Seungwon Oh

Drowsy Driving Detection Based on the Driver's Head Movement using Infrared Sensors

In the driving circumstance, the driver¿s condition is directly connected with the car accident. Therefore, there are many researches to decrease the car accidents by keeping the driver¿s state in a good condition. While many of these researches are focused on the driver¿s face, our approach is focused on the driver¿s head movement. By collecting the driver¿s head position and extracting the feature points, the proposed system calculates the driver¿s physical state: Normal driving or Drowsy driving. The experimental results showed 78% of success rate to find the drowsy driving in the real driving situations.

Drowsy driving detection based on human pulse wave by photoplethysmography signal processing

Drowsiness of driver while driving is one major factor of traffic accident. Therefore, there are many researches to prevent and detect drowsy driving. Recent researches have focused on motion detection using cameras to determine drowsy driving. However, we have focused on non-invasive and inexpensive drowsiness detection system. In our previous research, we suggested a system based on the drivers head movement using infrared sensors. In this paper, we suggest another non-invasive and inexpensive system based on the drivers pulse wave by photoplethysmography (PPG) signal processing. Firstly, the system collects a pulse wave from a PPG sensor on a steering wheel and then it processes the signal to analyze drivers state. In order to evaluate the effectiveness of a human pulse wave for drowsiness detection, we integrated two systems. The experimental result using new integration system showed 83 percent drowsy driving detection rate in the state of real driving.

Unified Performance Authoring Tool for Heterogeneous Devices and Protocols

A contents authoring software with device management for interactive shows and performances is proposed. The proposed system allows user to register and to manage various stage-related devices such as lighting system, fog generator, robots or multimedia players. In this paper, we describe software architecture, XML specification for unified protocol description, and user interface of the proposed system. The system can control multiple devices of heterogeneous protocols in timely manner. Once devices are registered, user can browse commands of each device and can organize commands to step-based list according to the performance scenario. Unlike current commercialized products, the system allows to manipulate authored list of commands during the show instantly. The proposed system also supports to control playback of authored commands by sensor inputs so that a player can trigger devices to execute according to events. The contributions of this paper can be summarized to three points; (1) define unified protocol description with XML structures for simplicity (2) give sensor triggering capability to control devices, and (3) implement fast and instant manipulation user interface during the show.

Music Mood Classification Using Intro and Refrain Parts of Lyrics

In this paper, we propose an lyrics-based classification approach. It estimates a mood of a song with only intro and refrain parts of lyrics. In general, the intro part creates a specific atmosphere of a song, and the chorus part is the strongest part of the song. The proposed method detects important features significantly associated with the mood of songs from the both parts. By calculating the similarity between terms of the parts and eight basic emotions, it can classify songs according to mood.

Simultaneous Localization and Mapping for Mobile Robots in Dynamic Environments

This paper presents a new SLAM framework for solving the problem of SLAM in dynamic environments. The landmark location change causes the error of robot pose estimation and landmark mapping. In this paper, we propose Dynamic EKF SLAM based on the independence of the dynamic landmarks. The proposed framework decomposes the SLAM problem into a traditional SLAM problem for the static landmarks and individual SLAM problems for the dynamic landmarks. Therefore, in the dynamic environments, it is able to minimize the error caused by the dynamic landmarks and reduce the uncertainty in the robot pose and the landmark locations. The simulation results show the validity and robustness of the proposed approach in terms of robot path estimation error, landmark location mapping error, and the variances of robot and landmarks.

Dynamic EKF-based SLAM for autonomous mobile convergence platforms

This paper presents a new Simultaneous Localization and Mapping (SLAM) framework for solving the problem of SLAM in dynamic environments. The landmark location change causes the error of robot pose estimation and landmark mapping. In this paper, we propose the Dynamic Extended Kalman Filter (EKF) SLAM based on the independence of the dynamic landmarks. The proposed framework decomposes the SLAM problem into a traditional SLAM problem for the static landmarks and individual SLAM problems for the dynamic landmarks. Therefore, in the dynamic environments, it is able to minimize the error caused by the dynamic landmarks and reduce the uncertainty in the robot pose and the landmark locations. In order to validate the proposed approach, we implement an indoor mobile robot platform with a Red Green Blue - Depth (RGB-D) sensor and utilize Speeded Up Robust Features (SURF) algorithm to extract appearance-based features. The simulation and experimental results show the validity and robustness of the Dynamic EKF SLAM in indoor environments including the dynamic landmarks.

Digital Costume Platform for the Expansion of Stage Representation Technology using LEDs

Recently, LEDs are used in various fields such as lightings, billboards, displays, and so on. In this paper, we tried to combine a costume with LEDs in a performance environment. To meet the environmental requirements, we propose a digital costume platform which consists of wireless network, an embedded system, a control jacket, a digital skin, and a pattern authoring tool. It is utilized for making a digital costume with LED lighting effects. The embedded system controls LED lighting according to the signals from a show control system through wireless networks. The control jacket can carry the embedded system and connect it with LEDs. The digital skin means a costume with LEDs. The LEDs were designed to fit in performance concept in point of aesthetic. The pattern authoring tool enables users to make timeline-based changing patterns of LED lighting. The proposed platform is a new lighting element in performances. It can expand stage representation techniques and be used as a special effect. It will play a role as a moving light in performances. We evaluated stable operations of our platform by employing it in live performances.

Energy self-sufficient electrolysis apparatus for sterilization of portable toilet in small vessels

Marine caused pollution occurs mostly near coastal area and its main cause was known to be human feces issued from small vessels. To sterilize liquid pollutants from portable toilets of small vessels, an electrolysis treatment is judged to be the most economic and stable method considering an environment of its use. In this paper, we presents an electrolysis apparatus which is the most appropriate for sterilizing pollutants from portable toilets of small vessels and derives the minimum operating time of the apparatus for sterilizing norovirus which is a main target of marine caused pollution sources. In order to utilize renewable energy, we designed an apparatus which generates a renewable energy from solar cells. As a result, we could confirm the applicability of the proposed system with the results from experiments in three cases of different weather conditions.

The ontology for experience media authoring system

We propose the ontology-based inference rule for an experience media authoring system. The experience media lets people feel realistic while satisfying the five senses. The experience media means the media recreating more realistic situation by utilizing various peripheral devices in addition to audio-visual contents. The proposed ontology has advantages in producing the experience media by defining the relationships between sensory effects and sensory devices and utilizing ontology semantic knowledge representation as the expansion of the previous research. We also implemented an application, the Ontology-based Multi-Sensory Inference Engine (OMSIE), applying the proposed ontology model. The OMSIE infers sensory effect information from the given multimedia content information.

Proposal of an Artificial Emotion Expression System Based on External Stimulus and Emotional Elements

Recently, for intelligent agents, the concept of emotion has become more and more important and many researchers think that emotion is one of the major factors for more natural and friendly interaction between human and agents [1]. There have been several researches to build more emotional creatures.