

An implementation of modified stereo matching using efficient belief propagation (BP) algorithm is presented in this paper. We do recommend the use of the simple sobel, prewitt edge operator. The application of B band sobel edge operator over image demonstrates result with somewhat noisy (distinct border). When we adopt the only MRF + BP algorithm, however, borders cannot be distinguished due to that the message functions in the BP algorithm is just the mechanism which passes energy data to the only large gap of each Message functions In order to address the abovementioned disadvantageous phenomenon, we use the sobel edge operator + MRF + BP algorithm to distinguish the border that is located between the similar message data. Using edge information, the result shows that our proposed process diminishes the propagation of wrong probabilistic information. The enhanced result is due to that our proposed method effectively reduced errors incurred by ambiguous scene properties.

• 한국기계가공학회지
• /
• 제16권5호
• /
• pp.134-140
• /
• 2017

Shape-from-shading (SFS) or stereo vision algorithms can be utilized to measure the shape of an object with imaging techniques for effective sensing in non-contact measurements. SFS algorithms could reconstruct the 3D information from a 2D image data, offering relatively comprehensive information. Meanwhile, a stereo vision algorithm needs several feature points or lines to extract 3D information from two 2D images. However, to measure the size of an object with a freeform surface, the two algorithms need some additional information, such as boundary conditions and grids, respectively. In this study, a stereo vision scheme using the depth information obtained by shape-from-shading as patterns was proposed to measure the size of an object with a freeform surface. The feasibility of the scheme was proved with an experiment where the images of an object were acquired by a CCD camera at two positions, then processed by SFS, and finally by stereo matching. The experimental results revealed that the proposed scheme could recognize the size and shape of freeform surface fairly well.

• 전자공학회논문지B
• /
• 제32B권11호
• /
• pp.1393-1404
• /
• 1995

For the factory automation(FA) of production or assembly lines, computer vision techniques have been widely used for the recognition and position-control of objects. In this application, it is very important to analyze characteristic features of each object and to find an efficient matching algorithm using the selected features. If the object has regular or homogeneous patterns, the problem is relatively simple. However, If the object is shifted or rotated, and if the depth of the input visual system is not fixed, the problem becomes very complicated. Also, in order to understand and recognize objects with concentric noise patterns, it is more effective to use feature-information represented in polar coordinates than in cartesian coordinates. In this paper, an algorithm for the recognition of objects with concentric circular noise-patterns is proposed. And position-conrtol information is calculated with the matching result. First, a filtering algorithm for eliminating concentric noise patterns is proposed to obtain concentric-feature patterns. Then a shift, rotation and scale invariant alogrithm is proposed for the recognition and position-control of objects uusing invariant feature information. Experimental results indicate the effectiveness of the proposed alogrithm.

• 전자공학회논문지
• /
• 제50권12호
• /
• pp.168-175
• /
• 2013

스테레오 좌우 영상간의 색 일치는 3D 영상을 재현할 때 매우 중요하다. 이를 위해 카메라 세팅 및 촬영 환경을 일치시켜서 스테레오 영상을 획득하더라도 여전히 색 불일치가 나타나게 된다. 이러한 색 불일치는 특성에 따라 전역과 지역적인 색불일치로 구분될 수 있다. 따라서 이들 특성을 고려하여 스테레오 영상의 색을 정확히 일치시킬 수 있는 방법이 필요하다. 본 논문에서는 누적 히스토그램과 3D 거리정보를 이용하여 전역과 지역의 색 불일치를 동시에 보정하는 방법을 제안한다. 먼저 기준이 되는 영상의 누적 히스토그램을 기반으로 한 매칭 함수를 이용하여 전역적으로 발생하는 색 불일치를 보정한다. 다음으로 대응되는 샘플 특징점 간의 CD-LUT(color difference look-up table)을 구성하고, disparity map을 통한 3D 거리 정보를 기반으로 한 샘플 특징점의 유사성을 기준으로 가중치를 적용하여 지역적인 색 일치를 수행한다. 마지막으로 전역적인 보정과 지역적인 보정된 영상을 결합함으로서 스테레오 영상에서 나타나는 색 불일치를 보정하였다. 색차가 발생한 스테레오 영상에 대해 기존 색 일치 방법과 제안한 방법을 비교하기 위하여 색상 유사도를(hue similarity)와 MOS(mean opinion scores) 이용하여 평가하였다. 실험 결과에서 제안한 방법을 통한 결과 영상이 기존 방법을 통한 결과 영상보다 더 높은 수치를 나타냄을 알 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권7호
• /
• pp.2585-2598
• /
• 2015

