• Journal of Information Display
• /
• v.6 no.4
• /
• pp.16-25
• /
• 2005

In this paper, a new 3D object tracking system using the disparity motion vector (DMV) is presented. In the proposed method, the time-sequential disparity maps are extracted from the sequence of the stereo input image pairs and these disparity maps are used to sequentially estimate the DMV defined as a disparity difference between two consecutive disparity maps Similarly to motion vectors in the conventional video signals, the DMV provides us with motion information of a moving target by showing a relatively large change in the disparity values in the target areas. Accordingly, this DMV helps detect the target area and its location coordinates. Based on these location data of a moving target, the pan/tilt embedded in the stereo camera system can be controlled and consequently achieve real-time stereo tracking of a moving target. From the results of experiments with 9 frames of the stereo image pairs having 256x256 pixels, it is shown that the proposed DMV-based stereo object tracking system can track the moving target with a relatively low error ratio of about 3.05 % on average.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.428-435
• /
• 2017

In this paper, we propose a novel motion field estimation algorithm for which a U-disparity map and forward-and-backward error removal are applied in a vehicular environment. Generally, a motion exists in an image obtained by a camera attached to a vehicle by vehicle movement; however, the obtained motion vector is inaccurate because of the surrounding environmental factors such as the illumination changes and vehicles shaking. It is, therefore, difficult to extract an accurate motion vector, especially on the road surface, due to the similarity of the adjacent-pixel values; therefore, the proposed algorithm first removes the road surface region in the obtained image by using a U-disparity map, and uses then the optical flow that represents the motion vector of the object in the remaining part of the image. The algorithm also uses a forward-backward error-removal technique to improve the motion-vector accuracy and a vehicle's movement is predicted through the application of the RANSAC (RANdom SAmple Consensus) to the previously obtained motion vectors, resulting in the generation of a motion field. Through experiment results, we show that the performance of the proposed algorithm is superior to that of an existing algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.12
• /
• pp.2343-2352
• /
• 2015

In this paper, we propose novel motion field estimation method using U-disparity map and forward-backward error removal in vehicles environment. Generally, in an image obtained from a camera attached in a vehicle, a motion vector occurs according to the movement of the vehicle. but this motion vector is less accurate by effect of surrounding environment. In particular, it is difficult to extract an accurate motion vector because of adjacent pixels which are similar each other on the road surface. Therefore, proposed method removes road surface by using U-disparity map and performs optical flow about remaining portion. forward-backward error removal method is used to improve the accuracy of the motion vector. Finally, we predict motion of the vehicle by applying RANSAC(RANdom SAmple Consensus) from acquired motion vector and then generate motion field. Through experimental results, we show that the proposed algorithm performs better than old schemes.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.345-348
• /
• 2001

본 논문에서는 변이-움직임 벡터의 상관관계를 통한 동시 추정(joint disparity and motion estimation)을 이용하여 방대한 계산량과 데이터량을 요구하는 스테레오 영상 데이터의 효율적인 부호화를 위한 알고리즘을 제안한다. 스테레오 시퀀스에 대해서 두 변이 벡터(disparity vector)와 하나의 움직임 벡터(motion vector)의 상관관계를 이용하면 나머지 움직임 벡터는 직접적인 추정 과정 없이 얻을 수 있다. 하지만, 이렇게 얻어진 움직임 벡터는 직접 추정에 비해 정확도가 현저히 떨어져 이 벡터를 그대로 사용하여 영상을 복원하게 될 경우 심각한 오차의 누적이 발생한다. 따라서 본 논문에서는 효율적인 동시 추정을 위해 추정단에서 벡터 평활화(vector regularization)과정을 수행하고 불확실 벡터 영역 추출을 통한 선택적인 보정 과정을 수행한다. 또한, 불확실 벡터 영역의 벡터만을 가변장 부호화(variable length coding)한다. 실험결과, 직접 추정 과정을 거치지 않고 도 만족할 만한 화질의 영상을 얻을 수 있었으며, 부호화량도 상당히 감소시킬 수 있었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.2C
• /
• pp.166-174
• /
• 2006

In this paper, a new stereo object tracking system using the disparity motion vector is proposed. In the proposed method, the time-sequential disparity motion vector can be estimated from the disparity vectors which are extracted from the sequence of the stereo input image pair and then using these disparity motion vectors, the area where the target object is located and its location coordinate are detected from the input stereo image. Being based on this location data of the target object, the pan/tilt embedded in the stereo camera system can be controlled and as a result, stereo tracking of the target object can be possible. From some experiments with the 2 frames of the stereo image pairs having 256$\times$256 pixels, it is shown that the proposed stereo tracking system can adaptively track the target object with a low error ratio of about 3.05$\%$ on average between the detected and actual location coordinates of the target object.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.121-124
• /
• 2001

