• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06b
• /
• pp.147-153
• /
• 1998

This paper provides a method for video augmentation using image interpolation. In computer graphics or augmented reality, 3D information of a model object is necessary to generate 2D views of the model, which are then inserted into or overlayed on environmental views or real video frames. However, we do not require any three dimensional model but images of the model object at some locations to render views according to the motion of video camera which is calculated by an SFM algorithm using point matches under weak-perspective (scaled-orthographic) projection model. Thus, a linear view interpolation algorithm is applied rather than a 3D ray-tracing method to get a view of the model at different viewpoints from model views. In order to get novel views in a way that agrees with the camera motion the camera coordinate system is embedded into model coordinate system at initialization time on the basis of 3D information recovered from video images and model views, respectively. During the sequence, motion parameters from video frames are used to compute interpolation parameters, and rendered model views are overlayed on corresponding video frames. Experimental results for real video frames and model views are given. Finally, discussion on the limitations of the method and subjects for future research are provided.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.145-151
• /
• 2023

3D-CNN is one of the deep learning techniques for learning time series data. Such three-dimensional learning can generate many parameters, so that high-performance machine learning is required or can have a large impact on the learning rate. When learning dynamic hand-gestures in spatiotemporal domain, it is necessary for the improvement of the efficiency of dynamic hand-gesture learning with 3D-CNN to find the optimal conditions of input video data by analyzing the learning accuracy according to the spatiotemporal change of input video data without structural change of the 3D-CNN model. First, the time ratio between dynamic hand-gesture actions is adjusted by setting the learning interval of image frames in the dynamic hand-gesture video data. Second, through 2D cross-correlation analysis between classes, similarity between image frames of input video data is measured and normalized to obtain an average value between frames and analyze learning accuracy. Based on this analysis, this work proposed two methods to effectively select input video data for 3D-CNN deep learning of dynamic hand-gestures. Experimental results showed that the learning interval of image data frames and the similarity of image frames between classes can affect the accuracy of the learning model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.7
• /
• pp.3438-3454
• /
• 2018

In this paper, we propose a robust blind watermarking scheme for high-definition video. In the embedding process, luminance component of each frame is transformed by 2-dimensional fast Fourier transform (2D FFT). A secret key is used to generate a matrix of random numbers for the security of watermark information. The matrix is transformed by inverse steerable pyramid transform (SPT). We embed the watermark into the low and mid-frequency of 2D FFT coefficients with the transformed matrix. In the extraction process, the 2D FFT coefficients of each frame and the transformed matrix are transformed by SPT respectively, to produce two oriented sub-bands. We extract the watermark from each frame by cross-correlating two oriented sub-bands. If a video is degraded by some attacks, the watermarks of frames contain some errors. Thus, we use an ensemble position-based error correcting algorithm to estimate the errors and correct them. The experimental results show that the proposed watermarking algorithm is imperceptible and moreover is robust against various attacks. After embedding 64 bits of watermark into each frame, the average peak signal-to-noise ratio between original frames and embedded frames is 45.7 dB.

• Steel and Composite Structures
• /
• v.50 no.5
• /
• pp.583-594
• /
• 2024

In this paper, a Guided Simulated Annealing (GSA) algorithm is presented to optimize 2D and 3D steel frames against Progressive Collapse. Considering the nature of structural optimization problems, a number of restrictions and improvements have been applied to the decision mechanisms of the algorithm without harming the randomness. With these improvements, the algorithm aims to focus relatively on the flawed variables of the analyzed frame. Besides that, it is intended to be more rational by instituting structural constraints on the sections to be selected as variables. In addition to the LRFD restrictions, the alternate path method with nonlinear dynamic procedure is used to assess the risk of progressive collapse, as specified in the US Department of Defense United Facilities Criteria (UFC) Design of Buildings to Resist Progressive Collapse. The entire optimization procedure was carried out on a C# software that supports parallel processing developed by the authors, and the frames were analyzed in SAP2000 using OAPI. Time history analyses of the removal scenarios are distributed to the processor cores in order to reduce computational time. The GSA produced 3% lighter structure weights than the SA (Simulated Annealing) and 4% lighter structure weights than the GA (Genetic Algorithm) for the 2D steel frame. For the 3D model, the GSA obtained 3% lighter results than the SA. Furthermore, it is clear that the UFC and LRFD requirements differ when the acceptance criteria are examined. It has been observed that the moment capacity of the entire frame is critical when designing according to UFC.

