• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.4
• /
• pp.191-197
• /
• 2022

This study proposes an image-based Pose Intention Network (PIN) algorithm for rehabilitation via patients' intentions. The purpose of the PIN algorithm is for enabling an active rehabilitation exercise, which is implemented by estimating the patient's motion and classifying the intention. Existing rehabilitation involves the inconvenience of attaching a sensor directly to the patient's skin. In addition, the rehabilitation device moves the patient, which is a passive rehabilitation method. Our algorithm consists of two steps. First, we estimate the user's joint position through the OpenPose algorithm, which is efficient in estimating 2D human pose in an image. Second, an intention classifier is constructed for classifying the motions into three categories, and a sequence of images including joint information is used as input. The intention network also learns correlations between joints and changes in joints over a short period of time, which can be easily used to determine the intention of the motion. To implement the proposed algorithm and conduct real-world experiments, we collected our own dataset, which is composed of videos of three classes. The network is trained using short segment clips of the video. Experimental results demonstrate that the proposed algorithm is effective for classifying intentions based on a short video clip.

• The Journal of the Korea Contents Association
• /
• v.17 no.3
• /
• pp.42-52
• /
• 2017

Panorama image is a single image obtained by combining images taken at several viewpoints through matching of corresponding points. Existing panoramic image generation methods that find the corresponding points are extracting local invariant feature points in each image to create descriptors and using descriptor matching algorithm. In the case of video sequence, frames may be a lot, so therefore it may costs significant amount of time to generate a panoramic image by the existing method and it may has done unnecessary calculations. In this paper, we propose a method to quickly create a single panoramic image from a video sequence. By assuming that there is no significant changes between frames of the video such as in locally, we use the FAST algorithm that has good repeatability and high-speed calculation to extract feature points and the Lucas-Kanade algorithm as each feature point to track for find the corresponding points in surrounding neighborhood instead of existing descriptor matching algorithms. When homographies are calculated for all images, homography is changed around the center image of video sequence to warp images and obtain a planar panoramic image. Finally, the spherical panoramic image is obtained by performing inverse transformation of the spherical coordinate system. The proposed method was confirmed through the experiments generating panorama image efficiently and more faster than the existing methods.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.1 no.1
• /
• pp.51-54
• /
• 2009

In or automotive engineering education is introduced. Main objective of the system is teaching disassemble/assemble procedure of automatic transmission of a vehicle to students, who study automotive engineering. System includes vehicle transmission, set of tools and mechanical facilities, two video cameras, computer with developed software, HMD glasses and two LCD screens. Developed software gives instructions on assembling and disassembling processes of real vehicle transmission with the help of augmenting virtual reality objects on the video stream. Overlaying of 3D instructions on the technological workspace can be used as an interactive educational material. In disassembling process, mechanical parts which should be disassembled are augmented on video stream from video cameras. Same is done for assembling process. Animation and other visual effects are applied for better indication of the current assembling/disassembling instruction. During learning and training, student can see what parts of vehicle transmission and in which order should be assembled or disassembled. Required tools and technological operations are displayed to a student with the help of augmented reality, as well. As a result, the system guides a student step-by-step through an assembly/disassembly sequence. During educational process a student has an opportunity to return back to any previous instruction if it is necessary. Developed augmented reality system makes educational process more interesting and intuitive. Using of augmented reality system for engineering education in automotive technology makes learning process easier and financially more effective.

• Journal of Broadcast Engineering
• /
• v.22 no.6
• /
• pp.808-816
• /
• 2017

360 VR video systems has become important to provide immersive effect for viewers. The system consists of stitching, projection, compression, inverse projection, viewport extraction. In this paper, an efficient luminance compensation technique for 360 VR video sequences, where feature extraction and histogram equalization algorithms are utilized. The proposed luminance compensation algorithm enhance the performance of stitching in 360 VR system. The simulation results showed that the proposed technique is useful to increase the quality of the displayed image.

