• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.2 no.3
• /
• pp.53-60
• /
• 2009

The vision-based driver fatigue detection is one of the most prospective commercial applications of facial expression recognition technology. The facial feature tracking is the primary technique issue in it. Current facial tracking technology faces three challenges: (1) detection failure of some or all of features due to a variety of lighting conditions and head motions; (2) multiple and non-rigid object tracking; and (3) features occlusion when the head is in oblique angles. In this paper, we propose a new active approach. First, the active IR sensor is used to robustly detect pupils under variable lighting conditions. The detected pupils are then used to predict the head motion. Furthermore, face movement is assumed to be locally smooth so that a facial feature can be tracked with a Kalman filter. The simultaneous use of the pupil constraint and the Kalman filtering greatly increases the prediction accuracy for each feature position. Feature detection is accomplished in the Gabor space with respect to the vicinity of predicted location. Local graphs consisting of identified features are extracted and used to capture the spatial relationship among detected features. Finally, a graph-based reliability propagation is proposed to tackle the occlusion problem and verify the tracking results. The experimental results show validity of our active approach to real-life facial tracking under variable lighting conditions, head orientations, and facial expressions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05b
• /
• pp.603-607
• /
• 2004

The vision-based driver fatigue detection is one of the most prospective commercial applications of facial expression recognition technology. The facial feature tracking is the primary technique issue in it. Current facial tracking technology faces three challenges: (1) detection failure of some or all of features due to a variety of lighting conditions and head motions; (2) multiple and non-rigid object tracking and (3) features occlusion when the head is in oblique angles. In this paper, we propose a new active approach. First, the active IR sensor is used to robustly detect pupils under variable lighting conditions. The detected pupils are then used to predict the head motion. Furthermore, face movement is assumed to be locally smooth so that a facial feature can be tracked with a Kalman filter. The simultaneous use of the pupil constraint and the Kalman filtering greatly increases the prediction accuracy for each feature position. Feature detection is accomplished in the Gabor space with respect to the vicinity of predicted location. Local graphs consisting of identified features are extracted and used to capture the spatial relationship among detected features. Finally, a graph-based reliability propagation is proposed to tackle the occlusion problem and verify the tracking results. The experimental results show validity of our active approach to real-life facial tracking under variable lighting conditions, head orientations, and facial expressions.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.1
• /
• pp.124-130
• /
• 2007

RFID technology is considered as a promising solution to increase efficiency of port logistics. Especially active RFID technology, such as e-Seal for container security, is receiving attention nowadays. If active RFID system is combined with passive RFID and legacy bar-code system overall efficiency of port logistics can be improved However, due to the device dependent control interface of RFID readers, there are many difficulties in making active-passive combined RFID system environment. In this paper, we introduce Smart Reader Interface (SRI) system, which provides a device independent RFID reader interrace to control different kinds of RFID readers by hiding device dependent control interface through adapter architecture which is similar to device driver of conventional operating systems. The key design objectives of SRI are the followings; conformance to the related standard. efficiency in processing, easy addition of an adapter for a new RFID reader. Actually, the implemented SRI system can support various kinds of commercial RFID readers, and through the test carried out not only in laboratory but also in the container terminal in the GwangYang Port, its practicality is verified.

• Current Optics and Photonics
• /
• v.3 no.5
• /
• pp.415-422
• /
• 2019

Retroreflection of vehicle headlights, as induced by spherical glass beads, is a key optical phenomenon that provides road-surface markings with greatly enhanced visibility, thus better securing a driver's safety in the nighttime as well as in unclear daytime. Retroreflectance of glass beads is a quite sensitive function of their refractive index, so that measurement of the refractive index of glass specifically in the shape of spherical beads needs to be performed within a reasonable uncertainty that is tolerable for road-marking applications. The Becke line method has been applied in assessing refractive index of such glass beads as e.g. an industrial standard in the Republic of Korea; however, the reference refractive-index liquids are not commercially available these days for refractive index greater than 1.80 due to the toxicity of the constituent materials. As such, high-refractive-index glass beads require an alternate method, and in this regard we propose a practically serviceable technique with uncertainty tantamount to that of the Becke line method: Based on comparison of calculated and measured retroreflectance values of commercial glass beads, we discover that their refractive index can be determined with reasonable precision via the retroreflectance measurement. Specifically, in this study the normalized retroreflectance originating from a single glass sphere is computed as a function of refractive index using the Fresnel equations, which is then validated as coinciding well with retroreflectance values measured from actual specimens, i.e. glass-bead aggregates. The uncertainties involved are delineated in connection with radius and imperfections of the glass beads.