• Journal of Broadcast Engineering
• /
• v.14 no.2
• /
• pp.114-126
• /
• 2009

In this paper, we propose a PSNR(peak-to-peak signal to noise ratio) estimation method exploiting visual rhythm information for the reconstructed video frames at the customer's STB(Set-top Box). Key idea is that we can estimate the PSNR by using VR(visual rhythm) information even though a VR consists of the pixels in a vertical direction of a 2D(2-dimensional) video frame, because VR is the 1D projected version of a 2D video frame approximately. Simulation results show that the estimated PSNR from VR information is closely related to the PSNR from 2D video frames. The advantages of the proposed scheme includes that it can monitor the video quality efficiently while minimizing the computation load of STB, and show the location, duration and occurrence count of severe picture degradation.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.680-691
• /
• 2021

Due to the recent developments of attaining 3D contents by using devices such as 3D scanners, the diversity of the contents being used in AR(Augmented Reality)/VR(Virutal Reality) fields is significantly increasing. There are several ways to represent 3D data, and using point clouds is one of them. A point cloud is a cluster of points, having the advantage of being able to attain actual 3D data with high precision. However, in order to express 3D contents, much more data is required compared to that of 2D images. The size of data needed to represent dynamic 3D point cloud objects that consists of multiple frames is especially big, and that is why an efficient compression technology for this kind of data must be developed. In this paper, a motion estimation and compensation method for dynamic point cloud objects using 3D DCT is proposed. This will lead to switching the 3D video frames into I frames and P frames, which ensures higher compression ratio. Then, we confirm the compression efficiency of the proposed technology by comparing it with the anchor technology, an Intra-frame based compression method, and 2D-DCT based V-PCC.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.12
• /
• pp.2844-2851
• /
• 2015

How to recover from the multiple 2D images into 3D object has been widely studied in the field of computer vision. In order to improve the accuracy of the recovered 3D shape, it is more important that noise must be minimized and the number of image frames must be guaranteed. However, potential noise is implied when tracking feature points. And the number of image frames which is consisted of an observation matrix usually decrease because of tracking failure, occlusions, or low image resolution, and so on. Therefore, it is obviously essential that the number of image frames must be secured by recovering the missing feature points under noise. Thus, we propose the analytic approach which can control directly the error distance and orientation of missing feature point by the geometrical properties under noise distribution. The superiority of proposed method is demonstrated through experimental results for synthetic and real object.

• The Journal of the Korea Contents Association
• /
• v.9 no.2
• /
• pp.43-50
• /
• 2009

We proposed similarity detection method of the video frame data that extracts the feature data of own video frame and creates the 1-D signal in this paper. We get the similar frame boundary and make the representative frames within the frame boundary to extract the similarity extraction between video. Representative frames make blurring frames and extract the feature data using DOG values. Finally, we convert the feature data into the 1-D signal and compare the contents similarity. The experimental results show that the proposed algorithm get over 0.9 similarity value against noise addition, rotation change, size change, frame delete, frame cutting.

• Spatial Information Research
• /
• v.12 no.2
• /
• pp.137-149
• /
• 2004

For 3D modelling artificial objects with computers, we have to draw frames and paint the facet images on each side. In this paper, a geographic modelling system building automatically 3D geographic spaces using GIS data and real images of buildings is proposed. First, the 3D model of terrain is constructed by using TIN and DEM algorithms. The images of buildings are acquired with a camera and its position is estimated using vertical lines of the image and the GIS data. The height of the building is computed with the image and the position of the camera, which used for making up the frames of buildings. The 3D model of the building is obtained by detecting the facet iamges of the building and texture mapping them on the 3D frame. The proposed geographical modeling system is applied to real area and shows its effectiveness.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.23 no.4
• /
• pp.201-209
• /
• 2019

Response modification factors of school facilities for non-seismic RC moment frames with partial masonry infills in 'Manual for Seismic Performance Evaluation and Retrofit of School Facilities' published in 2018 were investigated in the preceding study. However, since previous studies are based on 2D frame analysis and limited analysis conditions, additional verification needs to be performed to further apply various conditions including orthogonal effect of seismic load. Therefore, this study is to select appropriate response modification factors of school facilities for non-seismic RC moment frames with partial masonry infills by 3D frame analysis. The results are as follows. An appropriate response modification factor for non-seismic RC moment frames with partial masonry infills is proposed as 2.5 for all cases if the period is longer than 0.6 seconds. Also if the period is less than 0.4 seconds and the ratio of shear-controlled columns is less than 30%, 2.5 is chosen too. However, if the period is less than 0.4 seconds and the ratio of shear-controlled columns is higher than 30%, the response modification factor shall be reduced to 2.0. If the period is between 0.4 and 0.6 seconds, then linearly interpolates the response correction factor.