• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.580-582
• /
• 2000

본 논문에서는 MAM을 이용한 특징 벡터의 보정을 기반으로 하는 헤드 제스처 인식에 관해 기술한다. 제안된 시스템은 얼굴 움직임 검출 모듈과 눈 영역 추적 모듈, 미 측정된 벡터 보정 모듈, 측정된 제스처에 대한 인식모듈로 구성된다. 신경망과 모자이크 이미지를 이용하여 얼굴 영역을 검출하고, 이 영역에서 눈 영역을 검출한다. 만약 눈의 쌍이 검출되지 않는다면 시스템은 특징 벡터 보정(MAM)을 수행하여 손실된 정보를 예측한다. 검출된 눈 영역은 정규화된 벡터로 변경된다. 이 벡터의 분산을 이용하여 긍정, 부정, 중립의 제스처를 판단한다. 제스처의 인식은 직접 관측, 이중 HMM, 삼중 HMM을 사용한 다중 인식기를 이용한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.5
• /
• pp.1119-1128
• /
• 2013

In this paper, we propose an algorithm to detect and track the human face with a GPU-based high speed. Basically the detection algorithm uses the existing Adaboost algorithm but the search area is dramatically reduced by detecting movement and skin color region. Differently from detection process, tracking algorithm uses only depth information. Basically it uses a template matching method such that it searches a matched block to the template. Also, In order to fast track the face, it was computed in parallel using GPU about the template matching. Experimental results show that the GPU speed when compared with the CPU has been increased to up to 49 times.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.135-136
• /
• 2008

본 논문에서는 배경 분리(Background Subtraction) 기법 및 픽셀 농도를 기반으로 조명 환경의 변화에 강인한 도로상 불법 주정차차량을 검출하고, 추적할 수 있는 기법을 제안하였다. 제안된 기법은 영상내 도로변을 관심영역으로 설정하고, 실시간으로 전후 영상을 비교하여 조명변화에 강인한 분별력을 가질 수 있는 적응 배경 모델을 생성한다. 제안 된 픽셀 농도의 수치를 기반으로 변화량이 작은 배경 영역을 제거하고, 상대적으로 큰 변화량을 가지는 차량 영역을 구별할 수 있다. 구별된 대상 차량 영역에 군집 추적 기법을 적용하여 겹쳐신 자동차들 간의 구별이 가능 하도록 하였다. 제안된 기법에 대한 실험은 불법 주정자 단속 카메라로부터 다양한 조명환경에 대한 고려가 가능한 시간대별 영상을 통해 검증하였다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.18 no.2
• /
• pp.19-25
• /
• 2013

In this paper, we propose an approach to tracking road regions from video sequences. The proposed method segments and tracks road regions by utilizing the prior information from the result of the previous frame. For the efficiency of the system, we have a simple assumption that the road region is usually shown in the lower part of input images so that lower 60% of input images is set to the region of interest(ROI). After initial segmentation using flood-fill algorithm, we merge neighboring regions based on color similarity measure. The previous segmentation result, in which seed points for the successive frame are extracted, is used as prior information to segment the current frame. The similarity between the road region of the previous frame and that of the current frame is measured by the modified Jaccard coefficient. According to the similarity we refine and track the detected road regions. The experimental results reveal that the proposed method is effective to segment and track road regions in noisy and non-noisy environments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.239-241
• /
• 2015

본 논문에서는 클러스터 개수를 동적으로 생성하는 개선된 FCM을 적용하여 초음파 영상에서 충수염을 추출하는 방법을 제안한다. 초음파 영상에서 ROI 영역을 추출한 후, Max-Min 기반 이진화 기법을 적용한다. 이진화된 영상에서 근막 영역의 크기가 ROI 영역의 1/3이상을 차지한다는 정보를 이용하여 Labelling 기법을 적용하여 근막 영역을 추출한다. 근막의 최하단 좌표를 이용하여 근막의 하단 영역을 추출한 후, 근막의 하단 영역에서 객체들의 선명도를 높이기 위해 Blurring 기법과 Sharpening 기법을 적용한다. 충수염의 후보 영역을 추출하기 위해 FCM 알고리즘을 개선하여 양자화를 수행한다. 개선된 FCM 알고리즘으로 양자화를 수행하여 충수염의 후보 영역을 추출한다. 추출된 충수염의 후보 영역에서 8방향 윤곽선 추적 기법을 적용하여 객체들을 추출한다. 추출된 객체들 중에서 낮은 명암도를 가지고 초음파 전체 영상 크기의 1/3이하 되는 객체를 충수염으로 추출한다. 초음파 영상을 대상으로 제안된 방법을 적용하여 실험한 결과, 기존의 방법보다 충수염 영역의 추출률이 개선된 것을 확인하였다.

