• ETRI Journal
• /
• 제37권4호
• /
• pp.766-771
• /
• 2015

Robust motion estimation for human-computer interactions played an important role in a novel method of interaction with electronic devices. Existing pose estimation using a monocular camera employs either ego-motion or exo-motion, both of which are not sufficiently accurate for estimating fine motion due to the motion ambiguity of rotation and translation. This paper presents a hybrid vision-based pose estimation method for fine-motion estimation that is specifically capable of extracting human body motion accurately. The method uses an ego-camera attached to a point of interest and exo-cameras located in the immediate surroundings of the point of interest. The exo-cameras can easily track the exact position of the point of interest by triangulation. Once the position is given, the ego-camera can accurately obtain the point of interest's orientation. In this way, any ambiguity between rotation and translation is eliminated and the exact motion of a target point (that is, ego-camera) can then be obtained. The proposed method is expected to provide a practical solution for robustly estimating fine motion in a non-contact manner, such as in interactive games that are designed for special purposes (for example, remote rehabilitation care systems).

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.807-810
• /
• 2000

In this paper, a new hierarchical motion estimation (ME) scheme using the wavelet transformed multi-resolution image layers is proposed. While the coarse-to-fine (CtF) ME, used in previously proposed coding schemes, can provide a better estimate at the coarsest resolution, it is difficult to accurately track motion at finer resolution. On the other hand, in fine-to-coarse (FtC) ME, it can solves this local minima problem by estimating motion track at the finest subband and propagating the motion vector (MV) to coarser subband. But this method causes to higher computational overhead. This paper proposes a new method for reducing the computational overhead of fine-to-coarse rnulti-resolution motion estimation (MRME) at the finest resolution level by searching for the region to consider motion vectors of the coarsest resolution subband.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.165-168
• /
• 2004

This paper propose a target tracker using phase correlation. The tracker consist of a pre-processing module, a translation estimation module based on phase correlation, a fine motion estimation module applied when confidence rate could not fulfill a threshold value and a reference image update module. The fine motion estimation module measure the shift, rotation and scale of input image compared to reference using Fourier-Mellin transform. Proposed tracker was tested its accuracy and robustness using some real indoor and outdoor image sequences.

• 한국멀티미디어학회논문지
• /
• 제6권1호
• /
• pp.40-47
• /
• 2003

본 논문에서는 저해상도 대역에서의 움직임 벡터를 고려한 고해상도 대역의 영역에서 움직임 탐색을 행함으로써 밀-소 다중해상도 움직임 추정의 과도한 계산량을 줄일 수 있는 새로운 방법을 제안하였다. 또한 정확한 움직임을 찾아서 복원 영상의 화질을 높이기 위해 반화소 단위 움직임 추정을 사용하는데, 많은 계산량이 필요하게 된다. 따라서 본 논문에서는 인접 화소들간의 상관관계를 이용해 오차가 최소가 되는 방향을 예측하여 선택적 보간을 이용하여 계산량을 줄일 수 있었다.

• 전자공학회논문지S
• /
• 제34S권2호
• /
• pp.33-42
• /
• 1997

In this paper, a video coding method in wavelet transformed multi-resolution image using variable block sized motion estimation and multi-codebook is proposed. In the propoed method, the accuracy of motion estimation is increased by using variable block matching algorithm based on edge type of blocks which estimation is increased by using variable block matching algoritm based on edge type of blocks which is classified accoridng to the magnitude of wavelet coefficients in vertical subband and horizontal subband of the highest layer. Also, we increased the flexibility of bit allocation and decreased vector quantization error for motion compensated error transmission by using importance of each subband. Some experimental results confirm that he proposed mothod has fine reconstructed images without blocking effect at low bit rate, and especially reconstructs edges well to which human eyes are sensitive.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.999-1002
• /
• 2002

In this paper, we proposes an adaptive method for reducing the computational overhead of fine-to-coarse MRME at the finest resolution level by considering for the spatial and spectral characteristics between wavelet decomposition levels simultaneously. As we know, there is high correlation between the adjacent blocks and it can give the very important clue to estimate motion at finest level. So, in this paper, using the initial motion vector and the adjacent motion vector in the coarsest level, we determine the optimal direction that will be minimized the estimation error in the finest level. In that direction, we define the potential searching region within the full searching region that is caused to increase much computational overhead in the FtC method. Last, in that region, we process the efficient 2-step motion estimation. and estimate the motion vector at finest resolution level. And then, this determined motion vector is scaled to coarser resolutions. As simulation result, this method is similar to computational complexity of the CtF MRME method and very significantly reduces that of the FtC MRME method. In addition, they provide higher quality than CtF MRME, both visually and quantitatively

