• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.6
• /
• pp.7-14
• /
• 2018

Salient information extraction from multi-view videos is a very challenging area because of inter-view, intra-view correlations, and computational complexity. There are several techniques developed for keyframes extraction from multi-view videos with very high computational complexities. In this paper, we present a keyframes extraction approach from multi-view videos using entropy and complexity information present inside frame. In first step, we extract representative shots of the whole video from each view based on structural similarity index measurement (SSIM) difference value between frames. In second step, entropy and complexity scores for all frames of shots in different views are computed. Finally, the frames with highest entropy and complexity scores are considered as keyframes. The proposed system is subjectively evaluated on available office benchmark dataset and the results are convenient in terms of accuracy and time complexity.

• Journal of Digital Convergence
• /
• v.15 no.12
• /
• pp.531-541
• /
• 2017

Realistic videos using multi-view videos are created so that the contents shown on multi-view displays or screens look realistic. These images have been mostly used for special videos for exhibition, but, recently, systems such as Screen X have given rise to multi-view images as a format for storytelling contents such as movies. This study used HD-level broadcasting digital video camera with three zoom lenses for shooting wide to close-up shots focusing on a person, in the same way as Screen X, and identified and analyzed problems found during multi-view image registration correction. The results of this study suggested, provided the shooting technique and equipment are improved, the multi-view format can be used for conveying stories and information. Future research will need to investigate and supplement relevant techniques that will enable production of high-quality multi-view image contents by using a cinema-grade camera with standard lenses, instead of using broadcasting-grade zoom lenses.

• Journal of Korea Multimedia Society
• /
• v.15 no.9
• /
• pp.1093-1101
• /
• 2012

Multi-view video is obtained by capturing one three-dimensional scene with many cameras at different positions. Multi-view video coding exploits inter-view correlations among pictures of neighboring views and temporal correlations among pictures of the same view. Multi-view video coding which uses many cameras requires a method to reduce the computational complexity. In this paper, we proposed an efficient prediction structure to improve performance of multi-view video coding. The proposed prediction structure exploits an average distance between the current picture and its reference pictures. The proposed prediction structure divides every GOP into several small groups to decide the maximum index of hierarchical B layer and the number of pictures of each B layer. Experimental results show that the proposed prediction structure shows good performance in image quality and bit-rates. When compared to the performance of hierarchical B pictures of Fraunhofer-HHI, the proposed prediction structure achieved 0.07~0.13 (dB) of PSNR gain and was down by 6.5(Kbps) in bitrate.

• Journal of Broadcast Engineering
• /
• v.12 no.6
• /
• pp.565-573
• /
• 2007

In this paper, we propose a method to select motion vector predictor by considering prediction structure of a multi view content for coding efficiency of multi view coding which is being standardized in JVT. Motion vector of a different tendency is happened while carrying out temporal and view reference prediction of multi-view video coding. Also, due to the phenomena of motion vectors being searched in both temporal and view order, the motion vectors do not agree with each other resulting a decline in coding efficiency. This paper is about how the motion vector predictor are selected with information of prediction structure. By using the proposed method, a compression ratio of the proposed method in multi-view video coding is increased, and finally $0.03{\sim}0.1$ dB PSNR(Peak Signal-to-Noise Ratio) improvement was obtained compared with the case of JMVM 3.6 method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.9
• /
• pp.4317-4335
• /
• 2018

Semi-supervised multi-view latent space learning is gaining considerable popularity recently in many machine learning applications due to the high cost and difficulty to obtain the large amount of label information of data. Although some semi-supervised multi-view latent space learning methods have been presented, there is still much space for improvement: 1) How to learn latent discriminant intact feature representations by employing data of multiple views; 2) How to exploit the manifold structure of both labeled and unlabeled point in the learned latent intact space effectively. To address the above issues, we propose an approach called semi-supervised multi-view manifold discriminant intact space learning ($SM^2DIS$) for image classification in this paper. $SM^2DIS$ aims to seek a manifold discriminant intact space for data of different views by making use of both the discriminant information of labeled data and the manifold structure of both labeled and unlabeled data. Experimental results on MNIST, COIL-20, Multi-PIE, and Caltech-101 databases demonstrate the effectiveness and robustness of our proposed approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.5
• /
• pp.2366-2395
• /
• 2018

