• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.4
• /
• pp.388-398
• /
• 2002

Video representation through representative frames (key frames) has been addressed frequently as an efficient way of preserving the whole temporal information of sequence with a considerably smaller amount of data. Such compact video representation is suitable for the purpose of video browsing in limited storage or transmission bandwidth environments. In a case like this, the controllability of the total key frame number (i.e. key frame rate) depending on the storage or bandwidth capacity is an important requirement of a key frame selection method. In this paper, we present a sequential key frame selection method when the number of key frames is given as a constraint. It first selects the desired number of initial key frames and determines non-overlapping initial time intervals that are represented by each key frame. Then, it adjusts the positions of key frames and time intervals by iteration, which minimizes the distortion. Experimental result demonstrates the improved performance of our algorithm over the existing approaches.

• Proceedings of the IEEK Conference
• /
• 2000.11c
• /
• pp.137-140
• /
• 2000

In this paper, we propose as new algorithm for the selection of key frames in a given video. For the selected key frames to be well defined, the selected key frames need to spread out on the whole temporal domain of the given video and guaranteed not to be duplicate. For this purpose, we take the first frame of each shot of the video as the candidate key frame to represent the video. To reduce the overall processing time, we eliminate some candidate key frames which are visually indistinct in the histogram difference. The key frames are then selected using a clustering processing based on the singly linked hierarchical tree. To make the selected key frames be distributed evenly on the whole video, the deviation and time difference between the selected key frames are used. The simulation results demonstrate that our method provides the better performance compared with previous methods.

• Smart Media Journal
• /
• v.9 no.1
• /
• pp.23-29
• /
• 2020

This paper presents an approach for dynamic hand gesture recognition by using algorithm based on 3D Convolutional Neural Network (3D_CNN), which is later extended to 3D Residual Networks (3D_ResNet), and the neural network based key frame selection. Typically, 3D deep neural network is used to classify gestures from the input of image frames, randomly sampled from a video data. In this work, to improve the classification performance, we employ key frames which represent the overall video, as the input of the classification network. The key frames are extracted by SegNet instead of conventional clustering algorithms for video summarization (VSUMM) which require heavy computation. By using a deep neural network, key frame selection can be performed in a real-time system. Experiments are conducted using 3D convolutional kernels such as 3D_CNN, Inflated 3D_CNN (I3D) and 3D_ResNet for gesture classification. Our algorithm achieved up to 97.8% of classification accuracy on the Cambridge gesture dataset. The experimental results show that the proposed approach is efficient and outperforms existing methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.1
• /
• pp.38-46
• /
• 2008

Key-frame selection algorithm is defined as the process of selecting a necessary images for 3D reconstruction from the uncalibrated images. Also, camera calibration of images is necessary for 3D reconstuction. In this paper, we propose a new method of Key-frame selection with the minimal error for camera calibration. Using the full-auto-calibration, we estimate camera parameters for all selected Key-frames. We remove the false matching using the fundamental matrix computed by algebraic deviation from the estimated camera parameters. Finally we obtain 3D reconstructed data. Our experimental results show that the proposed approach is required rather lower time costs than others, the error of reconstructed data is the smallest. The elapsed time for estimating the fundamental matrix is very fast and the error of estimated fundamental matrix is similar to others.

• International journal of advanced smart convergence
• /
• v.5 no.4
• /
• pp.1-9
• /
• 2016

In order to reconstruct a 3D model in video sequences, to select key frames that are easy to estimate a geometric model is essential. This paper proposes a method to easily extract informative frames from a handheld video. The method combines selection criteria based on appropriate-baseline determination between frames, frame jumping for fast searching in the video, geometric robust information criterion (GRIC) scores for the frame-to-frame homography and fundamental matrix, and blurry-frame removal. Through experiments with videos taken in indoor space, the proposed method shows creating a more robust 3D point cloud than existing methods, even in the presence of motion blur and degenerate motions.