• Journal of Korea Multimedia Society
• /
• v.8 no.9
• /
• pp.1177-1186
• /
• 2005

In vision-based interfaces for video games, gestures are used as commands of the games instead of pressing down a keyboard or a mouse. In these Interfaces, unintentional movements and continuous gestures have to be permitted to give a user more natural interface. For this problem, this paper proposes a novel gesture spotting method that combines spotting with recognition. It recognizes the meaningful movements concurrently while separating unintentional movements from a given image sequence. We applied our method to the recognition of the upper-body gestures for interfacing between a video game (Quake II) and its user. Experimental results show that the proposed method is on average $93.36\%$ in spotting gestures from continuous gestures, confirming its potential for a gesture-based interface for computer games.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.3
• /
• pp.120-126
• /
• 2005

This paper presents the 3D wavelet based video compression system using quad-tree algorithm. The 3D wavelet based video compression system removes the temporal correlation of the input sequences using the motion compensation filter and decomposes the spatio-temporal subband using the spatial wavelet transform. The proposed system allocates the higher bit rate to the low frequency image of the 3D wavelet sequences and improves the 0.64dB PSNR performance of the reconstructed image in comparison with that of H.263. In addition to the limitation on the propagation of the motion compensation error by the 3D wavelet transform, the proposed system progressively transmits the input sequence according to the resolution and rate scalability.

• Journal of Broadcast Engineering
• /
• v.3 no.2
• /
• pp.127-137
• /
• 1998

In this paper, we propose the method of extracting edge information from MPEG video sequences for the detection of scene changes. In a the proposed method, five significant AC coefficients of each MPEG block are utilized to obtain edge images from the MPEG video. AC edge images obtained by the proposed scheme not only produce better object boundary information than conventional methods using only DC coefficients, but also can reduce the boundary effects produced by DC-based. Since the AC edge image contains the content information of each frame, it can be effectively utilized for the detection of scene change as well as the content-based video query. Experimental results show that the proposed method can be effectively utilized for the detection of scene changes.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.4
• /
• pp.868-876
• /
• 1999

In this paper, an efficient automatic video parsing technique on MPEG-compressed video that is fundamental for content-based indexing is described. The proposed method detects scene changes, regardless of IPB picture composition. To detect abrupt changes, the difference measure based on the dc coefficient in I picture and the macroblock reference feature in P and B pictures are utilized. For gradual scene changes, we use the macroblock reference information in P and B pictures. the process of scene change detection can be efficiently handled by extracting necessary data without full decoding of MPEG sequence. The performance of the proposed algorithm is analyzed based on precision and recall. the experimental results verified the effectiveness of the method for detecting scene changes of various MPEG sequences.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.132-140
• /
• 2011

Ultra-High Definition Television (U-HDTV) is a promising candidate for the next generation television. Since the U-HDTV video signal requires a huge amount of data, parallel implementation of the U-HDTV compression system is highly demanding. In the conventional parallel video codec, a video is divided into sub-sequences and the sub-sequences are independently encoded. In this paper, for efficient parallel processing, we propose a pipelined encoding structure which exploits cross-correlation among the sub-sequences. The experimental results demonstrate that the proposed technique improves the coding efficiency and provides the sub-sequences of the balanced visual quality.

• Journal of IKEEE
• /
• v.19 no.2
• /
• pp.244-253
• /
• 2015

Please This paper presents method of video stabilization based on detection and adaptive motion smoothing filtering of undesirable motion. The proposed algorithm consists of two stages: the detection of undesirable motion and smoothing filtering of detected undesired motion. To incorporate desired properties into the motion smoothing process, the local maximum and the local minimum are defined in a set composed of the parameters of accumulative global motion. Using the local information, the constraints on detecting undesirable motions are defined. Based on these constraints, the alpha parameter of the alpha-trimmed means filter is adjusted, so that the degree of motion smoothing in the reconstructed video sequence is controlled. The experimental results demonstrated the capability of the proposed algorithm.