• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.3
• /
• pp.1302-1309
• /
• 2012

In this paper, we propose applying differential techniques for 2D/3D video conversion to the objects grouped by depth information. One of the problems converting 2D images to 3D images using the technique tracking the motion of pixels is that objects not moving between adjacent frames do not give any depth information. This problem can be solved by applying relative height cue only to the objects which have no moving information between frames, after the process of splitting the background and objects and extracting depth information using motion vectors between objects. Using this technique all the background and object can have their own depth information. This proposed method is used to generate depth map to generate 3D images using DIBR(Depth Image Based Rendering) and verified that the objects which have no movement between frames also had depth information.

• Journal of Broadcast Engineering
• /
• v.7 no.3
• /
• pp.219-228
• /
• 2002

In this paper, we propose a new method of converting 2D video into 3D stereoscopic video, called stereoscopic conversion. In general, stereoscopic images are produced using the motion informations. However unreliable motion informations obtained especially from block-based motion estimation cause the wrong generation of stereoscopic images. To solve for this problem, we propose a stereoscopic conversion method based upon the utilization of key frame that has the better accuracy of estimated motion informations. As well, as generation scheme of stereoscopic images associated with the motion type of each key frame is proposed. For the performance evaluation of our proposed method, we apply it to five test images and measure the accuracy of key frame-based stereoscopic conversion. Experimental results show that our proposed method has the accuracy more than about 90 percent in terms of the detection ratio of key frames.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.3
• /
• pp.74-79
• /
• 2008

In an H.264/AVC video encoder, the motion estimation at fractional pixel accuracy improves a coding efficiency and image quality. However, it requires additional computation overheads for fractional search and interpolation, and thus, reducing the computation complexity of fractional search becomes more important. This paper proposes fast fractional search algorithms by combining the SASR(Simplified Adaptive Search Range) and the MSDSP(Mixed Small Diamond Search Pattern) with the predicted fractional motion vector. Compared with the full search and the prediction-based directional fractional pixel search, the proposed algorithms can reduce up to 93.2% and 81% of fractional search points, respectively with the maximum PSNR lost less than 0.04dB. Therefore, the proposed fast search algorithms are quite suitable for mobile applications requiring low power and complexity.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.33-38
• /
• 1999

Muscle based face image synthesis is one of the most realistic approach to realize life-like agent in computer. Facial muscle model is composed of facial tissue elements and muscles. In this model, forces are calculated effecting facial tissue element by contraction of each muscle strength, so the combination of each muscle parameter decide a specific facial expression. Now each muscle parameter is decided on trial and error procedure comparing the sample photograph and generated image using our Muscle-Editor to generate a specific race image. In this paper, we propose the strategy of automatic estimation of facial muscle parameters from 2D marker movement using neural network. This also 3D motion estimation from 2D point or flow information in captered image under restriction of physics based fare model.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.3
• /
• pp.527-535
• /
• 2016

Statistical optimization algorithms have been variously developed to estimate the 3D shape and motion. However, statistical approaches are limited to analyze the sensitive effects of SfM(Shape from Motion) according to the camera's geometrical position or viewing angles and so on. This paper propose the quantitative estimation method about the uncertainties of an observation matrix by using camera imaging configuration factors predict the reconstruction ambiguities in SfM. This is a very efficient method to predict the final reconstruction performance of SfM algorithm. Moreover, the important point is that our method show how to derive the active guidelines in order to set the camera imaging configurations which can be expected to lead the reasonable reconstruction results. The experimental results verify the quantitative estimates of an observation matrix by using camera imaging configurations and confirm the effectiveness of our algorithm.

• Journal of Broadcast Engineering
• /
• v.16 no.1
• /
• pp.44-53
• /
• 2011

In this paper, we propose a 3D conversion algorithm of 2D video using depth layer partition method. In the proposed algorithm, we first set frame groups using cut detection algorithm. Each divided frame groups will reduce the possibility of error propagation in the process of motion estimation. Depth image generation is the core technique in 2D/3D conversion algorithm. Therefore, we use two depth map generation algorithms. In the first, segmentation and motion information are used, and in the other, edge directional histogram is used. After applying depth layer partition algorithm which separates objects(foreground) and the background from the original image, the extracted two depth maps are properly merged. Through experiments, we verify that the proposed algorithm generates reliable depth map and good conversion results.

• Journal of Broadcast Engineering
• /
• v.25 no.3
• /
• pp.405-417
• /
• 2020

Due to the popularization of the Extended Reality, research is actively underway to implement human motion in real-time 3D animation. In particular, Microsoft developed Kinect cameras for 3D motion information can be obtained without the burden of facilities and with simple operation, real-time animation can be generated by combining with 3D formats such as FBX. Compared to the marker-based motion capture system, however, Kinect has low accuracy due to its lack of estimated performance of joint information. In this paper, two algorithms are proposed to correct joint estimation errors in order to realize natural human motion in motion capture animation system in Kinect camera-based FBX format. First, obtain the position information of a person with a Kinect and create a depth map to correct the wrong joint position value using the human body segment length constraint information, and estimate the new rotation value. Second, the pre-set joint motion range constraint is applied to the existing and estimated rotation value and implemented in FBX to eliminate abnormal behavior. From the experiment, we found improvements in human behavior and compared errors between algorithms to demonstrate the superiority of the system.

• Proceedings of the IEEK Conference
• /
• 2000.11c
• /
• pp.181-184
• /
• 2000

This paper presents an experimental system, where an object extracted from an image sequence is embedded into the desired position in a scene. First, a moving object is detected and the 3-D structure is obtained by SFM analysis of comer trajectories. We constrained the motion to translational motion only. Extracted objects are classified by matching with 3-D models and then the structure of the occluded part is restored. Camera calibration is performed for the background scene which will embed the object. Finally, the object is embedded into the scene. In the experiments, we used synthetic image sequences generated with OpenGL library for easy evaluation of the 3-D structure estimation.

• Journal of Digital Convergence
• /
• v.11 no.1
• /
• pp.243-248
• /
• 2013

In this paper, depth of foreground is analysed by focus and color analysis grouping for 2D/3D video conversion and depth of foreground progressing method is preposed by using focus and motion information. Candidate foreground image is generated by estimated movement of image focus information for extracting foreground from 2D video. Area of foreground is extracted by filling progress using color analysis on hole area of inner object existing candidate foreground image. Depth information is generated by analysing value of focus existing on actual frame for allocating depth at generated foreground area. Depth information is allocated by weighting motion information. Results of previous proposed algorithm is compared with proposed method from this paper for evaluating the quality of generated depth information.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.4
• /
• pp.187-194
• /
• 2015

In this paper, we present an effective visual odometry estimation system to track the real-time pose of a camera moving in 3D space. In order to meet the real-time requirement as well as to make full use of rich information from color and depth images, our system adopts a feature-based sparse odometry estimation method. After matching features extracted from across image frames, it repeats both the additional inlier set refinement and the motion refinement to get more accurate estimate of camera odometry. Moreover, even when the remaining inlier set is not sufficient, our system computes the final odometry estimate in proportion to the size of the inlier set, which improves the tracking success rate greatly. Through experiments with TUM benchmark datasets and implementation of the 3D scene reconstruction application, we confirmed the high performance of the proposed visual odometry estimation method.