• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.4
• /
• pp.755-762
• /
• 2016

Motion graphic is the recently emerged technique which extends the ways of expression in video industry. Currently, it is worldwide trends that the image design gets more attention in the field of movie, advertisement, exhibition, web, mobile, games and new media, etc. With the development of computer's new technologies, VFX methods for the visual content is dynamically changed. Such production methods combine the real scenary and CG(Computer Graphic) to compose realistic scenes, which cannot be pictured in the ways of ordinary filming. This methods overcome the difference between the real and virtual world, maximize the expressive ways in graphics and real space. Match moving is technique of accurate matching between real and virtual camera to provide realistic scene. In this paper we propose the novel technique for motion graphic image production. In this framework we utilize the match moving methods to get the movements of the real camera into 3D layer data.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.2
• /
• pp.36-54
• /
• 2017

The purpose of this paper is to develop a multi-sensor fusion-based traffic information acquisition system with robust to environmental changes. it combines the characteristics of each sensor and is more robust to the environmental changes than the video detector. Moreover, it is not affected by the time of day and night, and has less maintenance cost than the inductive-loop traffic detector. This is accomplished by synthesizing object tracking informations based on a radar, vehicle classification informations based on a video detector and reliable object detections of a infrared range finder. To prove the effectiveness of the proposed system, I conducted experiments for 6 hours over 5 days of the daytime and early evening on the pedestrian - accessible road. According to the experimental results, it has 88.7% classification accuracy and 95.5% vehicle detection rate. If the parameters of this system is optimized to adapt to the experimental environment changes, it is expected that it will contribute to the advancement of ITS.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.2 no.1
• /
• pp.84-88
• /
• 2010

Recently, it is essential to have the system which can track down and identity the random object in the space in which security is a high priority. Due to the fact that we mentioned above, in this paper. We suggest the intelligent video surveillance system effective image-process-education in this paper. The experiment was conducted to check and track down the entering vehicle. And, Pan-Tilt-Zoom camera was used to obtain the enlarged image of the object while a vehicle was making stop in target area. As a result, the experiment has shown the data as following. When the object is in motion, success rate is 97.4%, while success rate is 91% when the object is motionless. By using the suggested system, effective image-process-education is should be achieved because the students who participate in the class can have simultaneous access to the system for real time image data and camera control.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.10
• /
• pp.53-62
• /
• 2011

In this paper, high-tech IT Convergence, to the development of complex technology, special technology, video object recognition technology was considered only as a smart - phone technology with the development of personal portable terminal has been developed crossroads. Technology-based detection of 3D face recognition technology that recognizes objects detected through the intelligent video recognition technology has been evolving technologies based on image recognition, face detection technology with through the development speed is booming. In this paper, based on human face recognition technology to detect the object recognition image processing technology is applied through the face recognition technology applied to the IP camera is the party of the mouth, and allowed the ability to identify and apply the human face recognition, measurement techniques applied research is suggested. Study plan: 1) face model based face tracking technology was developed and applied 2) algorithm developed by PC-based measurement of human perception through the CPU load in the face value of their basic parameters can be tracked, and 3) bilateral distance and the angle of gaze can be tracked in real time, proved effective.

• Journal of Internet Computing and Services
• /
• v.15 no.6
• /
• pp.117-124
• /
• 2014

Cluttered background is a major obstacle in developing salient object detection and tracking system for mobile device captured natural scene video frames. In this paper we propose a context aware feature vector selection model to provide an efficient noise filtering by machine learning based classifiers. Since the context awareness for feature selection is achieved by searching nearest neighborhoods, known as NP hard problem, we apply a fast approximation method with complexity analysis in details. Separability enhancement in feature vector space by adding the context aware feature subsets is studied rigorously using principal component analysis (PCA). Overall performance enhancement is quantified by the statistical measures in terms of the various machine learning models including MLP, SVM, Naïve Bayesian, CART. Summary of computational costs and performance enhancement is also presented.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.3
• /
• pp.20-31
• /
• 2008

