• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2005.11a
• /
• pp.282-285
• /
• 2005

This paper discusses the interactive system for smart home environments. In order to realize this, the main emphasis of the paper lies on the description of the multiple signal processing on the basis of the technologies such as fingerprint recognition, video signal processing, speech recognition and synthesis. For essential modules of the interactive system, we adopted the motion detector based on the changes of brightness in pixels as well as the fingerprint identification for adapting home environments to the inhabitants. In addition, the real-time speech recognizer based on the HM-Net(Hidden Markov Network) and the speech synthesis were incorporated into the overall system for interaction between user and system. In experimental evaluation, the results showed that the proposed system was easy to use because the system was able to give special services for specific users in smart home environments, even though the performance of the speech recognizer was not better than the simulation results owing to the noisy environments.

• Journal of Digital Convergence
• /
• v.12 no.1
• /
• pp.319-324
• /
• 2014

In recent years, high-performance flying drones attract attention for many peoples. In particular, the drone equipped with multi-rotor is expanding its range of utilization in video imaging, aerial rescue, logistics, monitoring, measurement, military field, etc. However, the control function of its controller is very simple. In this study, using a G-sensor mounted on a mobile device, implements an enhanced controller to control flying drones through the intuitive gesture of user. The implemented controller improves the gesture recognition performance using a neural network algorithm.

• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.955-959
• /
• 2009

In this paper, we propose a novel method for analyzing human interactions based on the walking trajectories of human subjects. Our principal assumption is that an interaction episode is composed of meaningful smaller unit interactions, which we call 'sub-interactions.' The whole interactions are represented by an ordered concatenation or a network of sub-interaction models. From the experiments, we could confirm the effectiveness and robustness of the proposed method by analyzing the inner workings of an interaction network and comparing the performance with other previous approaches.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.7
• /
• pp.1280-1286
• /
• 2001

In this Study, we try to suggest a system that recognize worker's regular motion more effectively First, based on frame difference that separates still background from movable object to video that make a film of worker's motion. The next, with edge detection, estimating the center of motion could recognize continuous motion. By action cognition system that design in this research films worker's action using fixed CCTV to supplement problem of action awareness system that is applied in existent industry spot, various mountings to get action information minimized. Also, shorten session that need in awareness enforcing action awareness through image subtraction and edge detection between frame to reduce time necessary to draw worker's body part special quality, expense designed inexpensive action cognition system as being efficient.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.808-810
• /
• 2011

The background estimation algorithms had a significant impact on the performance of image processing and recognition. In this paper, background estimation algorithms were analysis of complexity and performance as preprocessing of image recognition. It was evaluated the performance of Gaussian Running Average, Mixture of Gaussian, and KDE algorithm. The simulation results show that KDE algorithm outperforms compared to the other algorithms.

• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.36T no.4
• /
• pp.9-16
• /
• 1999

We suggest the image recognition algorithm for automatic decision of EUT malfunction using computer vision in the radiant electromagnetic field. We monitor and analyze the EUT malfunction through the numerical value change of electro-measurement and medical instruments, or the image distortion of PC monitor. We could decide EUT malfunction by comparing the object image in the electromagnetic field with the reference image or by recognizing the numerical value change on the video camera monitor. We can show the evidence of EUT malfunction decision and reduce the possibility of malfunction in the tolerance test.

• Fire Science and Engineering
• /
• v.22 no.4
• /
• pp.27-32
• /
• 2008

In this paper, a flame and smoke detection algorithm is proposed to recognize a fire. Flame and smoke have specific color distribution and continuously change shapes of them. In the proposed flame detection algorithm, specific regions are candidated as flame by color distributions and variations of frames of video. Some of candidated regions are decided as flame by the magnitude of motion vector. To determine smoke in the field of view of camera, edge is important because high frequency component is decreased by it. Candidated region of smoke is assigned by color distributions, inter-frame differences and the value of edge. The candidated region is settled as smoke region with magnitude of motion vector. As results of simulations, it is shown that the proposed algorithm is useful for flame and smoke detection.

• Journal of Sensor Science and Technology
• /
• v.24 no.1
• /
• pp.69-77
• /
• 2015

The Microsoft Kinect is a motion sensing input device which is widely used for many motion recognition applications such as fitness, sports, and rehabilitation. Until now, most of remote rehabilitation systems with the Microsoft Kinect have allowed the user or patient to do rehabilitation or fitness by following the motion of a video screen. However in this paper we propose a smart remote rehabilitation system with the Microsoft Kinect motion sensor and a wearable ECG sensor which can allow patients to offer monitoring of the individual's performance and personalized feedback on rehabilitation exercises. The proposed noble smart remote rehabilitation is able to monitor and measure the state of the patient's condition during rehabilitation exercise, and transmits it to the prescriber. This system can give feedback to a prescriber, a doctor and a patient for improving and recovering motor performance. Thus, the efficient rehabilitation training service can be provided to patient in response to changes of patient's condition during exercise.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.4
• /
• pp.618-632
• /
• 2010

This paper presents a novel approach to control the augmented reality (AR) objects robustly in a marker-less AR system by fingertip tracking and hand pattern recognition. It is known that one of the promising ways to develop a marker-less AR system is using human's body such as hand or face for replacing traditional fiducial markers. This paper introduces a real-time method to manipulate the overlaid virtual objects dynamically in a marker-less AR system using both hands with a single camera. The left bare hand is considered as a virtual marker in the marker-less AR system and the right hand is used as a hand mouse. To build the marker-less system, we utilize a skin-color model for hand shape detection and curvature-based fingertip detection from an input video image. Using the detected fingertips the camera pose are estimated to overlay virtual objects on the hand coordinate system. In order to manipulate the virtual objects rendered on the marker-less AR system dynamically, a vision-based hand control interface, which exploits the fingertip tracking for the movement of the objects and pattern matching for the hand command initiation, is developed. From the experiments, we can prove that the proposed and developed system can control the objects dynamically in a convenient fashion.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.24-29
• /
• 2009

Sound source localization system is used in a robot, a video conference and CCTV(Closed-circuit television) systems. In this Sound source localization systems are applied to human and they can receive a number of sound data frames during speaking. In this paper, we propose methods which is reducing angle estimation error by selecting sound data frame which can more precisely compute the angles from inputted sound data frame. After selected data converted to angle, the error of sound source localization recognition system can be reduced by applying to medium filter. By the experiment using proposed system it is shown that the average error of angle estimation in sound source recognition system can be reduced up to 31 %.