Multi-view super-resolution (MVSR) refers to the process of reconstructing a high-resolution (HR) image from a set of low-resolution (LR) images captured from different viewpoints typically by different cameras. These multi-view images are usually obtained by a camera array. In our previous work [1], we super-resolved multi-view LR images via image fusion (IF) and blind deblurring (BD). In this paper, we present a new MVSR method that jointly realizes IF and BD based on an integrated energy function optimization. First, we reformulate the MVSR problem into a multi-channel blind deblurring (MCBD) problem which is easier to be solved than the former. Then the depth map of the desired HR image is calculated. Finally, we solve the MCBD problem, in which the optimization problems with respect to the desired HR image and with respect to the unknown blur are efficiently addressed by the alternating direction method of multipliers (ADMM). Experiments on the Multi-view Image Database of the University of Tsukuba and images captured by our own camera array system demonstrate the effectiveness of the proposed method.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.6
• /
• pp.17-24
• /
• 2017

In recent digital broadcasting, up to 250 channels are multiplexed and transmitted. The channel transmission is made in the form of MPEG-2 Transport Stream (TS) and transmits one channel (Video, Audio). In order to check if many broadcast channels are transmitted normally, in multi-channel multi-view system, ability of real-time monitoring is required. In order to monitor efficient multi-channel, a distributed system in which functions and load are distributed should be implemented. In the past, we used an inefficient system that gave all of the functionality to a piece of hardware, which limited the channel acceptance and required a lot of resources. In this paper, we implemented a distributed multi-view system which can reduce resources and monitor them economically through efficient function and load balancing. It is able to implement efficient system by taking charge of decoding, resizing and encoding function in specific server and viewer function in separate server. Through this system, the system was stabilized, the investment cost was reduced by 19.7%, and the wall monitor area was reduced by 52.6%. Experimental results show that efficient real-time channel monitoring for multi-channel digital broadcasting is possible.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.294-297
• /
• 2009

Multi-view video consists of a set of multiple video sequences from multiple viewpoints or view directions in the same scene. It contains extremely a large amount of data and some extra information to be stored or transmitted to the user. This paper presents inter-view correlations among video objects and the background to reduce the prediction complexity while achieving a high coding efficiency in multi-view video coding. Our proposed algorism is based on object-based segmentation scheme that utilizes video object information obtained from the coded base view. This set of data help us to predict disparity vectors and motion vectors in enhancement views by employing object registration, which leads to high compression and low-complexity coding scheme for enhancement views. An experimental results show that the superiority can provide an improvement of PSNR gain 2.5.3 dB compared to the simulcast.

• Journal of Multimedia Information System
• /
• v.1 no.1
• /
• pp.1-10
• /
• 2014

In this paper, we propose a new view synthesis technique for coding of multi-view color and depth data in arbitrary camera arrangements. We treat each camera position as a 3-D point in world coordinates and build clusters of those vertices. Color and depth data within a cluster are gathered into one camera position using a hierarchical representation based on the concept of layered depth image (LDI). Since one camera can cover only a limited viewing range, we set multiple reference cameras so that multiple LDIs are generated to cover the whole viewing range. Therefore, we can enhance the visual quality of the reconstructed views from multiple LDIs comparing with that from a single LDI. From experimental results, the proposed scheme shows better coding performance under arbitrary camera configurations in terms of PSNR and subjective visual quality.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.10
• /
• pp.881-886
• /
• 2013

Even though a multi-view camera system is able to capture multiple images at different viewpoints, the color distributions of captured multi-view images can be inconsistent. This problem decreases the quality of multi-view images and the performance of post-image processes. In this paper, we propose an improved polynomial model for effectively correcting the color inconsistency problem. This algorithm is fully automatic without any pre-process and considers occlusion regions of the multi-view image. We use the 5th order polynomial model to define a relative mapping curve between reference and source views. Sometimes the estimated curve is seriously distorted if the dynamic range of extracted correspondences is quite low. Therefore we additionally estimate the first order polynomial model for the bottom and top regions of the dynamic range. Afterwards, colors of the source view are modified via these models. The proposed algorithm shows the good subjective results and has better objective quality than the conventional color correction algorithms.