In this paper, we propose a single view-based technique for the estimation of human height and position. Conventional techniques for the estimation of 3D geometric information are based on the estimation of geometric cues such as vanishing point and vanishing line. The proposed technique, however, back-projects the image of moving object directly, and estimates the position and the height of the object in 3D space where its coordinate system is designated by a marker. Then, geometric errors are corrected by using geometric constraints provided by the marker. Unlike most of the conventional techniques, the proposed method offers a framework for simultaneous acquisition of height and position of an individual resident in the image. The accuracy and the robustness of our technique is verified on the experimental results of several real video sequences from outdoor environments.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.6
• /
• pp.1135-1142
• /
• 2017

In this paper, we propose an algorithm that can automatically mix the screen and sound by tracking the change of the sound data according to the screen change so that the real sound can be implemented in the personal broadcasting service. Since the personal broadcasting service is often broadcasted lively, it should be convenient to have a real-time mixing. Through experiments, it was confirmed that the sound pressure changes in a wide range in the high frequency band related to the clarity for understanding according to the rotation angle change of the screen. Regression analysis of the sound pressure changes at 2kHz, 4kHz, and 8kHz, The attenuation change of sound pressure was observed at the slope of -1.17, the slope of -2.0, and the slope of -2.44 for each frequency. Therefore, these experiment results can be applied to the VR service. This study is expected to be useful data in the implementation of personal broadcasting service.

• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.97-105
• /
• 2020

A thermal imaging sensor receives the radiating energy from the target and the background, so it has been widely used for detection, tracking, and classification of targets at night for military purpose. In recognizing the target automatically using thermal images, if the correct edges of object are used then it can generate the classification results with high accuracy. However since the thermal images have lower spatial resolution and more blurred edges than color images, the accuracy of the classification using thermal images can be decreased. In this paper, to overcome this problem, a new hierarchical classifier using both shape and local features based on the segmentation reliabilities, and the class/pose updating method for vehicle classification are proposed. The proposed classification method was validated using thermal video sequences of more than 20,000 images which include four types of military vehicles - main battle tank, armored personnel carrier, military truck, and estate car. The experiment results showed that the proposed method outperformed the state-of-the-arts methods in classification accuracy.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.738-747
• /
• 2021

Today, with the improvement of deep learning technology, computer vision areas such as image classification, object detection, object segmentation, and object tracking have shown remarkable improvements. Various applications such as intelligent surveillance, robots, Internet of Things, and autonomous vehicles in combination with deep learning technology are being applied to actual industries. Accordingly, the requirement of an efficient compression method for video data is necessary for machine consumption as well as for human consumption. In this paper, we propose an object-based compression of thermal infrared images for machine vision. The input image is divided into object and background parts based on the object detection results to achieve efficient image compression and high neural network performance. The separated images are encoded in different compression ratios. The experimental result shows that the proposed method has superior compression efficiency with a maximum BD-rate value of -19.83% to the whole image compression done with VVC.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2005.04a
• /
• pp.59-63
• /
• 2005

Respiration motion causes movement of internal structures in the thorax and abdomen, making accurate delivery of radiation therapy to tumors in those areas a challenge. Accounting for such motion during treatment, therefore, has the potential to reduce margins drawn around the clinical target volume (CTV), resulting in a lower dose to normal tissues (e.g., lung and liver) and thus a lower risk of treatment induced complications. Among the techniques that explicitly account for intrafraction motion are breath-hold, respiration gating, and 4D or tumor-tracking techniques. Respiration gating methods periodically turn the beam on when the patient's respiration signal is in a certain part of the respiratory cycle (generally end-inhale or end-exhale). These techniques require acquisition of some form of respiration motion signal (infrared reflective markers, spirometry, strain gauge, thermistor, video tracking of chest outlines and fluoroscopic tracking of implanted markers are some of the techniques employed to date), which is assumed to be correlated with internal anatomy motion. In preliminary study for the respiratory gating radiation therapy, we performed to measurement of this respiration motion signal. In order to measure the respiratory motion signals of patient, respiration measurement system (RMS) was composed with three sensor (spirometer, thermistor, and belt transducer), 4 channel data acquisition system and mobile computer. For two patients, we performed to evaluation of respiratory cycle and shape with RMS. We observed under this system that respiratory cycle is generally periodic but asymmetric, with the majority of time spent. As expected, RMS traced patient's respiration each other well and be easily handled for application.