• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.8
• /
• pp.3965-3983
• /
• 2017

We propose a novel eye tracking method that can estimate 3D world coordinates using an infrared (IR) stereo camera for indoor and outdoor environments. This method first detects dark evidences such as eyes, eyebrows and mouths by fast multi-level thresholding. Among these evidences, eye pair evidences are detected by evidential reasoning and geometrical rules. For robust accuracy, two classifiers based on multiple layer perceptron (MLP) using gradient local binary patterns (GLBPs) verify whether the detected evidences are real eye pairs or not. Finally, the 3D world coordinates of detected eyes are calculated by region-based stereo matching. Compared with other eye detection methods, the proposed method can detect the eyes of people wearing sunglasses due to the use of the IR spectrum. Especially, when people are in dark environments such as driving at nighttime, driving in an indoor carpark, or passing through a tunnel, human eyes can be robustly detected because we use active IR illuminators. In the experimental results, it is shown that the proposed method can detect eye pairs with high performance in real-time under variable illumination conditions. Therefore, the proposed method can contribute to human-computer interactions (HCIs) and intelligent transportation systems (ITSs) applications such as gaze tracking, windshield head-up display and drowsiness detection.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2004.03b
• /
• pp.11-19
• /
• 2004

When pile foundation constructed by driving method, it is desirable to perform monitoring and estimation of pile drivability and bearing capacity using some suitable tools. Dynamic Pile Monitoring yields information regarding the hammer, driving system, and pile and soil behaviour that can be used to confirm the assumptions of wave equation analysis. Dynamic Pile Monitoring is performed with the Pile Driving Analyser. The Pile Driving Analyser (PDA) uses wave propagation theory to compute numerous variables that fully describe the condition of the hammer-pile-soil system in real time, following each hammer impact. This approach allows immediate field verification of hammer performance, driving efficiency, and an estimate of pile capacity. The PDA has been used widely as a most effective control method of pile installations. A set of PDA test was performed at the site of Donghea-1 Gas Platform Jacket which is located east of Ulsan. The drilling core sediments of location of jacket subsoil are composed of mud and sand, silt. In this case study, the results of PDA test which was applied to measurement and estimation of large diameter open ended steel pipe pile driven by underwater hydraulic hammer, MHU-800S, at the marine sediments were summarized.

• ETRI Journal
• /
• v.43 no.4
• /
• pp.603-616
• /
• 2021

Over the last few years, autonomous vehicles have progressed very rapidly. The odometry technique that estimates displacement from consecutive sensor inputs is an essential technique for autonomous driving. In this article, we propose a fast, robust, and accurate odometry technique. The proposed technique is light detection and ranging (LiDAR)-based direct odometry, which uses a spherical range image (SRI) that projects a three-dimensional point cloud onto a two-dimensional spherical image plane. Direct odometry is developed in a vision-based method, and a fast execution speed can be expected. However, applying LiDAR data is difficult because of the sparsity. To solve this problem, we propose an SRI generation method and mathematical analysis, two key point sampling methods using SRI to increase precision and robustness, and a fast optimization method. The proposed technique was tested with the KITTI dataset and real environments. Evaluation results yielded a translation error of 0.69%, a rotation error of 0.0031°/m in the KITTI training dataset, and an execution time of 17 ms. The results demonstrated high precision comparable with state-of-the-art and remarkably higher speed than conventional techniques.

• 전자공학회논문지 IE
• /
• v.45 no.4
• /
• pp.33-41
• /
• 2008

Telematics system includes the "vehicle remote diagnosis technology", "driving pattern analysis technology" which are commercially attractive in the real life. To implement those technologies, we need vehicle signal interface, vehicle diagnosis interface, accelerometer/yaw-rate sensor interface, GPS data processing, driving pattern analysis, and CDMA data processing technique. Based on these technologies, we analyze the error existence by diagnosing the EMS(Engine Management System), TMS(Transmission Management System), ABS/TCS, A/BAG in real time. And we are checking about a driving pattern and management of the vehicle, which are sent to the information center through the wireless communication. These database results will make the efficient vehicle and driver management possible. We show the effectiveness of our results by field driving test after completing the H/W & S/W design and implementation for vehicle remote diagnosis and driving pattern analysis.