• 한국콘텐츠학회논문지
• /
• 제3권1호
• /
• pp.9-13
• /
• 2003

이 논문에서는 비디오 영상에서의 블록 모션 측정을 위한 통계학적인 특징에 기반 한 알고리즘을 제안한다. 우선 참조 블록의 통계학적인 특징을 구하고, 이를 참조 블록의 통계적 특징과 정규 시작점 패턴 (SPP) 에 퍼져 있는 블록에서의 특징을 비교하여, SPP에서의 시작점 (SP) 후보를 선택하는 데에 적용한다. 최종적인 SP 들은 SP 후보 들에서의 평균절대차이 (MAD) 값으로 구한다. 마지막으로 기존의 고속탐색 알고리즘인 BBG나 DS 그리고 TSS중 하나를 이용하여 참조블록의 모션 벡터를 최종 SP를 시작점으로 하여 계산하였다. 실험결과는 기대 했던 바와 같이 최종 SP로부터의 시작점들이 전역최소값 (global minimum)에 근접함을 보여 주었다.

• ETRI Journal
• /
• 제31권6호
• /
• pp.784-794
• /
• 2009

We present a full HD (1080p) H.264/AVC High Profile hardware encoder based on fast motion estimation (ME). Most processing cycles are occupied with ME and use external memory access to fetch samples, which degrades the performance of the encoder. A novel approach to fast ME which uses shared multibank memory can solve these problems. The proposed pixel subsampling ME algorithm is suitable for fast motion vector searches for high-quality resolution images. The proposed algorithm achieves an 87.5% reduction of computational complexity compared with the full search algorithm in the JM reference software, while sustaining the video quality without any conspicuous PSNR loss. The usage amount of shared multibank memory between the coarse ME and fine ME blocks is 93.6%, which saves external memory access cycles and speeds up ME. It is feasible to perform the algorithm at a 270 MHz clock speed for 30 frame/s real-time full HD encoding. Its total gate count is 872k, and internal SRAM size is 41.8 kB.

• 제어로봇시스템학회논문지
• /
• 제16권12호
• /
• pp.1233-1240
• /
• 2010

In the flat panel display and semiconductor industries, the visual alignment system is considered as a core technology which determines the productivity of a manufacturing line. It consists of the vision system to extract the centroids of alignment marks and the stage control system to compensate the alignment error. In this paper, we develop a Kalman filter algorithm to estimate the alignment mark postures and propose a coarse-fine alignment control method which utilizes both original fine images and reduced coarse ones in the visual feedback. The error compensation trajectory for the distributed joint servos of the alignment stage is generated in terms of the inverse kinematic solution for the misalignment in task space. In constructing the estimation algorithm, the equation of motion for the alignment marks is given by using the forward kinematics of alignment stage. Secondly, the measurements for the alignment mark centroids are obtained from the reduced images by applying the geometric template matching. As a result, the proposed Kalman filter based coarse-fine alignment control method enables a considerable reduction of alignment time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권6호
• /
• pp.3086-3103
• /
• 2017

Video images captured by vehicle cameras often contain blurry or dithering frames due to inadvertent motion from bumps in the road or by insufficient illumination during the morning or evening, which greatly reduces the perception of objects expression and recognition from the records. Therefore, a real-time electronic stabilization method to correct fuzzy video from driving recorders has been proposed. In the first stage of feature detection, a coarse-to-fine inspection policy and a scale nonlinear diffusion filter are proposed to provide more accurate keypoints. Second, a new antiblurry binary descriptor and a feature point selection strategy for unintentional estimation are proposed, which brought more discriminative power. In addition, a new evaluation criterion for affine region detectors is presented based on the percentage interval of repeatability. The experiments show that the proposed method exhibits improvement in detecting blurry corner points. Moreover, it improves the performance of the algorithm and guarantees high processing speed at the same time.