• 융합신호처리학회논문지
• /
• 제5권2호
• /
• pp.96-105
• /
• 2004

2차원 이미지로부터 3차원 이미지 복원은 각 픽셀까지의 깊이 정보가 필요하고, 3차원 모델의 복원에 관한 일반적인 수작업은 많은 시간과 비용이 소모된다. 본 논문의 목표는 카메라가 이동하는 중에, 획득된 단안 영상에서 영역의 상대적인 깊이 정보를 추출하는 것이다. 카메라 이동에 의한 영상의 모든 점들의 움직임은 깊이 정보에 종속적이라는 사실에 기반을 두고 있다. 전역 탐색 기법을 사용하여 획득한 움직임 벡터에서 카메라 회전과 배율에 관해서 보상을 한다. 움직임 벡터를 분석하여 평균 깊이를 측정하고, 평균 깊이에 대한 각 영역의 상대적 깊이를 구하였다. 실험결과 영역의 상대적인 깊이는 인간이 인식하는 상대적인 깊이와 일치한다는 것을 보였다.

• 방송공학회논문지
• /
• 제22권4호
• /
• pp.429-437
• /
• 2017

2D영상의 3D변환 기술은 3D 디스플레이 및 3DTV에 기본적으로 장착된 기술로 꾸준히 연구 및 상업화가 진행된 기술이다. 3D변환은 정지영상으로부터 다양한 깊이단서를 이용하여 깊이맵을 추출한 후에, DIBR(Depth Image Based Rendering)로 입체영상을 생성한다. 또한 비디오에서 추출할 수 있는 모션정보를 활용하여 모션 깊이맵을 얻기도 한다. 본 논문에서는 기존의 블록기반 모션예측, 광유 등의 모션 추출 방식이 아닌 운동 히스토리 영상(Motion History Image)를 활용하여 모션 깊이맵을 얻는 새로운 방법을 제안하고 실제 활용 가능성을 조사한다. 실험에서는 제안한 방법을 다양한 운동 유형을 가지는 8개의 2D 비디오 콘텐츠에 적용하였고, 생성된 모션 깊이맵의 정성적 평가 및 수행 속도의 비교를 통하여 MHI 기반 깊이맵의 실제 적용이 적합함을 증명하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권1호
• /
• pp.242-259
• /
• 2015

Three-dimensional video coding is one of the main challenges restricting the widespread applications of 3D video and free viewpoint video. In this paper, a novel fractal coding algorithm with motion-vector-field-based motion estimation for depth map sequence is proposed. We firstly add pre-search restriction to rule the improper domain blocks out of the matching search process so that the number of blocks involved in the search process can be restricted to a smaller size. Some improvements for motion estimation including initial search point prediction, threshold transition condition and early termination condition are made based on the feature of fractal coding. The motion-vector-field-based adaptive hexagon search algorithm on the basis of center-biased distribution characteristics of depth motion vector is proposed to accelerate the search. Experimental results show that the proposed algorithm can reach optimum levels of quality and save the coding time. The PSNR of synthesized view is increased by 0.56 dB with 36.97% bit rate decrease on average compared with H.264 Full Search. And the depth encoding time is saved by up to 66.47%. Moreover, the proposed fractal depth map sequence codec outperforms the recent alternative codecs by improving the H.264/AVC, especially in much bitrate saving and encoding time reduction.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.383-388
• /
• 2005

Depth recovery in robot vision is an essential problem to infer the three dimensional geometry of scenes from a sequence of the two dimensional images. In the past, many studies have been proposed for the depth estimation such as stereopsis, motion parallax and blurring phenomena. Among cues for depth estimation, depth from lens translation is based on shape from motion by using feature points. This approach is derived from the correspondence of feature points detected in images and performs the depth estimation that uses information on the motion of feature points. The approaches using motion vectors suffer from the occlusion or missing part problem, and the image blur is ignored in the feature point detection. This paper presents a novel approach to the defocus technique based depth from lens translation using sequential SVD factorization. Solving such the problems requires modeling of mutual relationship between the light and optics until reaching the image plane. For this mutuality, we first discuss the optical properties of a camera system, because the image blur varies according to camera parameter settings. The camera system accounts for the camera model integrating a thin lens based camera model to explain the light and optical properties and a perspective projection camera model to explain the depth from lens translation. Then, depth from lens translation is proposed to use the feature points detected in edges of the image blur. The feature points contain the depth information derived from an amount of blur of width. The shape and motion can be estimated from the motion of feature points. This method uses the sequential SVD factorization to represent the orthogonal matrices that are singular value decomposition. Some experiments have been performed with a sequence of real and synthetic images comparing the presented method with the depth from lens translation. Experimental results have demonstrated the validity and shown the applicability of the proposed method to the depth estimation.