• Journal of Environmental Impact Assessment
• /
• v.20 no.2
• /
• pp.217-226
• /
• 2011

This paper was inspired by the fact that Real-time Traffic Information Service could play a key role in reducing incomplete combustion time remarkably since it can provide traffic jam information in real-time basis. Emission characteristics of experimental engines were studied with variable travel distances and speed of car in terms of traffic information provided. 12 Km distance road of Susung district in Daegu is taken as an experimental area to examine this new approach. The emission was tested while the driving was done at 8 AM, 3 PM, 6 PM which represents various traffic conditions. The reduced emission has been measured for a travel distance running at different loads (conventional shortest route and Real-time Traffic Information) and various loads (CO, VOC and NOx) are all inventoried and calculated in terms of existing emission factors. The emission has been shown to reduce linearly with travel distance : carbon monoxide (20.56%), VOC (29.21%), NOx(8.86%).

• Journal of Korean Society for Atmospheric Environment
• /
• v.27 no.4
• /
• pp.443-453
• /
• 2011

Real-time Traffic Information Service could play a key role in reducing incomplete combustion time remarkably since it can provide traffic information in real-time basis. Emission characteristics of test engines were studied in terms of travel distance and speed. The present study focused on a north district in Daegu, 12 km. The driving for the emission test was done at 8AM, 3PM, 7PM which represents various traffic conditions. The reduced emissions of Greenhouse Gases (GHG) have been measured for a travel distance running at different loads (conventional shortest route and Real-time Traffic Information) and GHG ($CO_2$, $CH_4$, $N_2O$) are all inventoried and calculated in terms of existing emission factors. The emission of GHG has been shown to reduce linearly with travel distance: $CO_2$ (9.15%), $CH_4$ (18.43%), $N_2O$(18.62%).

• The Journal of the Korea Contents Association
• /
• v.20 no.10
• /
• pp.1-13
• /
• 2020

There are many factors that influence the image quality of CMOS camera images, among which the image exposure time is an important factor. If the image exposure time is long, the entire image on the screen becomes brighter. If the exposure time is shorter, the entire image becomes darker. When photographing a still image, real time is not required because the automatic exposure system is given sufficient time to obtain an appropriate exposure time. However, if the surroundings and environment change rapidly like the black box of a driving car, the exposure time should be applied in response to real time. To this end, a robust automatic exposure system for real-time performance and ambient light environment is required. An automatic exposure system that has real-time capability and is robust against the ambient light environment is required. we designed a real-time control sysem capable of parallel operation processing through the design of an embedded system using zynq's logic and ARM core, and developed a real-time CMOS automatic exposure system that is robust to noise and converges to a desired target value within 66 ms through PID control.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2003.05c
• /
• pp.194-199
• /
• 2003

Depth error correction effect for maladjusted stereo cameras with calibrated pixel distance parameter is presented. The proposed neural network technique is the real time computation method based theory of inter-node diffusion for searching the safety distances from the sudden appearance-objects during the work driving. The main steps of the distance computation using the theory of stereo vision like the eyes of man is following steps. One is the processing for finding the corresponding points of stereo images and the other is the interpolation processing of full image data from nonlinear image data of objects. All of them request much memory space and time. Therefore the most reliable neural-network algorithm is derived for real-time matching of objects, which is composed of a dynamic programming algorithm based on sequence matching techniques.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.352-357
• /
• 2000

A full-scale driving simulator is being developed as an effective test-bed for reproducing realistic driving situation in a safe and tightly controlled environment and conducting various human sensibility ergonomics studies. The simulator will be equipped with a 6 degree-of-freedom, high frequency motion base and a 4 channel, wide field-of-view visual system. The simulator will be fully interactive, highly realistic, and yet economical, taking advantages of the fast growing PC technology.

• Journal of Mechanical Science and Technology
• /
• v.19 no.spc1
• /
• pp.395-402
• /
• 2005

This paper deals with modeling and computer simulation of a full multibody vehicle model for a driving simulator. The multibody vehicle model is based on the recursive formulation and a corresponding simulation code is generated automatically from AUTOCODE, which is a symbolic computation package developed by the authors using MAPLE. The paper describes a procedure for automatically generating a highly efficient simulation code for the full vehicle model, while incorporating realistically modeled components. The following issues have been accounted for in the procedure, including software design for representing a mechanical system in symbolic form as a set of computer data objects, a multibody formulation for systems with various types of connections between bodies, automatic manipulation of symbolic expressions in the multibody formulation, interface design for allowing users to describe unconventional force-and torque-producing components, and a method for accommodating external computer subroutines that may have already been developed. The effectiveness and efficiency of the proposed method have been demonstrated by the simulation code developed and implemented for driving simulation.