For efficient transmission of 3DTV video signals, it is necessary to eliminate the inherent redundancy between the stereo image pairs. Though disparity estimation provides a powerful tool for eliminating the redundancy, it is very time consuming. This paper presents a novel disparity estimation scheme based on the human visual property. The disparity vectors of image blocks spatially adjacent to the current block are used as initial guesses fur the disparity vector of the current block. In addition, mixed-resolution coding is applied to reduce the computational complexity of disparity estimation. Through computer simulations on a stereoscopic sequence we show that the proposed method gives rise .to visually pleasing results with much reduced computational complexity.

• Journal of Information Display
• /
• v.5 no.4
• /
• pp.31-37
• /
• 2004

In this paper, an effective method for reconstruction of stereoscopic image pair through the regularized adaptive disparity estimation is proposed. Although the conventional adaptive disparity window matching can sharply improve the PSNR of a reconstructed stereo image, but there still exist some problems of overlapping between the matching windows and disallocation of the matching windows, because the size of the matching window tend to changes adaptively in accordance with the magnitude of the feature values. In the proposed method, the problems relating to the conventional adaptive disparity estimation scheme can be solved and the predicted stereo image can be more effectively reconstructed by regularizing the extimated disparity vector with the neighboring disparity vectors. From the experimental results, it is found that the proposed algorithm show improvements the PSNR of the reconstructed right image by about 2.36${\sim}$2.76 dB, on average, compared with that of conventional algorithms.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.25-32
• /
• 2004

We propose a hierarchical disparity estimation algorithm with edge-preserving energy-based regularization. Initial disparity vectors are obtained from downsampled stereo images using a feature-based region-dividing disparity estimation technique. Dense disparities are estimated from these initial vectors with shape-adaptive windows in full resolution images. Finally, the vector fields are regularized with the minimization of the energy functional which considers both fidelity and smoothness of the fields. The first two steps provide highly reliable disparity vectors, so that local minimum problem can be avoided in regularization step. The proposed algorithm generates accurate disparity map which is smooth inside objects while preserving its discontinuities in boundaries. Experimental results are presented to illustrate the capabilities of the proposed disparity estimation technique.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.2
• /
• pp.273-278
• /
• 2009

The determination of the associated weights in the theory of ordered weighted averaging (OWA) operators is one of the important issue. Recently, Wang and Parkan [Information Sciences 175 (2005) 20-29] proposed a minimax disparity approach for obtaining OWA operator weights and the approach is based on the solution of a linear program (LP) model for a given degree of orness. Recently, Liu [International Journal of Approximate Reasoning, accepted] showed that the minimum variance OWA problem of Fuller and Majlender [Fuzzy Sets and Systems 136 (2003) 203-215] and the minimax disparity OWA problem of Wang and Parkan always produce the same weight vector using the dual theory of linear programming. In this paper, we give an improved proof of the minimax disparity problem of Wang and Parkan while Liu's method is rather complicated. Our method gives the exact optimum solution of OWA operator weights for all levels of orness, $0\leq\alpha\leq1$, whose values are piecewise linear and continuous functions of $\alpha$.

• Journal of Korea Multimedia Society
• /
• v.19 no.6
• /
• pp.1003-1013
• /
• 2016

This paper proposes a framework of superpixel-based vehicle detection method using plane normal vector in disparity space. We utilize two common factors for detecting vehicles: Hypothesis Generation (HG) and Hypothesis Verification (HV). At the stage of HG, we set the regions of interest (ROI) by estimating the lane, and track them to reduce computational cost of the overall processes. The image is then divided into compact superpixels, each of which is viewed as a plane composed of the normal vector in disparity space. After that, the representative normal vector is computed at a superpixel-level, which alleviates the well-known problems of conventional color-based and depth-based approaches. Based on the assumption that the central-bottom of the input image is always on the navigable region, the road and obstacle candidates are simultaneously extracted by the plane normal vectors obtained from K-means algorithm. At the stage of HV, the separated obstacle candidates are verified by employing HOG and SVM as for a feature and classifying function, respectively. To achieve this, we trained SVM classifier by HOG features of KITTI training dataset. The experimental results demonstrate that the proposed vehicle detection system outperforms the conventional HOG-based methods qualitatively and quantitatively.