• Journal of the Optical Society of Korea
• /
• 제4권1호
• /
• pp.25-29
• /
• 2000

Two different binocular cues are known for detecting motion in depth. One is disparity change in time and the other is inter-ocular velocity difference. Shioiri, Saisho and Yaguchi (1999) demon-strated that motion in depth can be seen based solely on inter-ocular velocity differences as well as on the disparity change in time. They used conditions in which either cue was minimized and measured performance based on motion in depth, finding better performance than chance level when either velocity cue or the disparity cue was almost isolated. However, there may have been influences from the cue minimized in each condition, since it was practically impossible to isolate perfectly either cue. I re-analyzed their data to examine whether the performance in the condition with disparity change and that in the condition with inter-ocular velocity difference were correlated. The result showed the correlation is very low and therefore, we can conclude that the visual system has two different mechanisms for motion in depth.

• 한국멀티미디어학회논문지
• /
• 제19권4호
• /
• pp.774-779
• /
• 2016

The conventional methods using color signal for tracking the movement of the object require a lot of calculation and the performance is not accurate. In this paper, we propose a method to effectively track the moving objects using the depth information from a depth camera. First, it separates the background and the objects based on the depth difference in the depth of the screen. When an object is moved, the depth value of the object becomes blurred because of the phenomenon of Motion Blur. In order to solve the Motion Blur, we observe the changes in the characteristics of the object (the area of the object, the border length, the roundness, the actual size) by its velocity. The proposed algorithm was implemented in the simulation that was applied directly to the tracking of a golf ball. We can see that the estimated value of the proposed method is accurate enough to be very close to the actual measurement.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2007년도 7th International Meeting on Information Display 제7권1호
• /
• pp.1029-1030
• /
• 2007

I introduce two experiments that investigate temporal factors of stereopsis: one is for depth perception and the other is for perception of motion in depth. Both studies show that there are multiple mechanisms to process depth information with different temporal characteristics.

• ETRI Journal
• /
• 제39권2호
• /
• pp.181-190
• /
• 2017

The movements of the human body are difficult to capture owing to the complexity of the three-dimensional skeleton model and occlusion problems. In this paper, we propose a motion capture system that tracks dynamic human motions in real time. Without using external markers, the proposed system adopts multiple depth sensors (Microsoft Kinect) to overcome the occlusion and body rotation problems. To combine the joint data retrieved from the multiple sensors, our calibration process samples a point cloud from depth images and unifies the coordinate systems in point clouds into a single coordinate system via the iterative closest point method. Using noisy skeletal data from sensors, a posture reconstruction method is introduced to estimate the optimal joint positions for consistent motion generation. Based on the high tracking accuracy of the proposed system, we demonstrate that our system is applicable to various motion-based training programs in dance and Taekwondo.

• 정보처리학회논문지B
• /
• 제8B권5호
• /
• pp.549-556
• /
• 2001

2차원 영상으로 부터 3차원 영상으로 복원하는 일은 일반적으로 카메라의 초점에서 영상 프레임의 각 픽셀까지의 깊이 정보가 필요하고, 3차원 모델의 복원에 관한 일반적인 수작업은 많은 식나과 비용이 소모된다. 본 논문에서는 카메라의 움직임이 포함되어 있는 단안 영상 시퀸스로부터 3차원 영상 제작에 필요한 상대적인 깊이 정보를 실시간으로 추출하는 알고리즘을 제안하고, 하드웨어를 구현하기 위한여 알고리즘을 단순화하였다. 이 알고리즘은 카메라 이동에 의한 영상의 모든 점들의 움직임은 깊이 정보의 종속적이라는 사실에 기반을 두고 있다. 불록매칭 알고리즘에 기반을 둔 전역 움직임 탐색에 의한 움직임 벡터를 추출한 후, 카메라 회전과 확대/축소에 관한 카메라 움직임 보상을 실행하고 깉이 정보 추출 과정이 전개된다. 깊이 정보 추출 과정은 단안 영상에서 객체의 이동처리를 분석하여 움직임 벡터를 구하고 프레임내의 모든 픽셀에 대한 평균 깊이를 계산한 후, 평균 깊이에 대한 각 블록의 상대적 깊이를 산출하였다. 모의 실험 결과 전경과 배경에 속하는 영역의 깊이는 인간 시각 체계가 인식하는 상대적인 깊이와 일치한다는 것을 보였다.

• 디지털산업정보학회논문지
• /
• 제4권2호
• /
• pp.15-19
• /
• 2008

In this paper, we propose a new algorithm of image depth detection using motion estimation and object tracking. In industry, robots are used for automobile, conveyer system, etc. But, these have much necessary time. Thus, in this paper, we develop the efficient method of image depth detection based on motion estimation and object tracking.