• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.5
• /
• pp.175-182
• /
• 2010

The paper presents a novel algorithm for face and iris detection with the application for driver iris monitoring. The proposed algorithm consists of the following major steps: Skin-color segmentation, facial features segmentation, and iris positioning. For the skin-segmentation we applied a multi-layer perceptron to approximate the statistical probability of certain skin-colors, and filter out those with low probabilities. The next step segments the face region into the following categories: eye, mouth, eye brow, and remaining facial regions. For this purpose we propose a novel segmentation technique based on estimation of facial class probability density functions (PDF). Each facial class PDF is estimated on the basis of salient features extracted from a corresponding facial image region. Then pixels are classified according to the highest probability selected from four estimated PDFs. The final step applies the circular Hough transform to the detected eye regions to extract the position and radius of the iris. We tested our system on two data sets. The first one is obtained from the Web and contains faces under different illuminations. The second dataset was collected by us. It contains images obtained from video sequences recorded by a CCD camera while a driver was driving a car. The experimental results are presented, showing high detection rates.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.3
• /
• pp.136-141
• /
• 2012

One of the main reasons for serious road accidents is driving while drowsy. For this reason, drowsiness detection and warning system for drivers has recently become a very important issue. Monitoring physiological signals provides the possibility of detecting features of drowsiness and fatigue of drivers. One of the effective signals is to measure electroencephalogram (EEG) signals and electrooculogram (EOG) signals. The aim of this study is to extract drowsiness-related features from a set of EEG signals and to classify the features into three states: alertness, drowsiness, sleepiness. This paper proposes a neural-network-based drowsiness detection system using Linear Predictive Coding (LPC) coefficients as feature vectors and Multi-Layer Perceptron (MLP) as a classifier. Samples of EEG data from each predefined state were used to train the MLP program by using the proposed feature extraction algorithms. The trained MLP program was tested on unclassified EEG data and subsequently reviewed according to manual classification. The classification rate of the proposed system is over 96.5% for only very small number of samples (250ms, 64 samples). Therefore, it can be applied to real driving incident situation that can occur for a split second.

• Journal of IKEEE
• /
• v.20 no.3
• /
• pp.241-250
• /
• 2016

AVM(Around View Monitoring) is a function of ADAS(Advanced Driver Assistance Systems), which provides a bird's eye view of the surroundings of a vehicle to the user. AVM systems require large bandwidth since they are composed of four input images and require real-time processing for vehicle-embedded environments. Also, the memory bandwidth requirement increases greatly when the resolution of the input data is higher. In this paper, we propose four basic hardware models of AVM systems. The models are decided by whether or not there is a valid data extraction module and an image processing purpose LUT generation module. We analyze the required bandwidth and hardware resource for each model. For verification of the proposed models, we implemented an AVM system using XC7Z045 FPGA and DDR3 memory for VGA and FHD resolution. All four of the proposed hardware model is executed below 33ms, which shows that it can operate in real-time.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.768-773
• /
• 2012

One of the main reasons for serious road accidents is driving while drowsy. For this reason, drowsiness detection and warning system for drivers has recently become a very important issue. Monitoring physiological signals provides the possibility of detecting features of drowsiness and fatigue of drivers. One of the effective signals is to measure electroencephalogram (EEG) signals and electrooculogram (EOG) signals. The aim of this study is to extract drowsiness-related features from a set of EEG signals and to classify the features into three states: alertness, drowsiness, sleepiness. This paper proposes a drowsiness detection system using Linear Predictive Coding (LPC) coefficients and Support Vector Machine (SVM). Samples of EEG data from each predefined state were used to train the SVM program by using the proposed feature extraction algorithms. The trained SVM program was tested on unclassified EEG data and subsequently reviewed according to manual classification. The classification rate of the proposed system is over 96.5% for only very small number of samples (250ms, 64 samples). Therefore, it can be applied to real driving incident situation that can occur for a split second.

• Journal of Information Technology Services
• /
• v.22 no.6
• /
• pp.87-102
• /
• 2023

Existing child car seats do not have a monitoring means for the driver or guardian to effectively recognize the status of whether the seat belt of car seat is fastened and whether the ISOFIX of the car seat is fastened to the inside device of the vehicle. In this paper, we propose a smart car seat system which can monitor in real time, whether the seat belt of a child seated in the car seat is fastened and whether the ISOFIX of the car seat is fastened. The proposed system has been developed with a prototype, in which a Hall sensor, magnet, Bluetooth, and display device are used to detect whether these are fastened and to display the detection results. The prototype system provides the detection results as texts and alarm signal to the display for driver or guardian' smartphone in the car in motion. With functional tests of the prototype system, it was confirmed that the detection functions are properly operated, and the detection results were transmitted to the display device and smartphone via Bluetooth within 0.5 seconds. It is expected that the development system can effectively prevent safety accidents of child car seats.

