• 융합신호처리학회논문지
• /
• 제21권2호
• /
• pp.55-60
• /
• 2020

본 논문에서는 우선순위와 문턱치를 가지고 최적 후보의 조기 탐지를 이용한 움직임 추정의 고속 블록 매칭 알고리즘을 제안한다. 전 영역 탐색(full search) 알고리즘의 계산량을 줄이기 위해 많은 고속 움직임 추정 알고리즘이 발표되었지만, 여전히 움직임 추정 성능을 향상시키기 위한 많은 연구가 보고되고 있다. 제안된 알고리즘은 이전 부분 매칭 오류에서 우선순위가 높은 각 후보에 대한 블록 매칭 오류를 계산한다. 제안된 알고리즘은 대부분의 기존 고속 블록 매칭 알고리즘에 추가적으로 적용하여 속도를 높일 수 있다. 그렇게 함으로써 최소 오류 지점을 조기에 찾고 불가능한 후보에 대한 불필요한 계산을 줄임으로써 속도를 높일 수 있다. 제안된 알고리즘은 전 영역 탐색 알고리즘과 동일한 예측 화질을 가지면서 기존의 고속 무손실 탐색 알고리즘보다 적은 계산을 사용한다. 실험결과로서, 제안된 알고리즘은 예측 화질 저하 없이 PDE 및 전 영역 탐색 방법의 계산에 비해 30 ~ 70%까지 줄일 수 있으며, 다른 고속 손실 알고리즘을 사용하면 더욱 감소시키는 것으로 나타났다.

• 한국멀티미디어학회논문지
• /
• 제18권4호
• /
• pp.437-442
• /
• 2015

Voice activity detection is very important process that voice activity separated form noisy speech signal for speech enhance. Over the past few years, many studies have been made on voice activity detection, but it has poor performance in low signal to noise ratio environment or fickle noise such as car noise. In this paper, it proposed new voice activity detection algorithm using ensemble variance based on wavelet band entropy and soft thresholding method. We conduct a survey in a lot of signal to noise ratio environment of car noise to evaluate performance of the proposed algorithm and confirmed performance of the proposed algorithm.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제12권1호
• /
• pp.60-65
• /
• 2012

This paper presents a method for occluded object based motion estimation and tracking system in dynamic image sequences using particle filter with 3D reconstruction. A unique characteristic of this study is its ability to cope with partial occlusion based continuous motion estimation using particle filter inspired from the mirror neuron system in human brain. To update a prior knowledge about the shape or motion of objects, firstly, fundamental 3D reconstruction based occlusion tracing method is applied and object landmarks are determined. And optical flow based motion vector is estimated from the movement of the landmarks. When arbitrary partial occlusions are occurred, the continuous motion of the hidden parts of object can be estimated by particle filter with optical flow. The resistance of the resulting estimation to partial occlusions enables the more accurate detection and handling of more severe occlusions.

• 한국군사과학기술학회지
• /
• 제7권2호
• /
• pp.22-31
• /
• 2004

In this paper, the measurements preprocessing algorithm for the fading of bearing and frequency measurements is proposed, which can improve the performance of BFTMA(Bearing and Frequency Target Motion Analysis). The fading and detection relation between bearing and frequency are rigorously established for measurements preprocessing, and BFTMA can be carried out the estimation of target motion by using measurements preprocessing. Batch estimation with bearing and frequency using the proposed algorithm can be applied to estimate the initial target states despite of the fading of frequency measurement. Simulation results show that BFTMA using the proposed measurements preprocessing has superior estimation performance, compared with batch estimation using only bearing measurements.

• 산업기술연구
• /
• 제21권B호
• /
• pp.91-98
• /
• 2001

In this paper, center detection and motion analysis of a moving object are studied. Kohonen's self-organizing neural network models are used for the moving objects tracking and time delay neural networks are used for dynamic characteristic analysis. Instead of objects brightness, neuron projections by Kohonen Networks are used. The motion of target objects can be analyzed by using the differential neuron image between the two projections. The differential neuron image which is made by two consecutive neuron projections is used for center detection and moving objects tracking. The two differential neuron images which are made by three consecutive neuron projections are used for the moving trajectory estimation. It is possible to distinguish 8 directions of a moving trajectory with two frames and 16 directions with three frames.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권2호
• /
• pp.173-181
• /
• 2004