• Proceedings of the IEEK Conference
• /
• 2001.06c
• /
• pp.213-216
• /
• 2001

Key frame extraction is an important method of summarizing a long video. This paper propose a technique to automatically extract several key frames representative of its content from video. We use the color layout descriptor to select key frames from video. For selection of key frames, we calculate similarity of color layout features extracted from video, and extract key frames using similarity. An important aspect of our algorithm is that does not assume a fixed number of key frames per video; instead, it selects the number of appropriate key frames of summarizing a long video Experimental results show that our method using color layout descriptor can successfully select several key frames from a video, and we confirmed that the processing speed for extracting key frames from video is considerably fast.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.4
• /
• pp.58-66
• /
• 2009

Recently the emerging demands of the light-video encoder promotes lots of research efforts on DVC (Distributed Video Coding). As an appropriate video compression method, DVC has been studied, and Wyner-Ziv (WZ) video compression is its one representative structure. The WZ encoder splits the image into two kinds of frames, one is key frame which is compressed by conventional intra coding, and the other is WZ frame which is encoded by WZ coding. The WZ decoder decodes the key frame first, and estimates the WZ frame using temporal correlation between key frames. Estimated WZ frame (Side Information) cannot be the same as the original WZ frame due to the absence of the WZ frame information at decoder. As a result, the difference between the estimated and original WZ frames are regarded as virtual channel noise. The WZ frame is reconstructed by removing noise in side information. Therefore precise noise estimation produces good performance gain in WZ video compression by improving error correcting capability by channel code. But noise cannot be estimated precisely at WZ decoder unless there is good WZ frame information, and generally it is estimated from the difference of corresponding key frames. Also the estimated noise is limited by comparing with frame level noise to reduce the uncertainty of the estimation method. However these methods cannot provide good noise estimation for every frame or each bit plane. In this paper, we propose a noise nodel selection method which chooses a better noise model for each bit plane after generating candidate noise models. Experimental result shows PSNR gain up to 0.8 dB.

• Steel and Composite Structures
• /
• v.19 no.2
• /
• pp.405-416
• /
• 2015

We proposed the concept of nominal rigidity of a long-span V-shaped rigid frame composite arch bridge, analyzed the effects of structural parameters on nominal rigidity, and derived a theoretical nominal rigidity equation. In addition, we discussed the selection of the arch-to-beam rigidity ratio and its effect on the distribution of internal forces, and analyzed the influence of the ratio on the internal forces. We determined the delimitation value between rigid arch-flexible beam and flexible arch-rigid beam. We summarized the nominal rigidity and arch to beam rigidity ratios of existing bridges. The results show that (1) rigid arch-flexible beam and flexible arch-rigid beam can be defined by the arch-to-beam rigidity ratio; (2) nominal rigidities have no obvious differences among the continuous rigid frame composite arch bridge, V-shaped rigid frame bridge, and arch bridge, which shows that nominal rigidity can reflect the global stiffness of a structure.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.8C
• /
• pp.1133-1141
• /
• 2004

In order to process video data effectively, it is required that the content information of video data is loaded in database and semantic-based retrieval method can be available for various query of users. In this paper, we propose semantic-based video retrieval system which support semantic retrieval of various users by feature-based retrieval and annotation-based retrieval of massive video data. By user's fundamental query and selection of image for key frame that extracted from query, the agent gives the detail shape for annotation of extracted key frame. Also, key frame selected by user become query image and searches the most similar key frame through feature based retrieval method that propose. From experiment, the designed and implemented system showed high precision ratio in performance assessment more than 90 percents.

• Journal of Broadcast Engineering
• /
• v.4 no.2
• /
• pp.155-163
• /
• 1999

In this paper, we propose novel scene change detection and key frame selection techniques, which use two feature images, i.e., DC and edge images, extracted directly from MPEG compressed video. For fast edge image extraction. we suggest to utilize 5 lower AC coefficients of each DCT. Based on this scheme, we present another edge image extraction technique using AC prediction. Although the former is superior to the latter in terms of visual quality, both methods all can extract important edge features well. Simulation results indicate that scene changes such as cut. fades, and dissolves can be correctly detected by using the edge energy diagram obtained from edge images and histograms from DC images. In addition. we find that our edge images are comparable to those obtained in the spatial domain while keeping much lower computational cost. And based on HVS, a key frame of each scene can also be selected. In comparison with an existing method using optical flow. our scheme can select semantic key frames because we only use the above edge and DC images.