• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.2
• /
• pp.69-75
• /
• 2014

Existing People Counting System using a single overhead mounted camera has limitation in object recognition and counting in various environments. Those limitations are attributable to overlapping, occlusion and external factors, such as over-sized belongings and dramatic light change. Thus, this paper proposes the new concept of People Counting System by Facial Age Group using two depth cameras, at overhead and frontal viewpoints, in order to improve object recognition accuracy and robust people counting to external factors. The proposed system is counting the pedestrians by five process such as overhead image processing, frontal image processing, identical object recognition, facial age group classification and in-coming/out-going counting. The proposed system developed by C++, OpenCV and Kinect SDK, and it target group of 40 people(10 people by each age group) was setup for People Counting and Facial Age Group classification performance evaluation. The experimental results indicated approximately 98% accuracy in People Counting and 74.23% accuracy in the Facial Age Group classification.

• Journal of Digital Contents Society
• /
• v.15 no.4
• /
• pp.457-464
• /
• 2014

Recently, interests in space information data are increasing due to the initiation of spatial information open platform service by the Ministry of Land, Infrastructure and Transport. The purpose of this study is optimizing management and storing of the texture data, one kinds of 3D-spatial data. First, extract 3D-spatial data through the aerial triangulation and 3D-writing using raw image taken with the Multi-directional aerial camera and the vertical aerial camera. And develop the method to create single texture data and related technique by align and place corresponding 3D-spatial data to optimal storage space. Through experiment, the results show effect of 8 times of storage capacity reduction compared to existing single-file storage method, additionally, new method can improve file management efficiency in comparison with multiple file storage method. The results of this study can be cornerstone of three-dimensional space information management when dealing with bulk data, and utilizations will be enhanced through the further studies and algorithm improvement.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.1
• /
• pp.56-63
• /
• 2003

This paper introduces a vision based autonomous mini mobile robot that is an approach to produce real autonomous vehicle. Previous autonomous vehicles are dependent on PC, because of complexity of designing hardware, difficulty of installation and abundant calculations. In this paper, we present an autonomous motile robot system that has abilities of accurate steering, quick movement in high speed and intelligent recognition as a stand-alone system using a mono camera. The proposed system has been implemented on mini track of which width is 25~30cm, and length is about 200cm. Test robot can run at average 32.9km/h speed on straight lane and average 22.3km/h speed on curved lane with 30~40m radius. This system provides a model of autonomous mobile robot adapted a lane recognition algorithm in odor to make real autonomous vehicle easily.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.4 s.310
• /
• pp.66-73
• /
• 2006

Safety is the most important for all traffic management and control technology. This paper focuses on developing a flexible, reliable and real-time processing algorithm which is able to generate signal for the entering vehicle at the joining road through a camera and image processing technique. The images obtained from the camera located beside and upon the road can be used for traffic surveillance, the vehicle's travel speed measurement, predicted arriving time in joining area between main road and joining road. And the proposed algorithm displays the confluence safety signal with red, blue and yellow color sign. The three methods are used to detect the vehicle which is driving in setted detecting area. The first method is the gray scale normalized correlation algorithm, and the second is the edge magnitude ratio changing algorithm, and the third is the average intensity changing algorithm The real-time prototype confluence safety signal generation algorithm is implemented on stored digital image sequences of real traffic state and a program with good experimental results.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.6
• /
• pp.1139-1145
• /
• 2014

User recognition technology, which identifies or verifies a certain individual is absolutely essential under robotic environments for intelligent services. The conventional face recognition algorithm using single distance face image as training images has a problem that face recognition rate decreases as distance increases. The face recognition algorithm using face images by actual distance as training images shows good performance but this has a problem that it requires user cooperation. This paper proposes the LDA-based long distance face recognition method which uses multiple distance face images from a zoom camera for training face images. The proposed face recognition technique generated better performance by average 7.8% than the technique using the existing single distance face image as training. Compared with the technique that used face images by distance as training, the performance fell average 8.0%. However, the proposed method has a strength that it spends less time and requires less cooperation to users when taking face images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.9
• /
• pp.1088-1095
• /
• 2019