본 논문에서는 움직이는 카메라로부터 획득한 연속영상에서 이동물체를 자동으로 검출하고 추적하는 시스템을 제안한다. 제안된 방법은 크게 이동물체 검출과 추적과정으로 나뉘어진다. 이동물체는 BBME(block-based motion estimation)와 DD(double difference)를 통합한 방법을 이용하여 검출된다. 검출된 이동물체는 히스토그램 백 프로젝션을 통하여 분할되며, 히스토그램 인터섹션과 XY-프로젝션을 사용하여 대상물체를 정합하고 추적된다. 본 논문에서는 컴퓨터 모의실험을 통하여 제안된 방법이 움직이는 카메라로부터 획득된 영상에서 이동물체를 검출하고 큰 오차 없이 추적함을 보였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1988년도 한국자동제어학술회의논문집(국내학술편); 한국전력공사연수원, 서울; 21-22 Oct. 1988
• /
• pp.178-182
• /
• 1988

In this study, the motion compensating interpolation algorithm is presented. The presented algorithm allows the unblutted reconstruction of omitted frames. It is shown that the Walker & Rao's estimation algorithm using modified displaced frame difference combined with rectangulat adaptive measurement window increases the reliability of the estimation results. The remark ably improved image quality is achieved by change detection and segmentation.

• 한국항공우주학회지
• /
• 제34권5호
• /
• pp.81-87
• /
• 2006

본 논문에서는 전투기 조종석과 같은 제한된 공간에서 사용 가능한 광학 방식의 헤드 트랙커 시스템을 설계하고 그 성능을 시험하였다. 이 시스템은 다른 빛의 간섭을 차단하기 위해 적외선 발광다이오드와 두 대의 적외선 CCD 카메라를 사용하였다. 그리고 광학 방식의 헤드 트랙커 알고리즘은 특징점 추출 알고리즘과 3차원 움직임 추정 알고리즘으로 구성하였다. 카메라 이미지 평면 위에서 특징점의 2차원 위치 좌표를 획득하기 위한 특징점 추출 알고리즘은 디지털 영상 처리 기술인 문턱치 (thresholding)와 마스킹 (masking) 기법을 사용하였다. 특징점의 위치 변화로부터 조종사의 머리 움직임을 추정하는 3차원 움직임 추정 알고리즘은 확장 칼만 필터 (EKF)를 사용하였다. 또한, 정밀한 레이트 테이블을 사용하여 시스템 성능을 검증하고 회전 성능에 대해 관성 센서와 비교하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권11호
• /
• pp.2191-2203
• /
• 2011

In this paper, we propose a fast and robust algorithm for fighting behavior detection based on Motion Vectors (MV), in order to solve the problem of low speed and weak robustness in traditional fighting behavior detection. Firstly, we analyze the characteristics of fighting scenes and activities, and then use motion estimation algorithm based on block-matching to calculate MV of motion regions. Secondly, we extract features from magnitudes and directions of MV, and normalize these features by using Joint Gaussian Membership Function, and then fuse these features by using weighted arithmetic average method. Finally, we present the conception of Average Maximum Violence Index (AMVI) to judge the fighting behavior in surveillance scenes. Experiments show that the new algorithm achieves high speed and strong robustness for fighting behavior detection in surveillance scenes.

• 스마트미디어저널
• /
• 제6권3호
• /
• pp.49-56
• /
• 2017

Images and Videos that include the human face contain a lot of information. Therefore, accurately extracting human face is a very important issue in the field of computer vision. However, in real life, human faces have various shapes and textures. To adapt to these variations, A model-based approach is one of the best ways in which unknown data can be represented by the model in which it is built. However, the model-based approach has its weaknesses when the motion between two frames is big, it can be either a sudden change of pose or moving with fast speed. In this paper, we propose an enhanced human face-tracking model. This approach included human face detection and motion estimation using Cascaded Convolutional Neural Networks, and continuous human face tracking and modeling correction steps using the Active Appearance Model. A proposed system detects human face in the first input frame and initializes the models. On later frames, Cascaded CNN face detection is used to estimate the target motion such as location or pose before applying the old model and fit new target.