• Journal of the Korean association of regional geographers
• /
• v.23 no.2
• /
• pp.403-419
• /
• 2017

This study analyzed the forces to drive the change of urban green spaces in Daegu from 1989 to 2009. First, the loss and fragmentation of green spaces in the past 20 years were spatially identified by performing the hot spots analysis for the cell-based spatial metrics quantifying the size and diversity of green spaces. Next, seven drivers such as slope, distance to roads, land price, population density, ratios of residential, commercial, and industrial areas were selected based on the previous studies and the direction of the association between the loss and fragmentation of green spaces and seven drivers was analyzed with the stepwise logistic regression. Finally, the relative importance of the seven drivers and their interactions in the past 20 years were analyzed with the geographical detector. The results show that the loss of green spaces was concentrated on a part of the Anshim housing development district from 1989 to 2009 and green spaces were highly fragmented around the housing development districts such as Seongseo, Anshim, Dalseong-gun and Chilgok. The forces to drive the loss and fragmentation of green spaces in these areas were different at the administrative levels, but the drivers such as slope and ratios of residential and industrial areas were commonly significant. These drivers were positively correlated with largest patch index(LPI) quantifying the loss of green spaces while they were negatively correlated with Shannon's diversity index(SHDI) measuring the fragmentation of green spaces. In other words, the loss and fragmentation of urban green spaces in Daegu appeared around such regions with lower slope and lower ratios of residential and industrial areas. The relative importance of drivers for LPI was listed as ratio of industrial area, land price, and ratio of commercial area in descending order whereas that of drivers for SHDI was listed as ratio of industrial area, land price, and distance to roads in descending order. Also, the interaction between slope and ratio of residential area had a great impact on LPI and SHDI. The ratio of industrial area was a single driver to most significantly explain the loss and fragmentation of urban green spaces in Daegu in the past 20 years. The interaction between slope and ratio of residential area was greater than the independent influence of a single driver. This study will provide the base data to build a sustainable urban green policy for the city of Daegu in the near future.

• Journal of the Korean Geographical Society
• /
• v.37 no.4
• /
• pp.337-356
• /
• 2002

It was proven that the spatial distribution pattern of the parking lots in Cheongju city was clarified through the concentric expansion of the parking lots, which started out from the center for commercial and business function, into the periphery regions. First of ail, in terms of the spatial distribution pattern of the parking lot according to the operational subject, the parking lot is distributed through private, public, and parking lots attached to buildings in the center, and in its adjacent regions, public and parking lots attached to buildings are distributed. And public parking lot, private and parking lots attached to buildings are distributed in sector pattern. And in terms of facility structure, more than half of the parking lots attached to buildings in Cheongju city are composed of Parking lots of self-driver type. In the case of the center, regional structure of self-Parking type of parking lots attacked to buildings, self-parking type lots on plane street parking, mechanical parking types attached to buildings, self-parking type of plane non-street diversely appear to be combined types, its spatial facility distribution patterns appear to be concentric patterns. Also, in terms of the spatial distribution pattern of the parking lots according to the contact types, with the centralizing of a center, southwestern regions show hourly and monthly charged parking lots; northeastern regions show free parking lots. The spatial distribution pattern of the parking lots as above, reflects the regional distribution change of the establishment and residential location.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.7
• /
• pp.1-8
• /
• 2018

This paper describes new communication methods for transmitting torque commands between the vehicle controller that determines the amount of power generation in a range-extended electric vehicle and the engine controller that performs it. Generally, vehicles use CAN communication, but in this case, the hardware and software of the existing engine controller must be modified. For this reason, it is not easy to apply CAN communication to small and medium sized automotive reorganize companies. Therefore, this research presents a pin-pin communication method for applying the existing mass produced engine controller to range-extended electric vehicles. The pin-pin communication method converts the driver's demand torque control map inside an mass produced engine controller into a virtual accelerator opening position according to the target speed and target torque of the engine, and converts this to a voltage signal for the existing mass produced engine controller to recognize it. The virtual accelerator opening positions are mounted in the form of a control map in the vehicle controller through the reverse conversion process in an offline environment and are determined by the engine generating power requirements and engine optimal operating point algorithm. These algorithms and signal conversion circuits for engine torque transmission have been mounted on the vehicle controller to conduct the virtual accelerator opening position conversion process according to the engine target torque and to establish the virtual accelerator voltage signal using the signal converter.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.3
• /
• pp.1-8
• /
• 2011