• Journal of Environmental Health Sciences
• /
• v.31 no.5 s.86
• /
• pp.379-386
• /
• 2005

[ $PM_{10},\;PM_{2.5},\;CO_2\;and\;CO$ ] in driver cabins of subway line from 5 to 8 were monitored from 07:00 through 21:00 (or 19:30 or 20:00) on May. Driver cabin of subway line 7 showed the highest $PM_{10},\;PM_{2.5},\;CO_2\;and\;CO$ concentrations. General Linear Model indicated that subway line, subway location (ground and underground track) and running time (morning and afternoon) significantly influenced the concentrations of $PM_{10},\;PM_{2.5},\;CO_2\;and\;CO$ (p=0.000). Daily profile of $PM_{10},\;PM_{2.5},\;CO_2\;and\;CO$, expressed as an 30 minutes average, showed similar variation pattern over day period. These concentrations showed the highest concentrations between 07:00 and 09:00 of rush hour, slightly dropped and again rose slightly after 18:00. In correlation analysis, significant relations among $PM_{10},\;PM_{2.5},\;CO_2\;and\;CO$ were detected (p<0.01). In particular, correlation coefficient between $PM_{10}\;and\;PM_{2.5}$ was highly significant (r=0.884). Regression analysis also concluded that $PM_{10}$ concentration significantly explained 71.4% of variation of $PM_{2.5}$ concentration (p=0.000, $R^2=0.714$). Correlations by CO with $PM_{10}\;and\;PM_{2.5}$ were 0.451 and 0.520, which were higher than those by $CO_2$. Further study is needed to examine the sources of $PM_{2.5}$ and CO in subway and to compare pollutants concentration among subway lines.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.4
• /
• pp.334-341
• /
• 2015

This paper develops a new system for remotely monitoring and controlling the windows and doors in mobile environment. We design and implement the opening and shutting unit, the gateway, and the control server system, respectively. The opening and shutting unit consists of the driver using DC motor and the motion controller which monitors the state and transfers the control information. The gateway supports TCP/IP and CDMA protocol, which is the interface of wire and wireless communication for transferring the current state and control information. The control server consists of the program to store and process the control information, the middleware to support the processing of various state message, and DB for monitoring the state and remotely controlling the system. Especially, an application software and the Web-based user interface have also been developed to support the mobile environment. The operation performances, environment influences, driving persistences, and operation failure ratio, which are based on PC and smart-phone, have been tested in 2 authorized agencies. The test results show that the developed system has a superior performance.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.4
• /
• pp.436-441
• /
• 2011

A TPMS is a wireless communication system designed to monitor its condition inside the pneumatic tires on various types of vehicles. These systems report the tire pressure information to the driver of the vehicle. While wireless communications is used to transmit the measurement data from TPMS sensors to a central processing unit in the vehicle, it suffers from the various interferences such as sensors of each tire or outside electrical equipments. Based on the conventional beamformer, a switching beamforming technique is proposed to minimize the interference and efficiently receive valid data. Moreover, in order to minimize the interference and reduce power consumption for communication, a system with unique Gold Code is presented for each tire. The performance of interference suppression is illustrated by computer simulations.

• Journal of the Korean Society for Railway
• /
• v.16 no.4
• /
• pp.241-245
• /
• 2013

In the case of the existing train control system, the driver monitors the condition of the vehicle through a composite controller device that displays various information on a screen in the vehicle. However, when problems arise such as car trouble, it is difficult for the drivers to take action immediately. In addition, maintenance personnel have to manually save data one by one after storing the vehicle to analyze control information of the main devices such as the brake controller and auxiliary power. To improve these points, a system that sends and receives all information in real time should be established by installing a sensor communication network and a surveillance system. This study attempts to improve the safety and maintenance of rail vehicles by suggesting a standardized method for train control and surveillance system.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.1
• /
• pp.100-108
• /
• 2016

In this paper, We propose a method which prevents severe traffic jam by controlling traffic signal by itself based on image-processed information and fuzzy logic. The detailed idea of this method is first to let a closed monitoring camera gather the number of cars which show the flow of traffic the designated roads which are commonly considered to have traffic. After executing the image processing method on each image gathered from the monitoring camera, this system determines the changing timing of traffic signal based on fuzzy logic. Also, this image processing method shows good performance in real road environment because the setup background image which used in this system is designed to be updated in real time. All of good points mentioned above would lead driver and users to cost efficient and time efficient results by preventing the increase of the number of traffic on road in advance with the automatic traffic signal controlling algorithm based on the fuzzy logic.