http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
객체기반 부호화에서의 개선된 움직임 영역 추출 및 추정 기법
정의윤,박영식,송근원,한규필,하영호 한국통신학회 1997 韓國通信學會論文誌 Vol.22 No.9
차세대 부호화 기법중 객체기반 영상부호화 기법은 전형적인 화상전화용 영상에 적합하다. 이 방법에서는 어떤 움직임 모델일 설정하여 영상분석을 하는가에 따라 성능에 큰 영향을 미친다. 본 연구에서는 효율적인 영상분석 알고리즘을 제안하였다. 이전 영상과 현재 영상의 차 영상(frame difference)의 표준편차를 구하여 그 값을 기준으로 배경과 움직임 영역을 추출한다. 창내에서 화소값의 합이 문턱값 이상이며 그 창내의 가운데 점을 움직임 영역으로 간주한다. 추출한 움직임 영역으로부터 움직임 내개변수 구할 때 움직임 영역에서 에지연산자를 사용하여 물체의 영역을 구하여 관찰점(observation point)을 선택하면 올바른 움직임 매개변수를 추정 할 수 있다. 또한, 이전 영상과 현재 영상의 관찰점에서의 변화량 및 인접화소의 변화량을 같이 고려함으로써 잡음의 영향을 줄였다. 그 결과 물체 중심의 관찰점 선택과 잡음의 영향 제거로 움직임 매개변수를 좀더 정확하고 빠르게 구할 수 있었다. 실험결과 제안한 방법이 기존의 방법보다 더 나은 화질을 얻을 수 있었다. The object-oriented coding technique which is one of the coding methods in very low bit rate environment is suitable for videophone image sequence. The selection of source model affect image analysis. In this paper, an image analysis method for the object-oriented coding is presented. The process is composed of changed region detection andmotion estimateion. First, we use the standard deviation of frame difference as thrreshold to extract themoving area. If thesum of gray values in mask is greater than the threshold, the center pixel of the mask is regarded as moving region. After moving is detected in changed region by edge operator, observation point is determined from moving region. The motion is estimated by 6-parameter mapping method with determined observation point. The experimantal resutls show that the proposed method can significantly improve the image quality.
정의윤(Euiyoon Chung),이인식(Insik Lee) 한국자동차공학회 2004 한국자동차공학회 춘 추계 학술대회 논문집 Vol.- No.-
Adaptive cruise control (ACC) systems, which maintain following distance from a preceding vehicle, are available from automobile manufacturers. A distance and relative velocity of the preceding vehicle can be estimated by analyzing a vehicle-mounted millimeter-wave radar signal. Because of a characteristic of the radar and the relative velocity of the preceding vehicle, it is difficult to detect and track the preceding vehicle in the same lane. In this paper, an algorithm is proposed to solve the tracking difficulties. The proposed algorithm separates radar range into some blocks, and detects and tracks a preceding object as a detected block. Applying this algorithm and assigning a priority between the blocks, the searching range for the targeting vehicle and response time of the system are reduced.
정의윤(Euiyoon Chung),정호철(Hochoul Jung),윤형진(Hyungjin Yoon) 한국자동차공학회 2005 한국자동차공학회 춘 추계 학술대회 논문집 Vol.2005 No.5_1
Numerous traffic accidents and dangerous situations arise from careless driving where drivers may not recognize the traffic environment including traffic signals and traffic signs. Recently, various kinds of intelligent systems have been developed to promote driving safety and convenience. In this paper, an algorithm to recognize the traffic signals and traffic signs using an image sensor is proposed and the test results are shown with various road situations and environment. In this algorithm, candidate traffic signals can be chosen by checking the ratios of heights and widths of candidate boxes because the ratios for the traffic signals are standardized. The position of red, yellow, green, and direction sign of the traffic signal is also standardized, so final decision to recognize the traffic signals can be made easily and the colors of the traffic signals are identified based on brightness. Traffic sign can be also recognized using standardized color and shape information and the traffic sign can be identified using a fast and effective pattern recognition algorithm which is appropriate for real time application. The recognized information of traffic signal or traffic sign is informed to driver through display device and speaker.