• The Journal of the Korea Contents Association
• /
• v.7 no.8
• /
• pp.94-101
• /
• 2007

In this paper, we propose a surveillance system using multi-person tracking in a WIPI based mobile system, which is the standard wireless internet platform. The proposed system consists of two subsystems: the person tracking system and the mobile information transmission system. The person tracking system tracks persons who invade security and the mobile information transmission system sends the tracking results from the person tracking system to the user's mobile phone. In this paper, the person tracking system tracks persons who appear on many cameras with non-overlapping views in order to achieve a wider view. The mobile information transmission system saves automatically tracked data to the owner's web server and transmits the saved data to the user's WIPI mobile phone. Therefore, whenever the user wishes to view tracked data later, the mobile system can provide the user with the tracking results by either the user selecting particular cameras or the time on the owner's mobile phone. The proposed system is a new surveillance system that transfers tracked data among cameras to the user's mobile phone in order to overcome space limitations in tracking areas and monitoring areas and spatial limitations in monitoring hours.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.781-783
• /
• 2005

본 논문은 손 모양 인식을 이용한 비전 기반의 보행 로봇 제어 시스템을 제안한다. 손의 모양을 인식하기 위해서 움직이는 카메라 영상으로부터 정확한 손의 경계선물 추출하고 추적하는 일이 선행되어야 한다. 따라서 본 논문에서는 민 시프트 방법을 사용한 활성 윤곽선 모델 기반의 추적 방법을 제안한다. 제안된 시스템은 손 추출기, 손 추적기, 손 모양 인식기 그리고 로봇 제어기, 4개의 모들로 구성된다. 손 추출기는 영상에서 미리 정의된 손의 모양을 가지는 피부색 영역을 추출한다. 추출된 손의 추적은 활성 윤관선 모델과 민 시프트 방법을 사용하여 실행된다. 그 후 Hue moments를 사용하여 추적된 손의 모양을 인식한다. 제안된 방법을 평가하기 위해서 본 논문에서는 2족 보행 로봇 KHR-1에 제안된 방법을 적용 한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.10C
• /
• pp.1032-1041
• /
• 2007

The global navigation satellite system (GNSS), which is the core technique for the location based service, adopts the direct sequence/spread spectrum (DS/SS) as its modulation method. The success of a DS/SS system depends on the synchronization between the received and locally generated pseudo noise (PN) signals. As a step in the synchronization process, the tacking scheme performs fine adjustment to bring the phase difference between the two PN signals to zero. The most widely used tracking scheme is the delay locked loop with early minus late discriminator (EL-DLL). In the ideal case, the EL-DLL is the best estimator among various DLL. However, in the band-limited multipath environment, the EL-DLL has tracking bias. In this paper, the timing offset range of correlation function is divided into advanced offset range (AOR) and delayed offset range (DOR) centering around the correct synchronization time point. The tracking bias results from the following two reasons: symmetry distortion between correlation values in AOR and DOR, and mismatch between the time point corresponding to the maximum correlation value and the synchronization time point. The former and latter are named as the type I and type II tracking bias, respectively. In this paper, when the receiver has finite bandwidth in the presence of multipath signals, it is shown that the type II tracking bias becomes a more dominant error factor than the type I tracking bias, and the correlation values in AOR are not almost changed. Exploiting these characteristics, we propose a novel tracking bias mitigation scheme and demonstrate that the tracking accuracy of the proposed scheme is higher than that of the conventional scheme, both in the presence and absence of noise.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.8
• /
• pp.65-75
• /
• 2013

This paper proposes a method of tracking the hand region and detecting the fingertip using only depth images. In order to eliminate the influence of lighting conditions and obtain information quickly and stably, this paper proposes a tracking method that relies only on depth information, as well as a method of using region growing to identify errors that can occur during the tracking process and a method of detecting the fingertip that can be applied for the recognition of various gestures. First, the closest point of approach is identified through the process of transferring the center point in order to locate the tracking point, and the region is grown from that point to detect the hand region and boundary line. Next, the ratio of the invalid boundary, obtained by means of region growing, is used to calculate the validity of the tracking region and thereby judge whether the tracking is normal. If tracking is normal, the contour line is extracted from the detected hand region and the curvature and RANSAC and Convex-Hull are used to detect the fingertip. Lastly, quantitative and qualitative analyses are performed to verify the performance in various situations and prove the efficiency of the proposed algorithm for tracking and detecting the fingertip.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.5
• /
• pp.1171-1176
• /
• 2014

The eye-tracking [ET] is used on the human computer interaction [HCI] analysing the movement status as well as finding the gaze direction of the eye by tracking pupil's movement on a human face. Nowadays, the ET is widely used not only in market analysis by taking advantage of pupil tracking, but also in grasping intention, and there have been lots of researches on the ET. Although the vision based ET is known as convenient in application point of view, however, not robust in changing environment such as illumination, geometrical rotation, occlusion and scale changes. This paper proposes two steps in the ET, at first, face and eye regions are discriminated by Haar classifier on the face, and then the pupils from the discriminated eye regions are tracked by CAMShift as well as Template matching. We proved the usefulness of the proposed algorithm by lots of real experiments in changing environment such as illumination as well as rotation and scale changes.