Minwoo Lee

Design of Exhibition contents using swipe gesture recognition communication based on Kinect

Exhibition content has been used a touch panel for the users convenience. Touch panel are not good recognition. And errors may occur when you use a long time. In addition there occurs a malfunction due to contamination. In the present study, such problems want to improve. We designed the Exhibition contents to recognize the swipe gesture of Kinect. Gesture recognition is constructed in three steps of Modeling, analysis, and recognition. Such gesture recognition was implemented using Kinect. Kinect provides Depth information of the image, Color Information and dimensional coordinates of your joints. Using this information in Were aware of the Hand movements. The KIOSK was controlled by use in 4 kind(up, down, left, and right) swipe gestures In order to verify the performance of the Exhibition contents applying the Kinect swipe gesture depth information and RGB image were used. And, verified the performance of the swipe gesture recognition and exhibition contents operations.

Forward Error Correction based Adaptive data frame format for Optical camera communication

Optical camera communication (OCC) is an extension of Visible Light Communication. Different from traditional visible light communication, optical camera communications is an almost no additional cost technology by taking the advantage of build-in camera in devices. It was became a candidate for communication protocol for IoT. Camera module can be easy attached to IoT device, because it is small and flexible. Furthermore almost smartphone equip one or two camera for both back and font side with high quality and resolution. It can be utilized for receiving the data from LED or positioning. Actually, OCC combines illumination and communication. It can supply communication for special areas or environment where do not allow Radio frequency such as hospital, airplane etc. There are many concept and experiment be proposed. In this paper we proposed utilizing Android smart-phone camera for receiver and introduce new approach in modulation scheme for LED at transmitter. It also show how Manchester coding can be used encode bits while at the same time being successfully decoded by Android smart-phone camera. We introduce new data frame format for easy decoded and can be achieve high bit rate. This format can be easy to adapt to performance limit of Android operator or embedded system.

Depth Sensor Combined Display Contents Control System

In this paper, we proposed a Depth Sensor Combined Display Contents Control System. Gestures recognition using depth sensor is generally composed of three steps as modeling, analysis, recognition. Gesture modeling is to create mathematical model of recognized gestures [1-2]. The approach for modeling can conduct a pivotal role in the gesture recognition and gesture analysis performance. If model is created, it can recognize gestures through parameters extracted from the input video. So, in this paper, we proposed a Depth Sensor Combined Display Contents Control System.

Sound source matching LED emotion contents design

In this paper, we proposed LED emotion contents design matched with sound source. LED emotion contents correct inputs signal (sound source) by matching to human emotion. Also, we used liner mapping methods, nonlinear mapping methods for displaying LED emotion contents matched with sound source. So, we proposed a LED emotion contents design and control matched with sound source.

Wall switch based LED light dimming system

Due to the development of recent semiconductor manufacturing technology, LED drew big attention as a new light source. Moreover, LED light can improve the energy saving efficiency by a dimming system. In this paper, we describe the new LED light dimming system by using the light switch. Also, we present experimental results that show proposed dimming system is valid.

Features extraction of fluorescent light image for positioning information acquisition using steerable Gaussian filter

Indoor positioning technology has been a goal of ubiquitous computing research. In this paper, we show the feasibility of detecting fluorescent light based on the camera images received from a smart phone. We present a robust and real time approach to fluorescent light detection in indoor environments. It is based on taking a ceiling image by Smartphone image sensor, filtering using selective oriented Gaussian filters. Our algorithm can detect all fluorescent light in still images of indoor environments in various conditions.

POSE-VIWEPOINT ADAPTIVE OBJECT TRACKING VIA ONLINE LEARNING APPROACH

In this paper, we propose an effective tracking algorithm with an appearance model based on features extracted from a video frame with posture variation and camera view point adaptation by employing the non-adaptive random projections that preserve the structure of the image feature space of objects. The existing online tracking algorithms update models with features from recent video frames and the numerous issues remain to be addressed despite on the improvement in tracking. The data-dependent adaptive appearance models often encounter the drift problems because the online algorithms does not get the required amount of data for online learning. So, we propose an effective tracking algorithm with an appearance model based on features extracted from a video frame.