The parking guidance system can increase driver's convenience with detailed parking information service, but it continuously consumes electrical energy with large amount of sensors, displays and control modules. With the increase of the demand for green and sustainable building design, it becomes a meaningful issue for parking guidance system to reduce operating power. This paper presents the preliminary design and estimated results of a parking guidance system which is optimized to reduce the power consumption mainly on detectors and displays. The system design is based on commercial wireless parking detectors, wireless-loop-detector and earth-magnetic-detector. We have performed system architecture design, communication network design, parking information service scenario planning, battery life regulation and at last operating power estimation. With the 7 years of battery replace cycle, the estimated result for power consumption of designed system was 0.33W/slot, which is 13% of the traditional system's estimation result. The estimated annual maintain cost was similar to the traditional ultrasonic sensor based system's. The low power operable designed system can be expected to reduce CO2 emission.

• Journal of Korean Society of Transportation
• /
• v.35 no.1
• /
• pp.11-24
• /
• 2017

Although many efforts to stop speeding or inappropriate speed, it failed to reduce the number of speeding-related crashes. Therefore, it is important to analyze the characteristics of speeding offenders and the cause of speeding at hot spots. In this study, we investigate the level of severity in speeding by the characteristics of speeding offenders using the Ordered Logistics Regression Models(OLRM). For the analysis, we use the speeding data collected by 39 traffic enforcement cameras in city of Cheongju and other related data including the speeding ticket history of drivers during the most recent 3 years, their demographic characteristics, their own vehicles, and road environment factors. The major results of this study are as follows. Firstly, commercial fleet drivers are more likely to repeat the conviction of high-range speeding with more than 30km/h over speed limits than other drivers. Secondly, mid-range speeding are observed as 21,462 frequency which is 76.7% of total speeding frequency and occurred mostly at suburban and rural area. It concludes that contributory factors affecting the severity of speeding at signalized intersection are drivers' speeding offence history, posted speed limits, time of day, gender of driver, and location of the intersection as show by the OLRM developed in this study(McFadden R-square : 0.296).

• Journal of Veterinary Clinics
• /
• v.32 no.4
• /
• pp.324-329
• /
• 2015

The primary aim of this study was to investigate biosecurity practices in pig farms and to determine the major risk factors associated with PCV2 infection for a sampled swine population in Korea. To this end, we analyzed data from a cross-sectional study of 296 farrow-to-finish farms, which was conducted between March and September 2014 to explore the prevalence of swine disease at farm level. Face-to-face interviews by on-site visit of trained veterinarians were conducted with the farm owners or managers using a standardized questionnaires with information about basic demographical data and management practices. Farms were classified as negative or positive through the use of infection profiles that combined data on serological testing including PCR antigen test result, antibody titer and sero-conversion pattern at each age category taking into account vaccination status. Data were analyzed using multivariate ordinal logistic regression. Results from this study indicated that biosecurity level of the farms was considered not good given low compliance of the biosecurity programs and facilities in the farm: off-site removal of dead stocks (7%), off-site location of storage facility for incoming feeds (12.6%), off-site pick-up location for finishers (19.3%), restrictions on feed supplier vehicles for farm entrance (19.6%), restriction of finisher trucks entering the farm (22.4%), and restriction on manure disposal trucks entering the farm (26.4%). In the final model (n = 255), allowance of finisher truck driver to the pig unit had increased risk of infection (OR = 2.4, 95% CI 1.22-4.67) whereas farms with a sign forbidding the entrance had decreased risk of infection (OR = 0.19, 95% CI 0.10-0.58). Further comprehensive research with larger sample size is required to better understand the multifactorial characteristic that some predisposing risk factors that were not available in this study. To the best knowledge of the authors, this was the first study to use empirical data to report risk factors associated with PCV2 infection in the Korean pig farms. Results from the current study could be used to decide optimal biosecurity measures to reduce the impact of PCV2 infection to farmers and policy makers.