Hand posture recognition has played a very important role in Human Computer Interaction (HCI) and Computer Vision (CV) for many years. The challenge arises mainly due to self-occlusions caused by the limited view of the camera. In this paper, a robust hand posture recognition approach based on 3D point cloud from two RGB-D sensors (Kinect) is proposed to make maximum use of 3D information from depth map. Through noise reduction and registering two point sets obtained satisfactory from two views as we designed, a multi-viewed hand posture point cloud with most 3D information can be acquired. Moreover, we utilize the accurate reconstruction and classify each point cloud by directly matching the normalized point set with the templates of different classes from dataset, which can reduce the training time and calculation. Experimental results based on posture dataset captured by Kinect sensors (from digit 1 to 10) demonstrate the effectiveness of the proposed method.

• Journal of Communications and Networks
• /
• 제18권5호
• /
• pp.837-845
• /
• 2016

Providing a customer with tailored location-based services (LBSs) is a fundamental problem. For location-estimation techniques with radio-based measurements, LBS applications are widely available for mobile devices (MDs), such as smartphones, enabling users to run multi-task applications. LBS information not only enables obtaining the current location of an MD but also provides real-time push-pull communication service. For indoor environments, localization technologies based on radio frequency (RF) pattern-matching approaches are accurate and commonly used. However, to survey radio information for pattern-matching approaches, a considerable amount of time and work is spent in indoor environments. Consequently, in order to reduce the system-deployment cost and computing complexity, this article proposes an indoor positioning approach, which involves using Asus Xtion to facilitate capturing RF signals during an offline site survey. The depth information obtained using Asus Xtion is utilized to estimate the locations and predict the received signal strength (RF information) at uncertain locations. The proposed approach effectively reduces not only the time and work costs but also the computing complexity involved in determining the orientation and RF during the online positioning phase by estimating the user's location by using a smartphone. The experimental results demonstrated that more than 78% of time was saved, and the number of samples acquired using the proposed method during the offline phase was twice as much as that acquired using the conventional method. For the online phase, the location estimates have error distances of less than 2.67 m. Therefore, the proposed approach is beneficial for use in various LBS applications.

• 전자공학회논문지
• /
• 제50권5호
• /
• pp.191-198
• /
• 2013

본 논문은 스테레오 동영상에서 깊이 정보와 움직임 정보를 이용하여 좌영상과 우영상이 바뀐 것을 검출하는 기법을 제안한다. 스테레오 정합 기법을 통해 깊이 정보를 얻어 영상을 전경과 배경 영역으로 나누고 움직임 추정 기법을 이용해 움직임 벡터를 얻는다. 제안 기법은 전경이 인접한 배경 쪽으로 움직이거나 배경이 인접한 전경 쪽으로 움직였을 때 가려짐이 발생하는 영역이 배경이라는 것을 이용한다. 그러나 좌영상과 우영상이 바뀐 경우에는 깊이 정보가 반대로 얻어져 전경과 배경 영역도 반대로 얻어지므로 위와 같은 움직임이 있을 경우에 가려짐이 발생하는 영역은 전경이다. 따라서 좌영상과 우영상이 바뀐 것을 검출할 수 있다. 모의실험을 통해 제안 기법이 전경에 의해 배경 영역이 충분히 가려지는 경우 높은 검출률을 보임을 알 수 있다.