The information and communication technology that is being developed recently has been greatly influencing the automobile market. In recent years, devices equipped with IT technology have been installed for the safety and convenience of the driver. However, it has the advantage of increased convenience as well as the disadvantage of increasing traffic accidents due to driver's distraction. In order to prevent such accidents, it is necessary to develop safety systems of various types and ways. In this paper implements a platform that can recognize LDWS and FCWS and PDWS by using a single camera without using radar sensor and camera fusion and stereo camera method using two or more sensors, and proposes to study multi-function driving safety platform using a single camera by analyzing recognition rate evaluation and validity on a vehicle.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.5
• /
• pp.139-148
• /
• 2009

In this paper, I propose an automatic analysis method of golf swine from single-camera video sequences. I define necessary swing features for automatic swing analysis in 2-dimensional environment and present efficient swing analysis methods using various image processing techniques including line and edge detection. The proposed method has two characteristics compared with previous swing analysis systems and related studies. First, the proposed method enables an automatic swing analysis in 2-dimension while previous systems require 3-dimensional environment which is relatively complex and expensive to run. Second, swing analysis is done automatically without human intervention while other 2-dimensional systems necessarily need analysis by a golf expert. I tested the method on 20 swing video sequences and found the proposed method works effective for automatic analysis of golf swing.

• Progress in Medical Physics
• /
• v.20 no.2
• /
• pp.51-61
• /
• 2009

A Compton camera, which is based on the geometrical interpretation of Compton scattering, is a very promising gamma-ray imaging device considering its several advantages over the conventional gamma-ray imaging devices: high imaging sensitivity, 3-D imaging capability from a fixed position, multi-tracing functionality, and almost no limitation in photon energy. In the present study, a Monte Carlo-based, user-friendly Compton imaging simulator was developed in the form of a graphical user interface (GUI) based on Geant4 and $MATLAB^{TM}$. The simulator was tested against the experimental result of the double-scattering Compton camera, which is under development at Hanyang University in Korea. The imaging resolution of the simulated Compton image well agreed with that of the measured image. The imaging sensitivity of the measured data was 2~3 times higher than that of the simulated data, which is due to the fact that the measured data contains the random coincidence events. The performance of a stacking-structure type Compton camera was evaluated by using the simulator. The result shows that the Compton camera shows its highest performance when it uses 4 layers of scatterer detectors.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.2
• /
• pp.99-109
• /
• 2018

The precision of the vibration-sensors, contact or non-contact types, is usually satisfactory for the practical measurement applications, but a sensor is confined to the measurement of a point or a direction. Although the precision and frequency span of the low-cost camera are inferior to these sensors, it has the merits in the cost and in the capability of simultaneous measurement of a large vibrating area. Furthermore, a camera can measure multi-degrees-of-freedom of a vibrating object simultaneously. In this study, the calibration method and the dynamic characteristics of the low-cost machine vision camera as a sensor are studied with a demonstrating example of the two-dimensional vibration of a cantilever beam. The planar image of the camera shot reveals two rectilinear and one rotational motion. The rectilinear vibration motion of a single point is first measured using a camera and the camera is experimentally calibrated by calculating error referencing the LDV (Laser Doppler Vibrometer) measurement. Then, by measuring the motion of multiple points at once, the rotational vibration motion and the whole vibration motion of the cantilever beam are measured. The whole vibration motion of the cantilever beam is analyzed both in time and frequency domain.

• The Journal of the Korea Contents Association
• /
• v.11 no.4
• /
• pp.11-17
• /
• 2011

This paper aims to realize the information of a subject existing in a still image with objective values. To attain the goal, this research takes the vanishing point that a 2D still image has as the basis and recomposes the still image into a 3D image using a 3D program. Also, in order to set up the axis of the camera necessary to recompose a 3D image, this paper used the lens angle of view that the image has and floor patterns as well. The 3D image completed in this way can measure the size and distance of all subjects in the floor patterns if the size value of a particular reference subject is known, and through this, it can be possible to acquire basic information of a subject that can be either a criminal or a clue in the images of CCTVs or some criminal scene.