• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.3
• /
• pp.38-50
• /
• 2023

Recent advances in artificial intelligence (AI) technology have enabled the integration of AI technology into image sensors, such as Closed-Circuit Television (CCTV), to detect specific traffic incidents. However, most incident detection methods have been carried out using fixed equipment. Therefore, there have been limitations to incident detection for all roadways. Nevertheless, the development of mobile image collection and analysis technology, such as image sensors and edge-computing, is spreading. The purpose of this study is to estimate the reducing effect of the incident detection time according to the introduction level of mobile image collection and analysis equipment (or connected vehicles). To carry out this purpose, we utilized data on the number of incidents collected by the Suwon branch of the Gyeongbu expressway in 2021. The analysis results showed that if the market penetration rate (MPR) of connected vehicles is 4% or higher for two-lane expressway and 3% or higher for three-lane expressways, the incident detection time was less than one minute. Furthermore, if the MPR is 0.4% or higher for two-lane expressways and 0.2% or higher for three-lane expressways, the incident detection time decreased compared to the average incident detection time announced by the Korea Expressway Corporation for both two-lane and three-lane expressways.

• Journal of Korea Multimedia Society
• /
• v.8 no.11
• /
• pp.1496-1509
• /
• 2005

In this paper, an adaptive license plate recognition system which detects and recognizes license plate at real-time by using projected plane convolution and Decision Tree Classifier is proposed. And it was tested in circumstances which presence of complex background. Generally, in expressway tollgate or gateway of parking lots, it is very difficult to detect and segment license plate because of size, entry angle and noisy problem of vehicles due to CCD camera and road environment. In the proposed algorithm, we suggested to extract license plate candidate region after going through image acquisition process with inputted real-time image, and then to compensate license size as well as gradient of vehicle with change of vehicle entry position. The proposed algorithm can exactly detect license plate using accumulated edge, projected convolution and chain code labeling method. And it also segments letter of license plate using adaptive binary method. And then, it recognizes license plate letter by applying hybrid pattern vector method. Experimental results show that the proposed algorithm can recognize the front and rear direction license plate at real-time in the presence of complex background environments. Accordingly license plate detection rate displayed $98.8\%$ and $96.5\%$ successive rate respectively. And also, from the segmented letters, it shows $97.3\%$ and $96\%$ successive recognition rate respectively.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.5
• /
• pp.74-84
• /
• 2017

Since a soldier manages a hand-held landmine detector by hands, it is necessary to develop a system that can detect the target quickly and accurately. However, the hand-held landmine detector used in Korea has a problem that it can only detect the metal mines. Therefore, it is important to solve the problem and to develop a hand-held landmine detection system suitable for the Korean environment. In this paper, we propose a hand-held landmine detection system suitable for the Korean environment using ground penetrating radar. The proposed system uses depth compensation, matched filtering, and frequency shifting filtering for preprocessing. Then, in the detection step, the system detects the target using the edge ratio. In order to evaluate the proposed system, we buried landmines in sandy loam which is most of the soil in Korea and obtained a set of ground penetrating radar data by using a hand-held landmine detector. By using the obtained data, we carried out some experiments on the size and position of the patch and the shifting frequency to find the optimal parameter values and measured the detection performance using the optimized values. Experimental results show that the proposed preprocessing algorithms are suitable for detecting all landmines at low false alarm rate and the performance of the proposed system is superior to that of previous works.

• Journal of KIISE:Software and Applications
• /
• v.27 no.7
• /
• pp.731-741
• /
• 2000

This paper proposes a method to detect a facial region and extract facial features which is crucial for visual recognition of human faces. In this paper, we extract the MER(Minimum Enclosing Rectangle) of a face and facial components using projection analysis on both edge image and binary image. We use an active contour model(snakes) for extraction of the contours of eye, mouth, eyebrow, and face in order to reflect the individual differences of facial shapes and converge quickly. The determination of initial contour is very important for the performance of snakes. Particularly, we detect Minimum Enclosing Rectangle(MER) of facial components and then determine initial contours using general shape of facial components within the boundary of the obtained MER. We obtained experimental results to show that MER extraction of the eye, mouth, and face was performed successfully. But in the case of images with bright eyebrow, MER extraction of eyebrow was performed poorly. We obtained good contour extraction with the individual differences of facial shapes. Particularly, in the eye contour extraction, we combined edges by first order derivative operator and zero crossings by second order derivative operator in designing energy function of snakes, and we achieved good eye contours. For the face contour extraction, we used both edges and grey level intensity of pixels in designing of energy function. Good face contours were extracted as well.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.61-68
• /
• 2018

In this paper, we propose a method of character detection by analyzing image enhancement and character type to detect characters in natural images that can be acquired in everyday life. The proposed method emphasizes the boundaries of the object part using the unsharp mask in order to improve the detection rate of the area to be recognized as a character in a natural image. By using the boundary of the enhanced object, the character candidate region of the image is detected using Maximal Stable Extermal Regions (MSER). In order to detect the region to be judged as a real character in the detected character candidate region, the shape of each region is analyzed and the non-character region other than the region having the character characteristic is removed to increase the detection rate of the actual character region. In order to compare the objective test of this paper, we compare the detection rate and the accuracy of the character region with the existing methods. Experimental results show that the proposed method improves the detection rate and accuracy of the character region over the existing character detection method.

• Journal of Astronomy and Space Sciences
• /
• v.38 no.1
• /
• pp.31-38
• /
• 2021

In this paper, we present observations of the Space Radiation Detectors (SRDs) onboard the Next Generation Small Satellite-1 (NEXTSat-1) satellite. The SRDs, which are a part of the Instruments for the study of Stable/Storm-time Space (ISSS), consist of the Medium-Energy Particle Detector (MEPD) and the High-Energy Particle Detector (HEPD). The MEPD can detect electrons, ions, and neutrals with energies ranging from 20 to 400 keV, and the HEPD can detect electrons over an energy range from 0.35 to 2 MeV. In this paper, we report an event where particle flux enhancements due to substorm injections are clearly identified in the MEPD A observations at energies of tens of keV. Additionally, we report a specific example observation of the electron distributions over a wide energy range in which we identify electron spatial distributions with energies of tens to hundreds of keV from the MEPD and with energy ranging up to a few MeV from the HEPD in the slot region and outer radiation belts. In addition, for an ~1.5-year period, we confirm that the HEPD successfully observed the well-known outer radiation belt electron flux distributions and their variations in time and L shell in a way consistent with the geomagnetic disturbance levels. Last, we find that the inner edge of the outer radiation belt is mostly coincident with the plasmapause locations in L, somewhat more consistent at subrelativistic energies than at relativistic energies. Based on these example events, we conclude that the SRD observations are of reliable quality, so they are useful for understanding the dynamics of the inner magnetosphere, including substorms and radiation belt variations.

• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.671-677
• /
• 2023

When a scintillator block is constructed using fine scintillator pixels, the scintillator block located at the edge of the scintillator block results in overlapping images. To solve this problem, a light guide was inserted between the scintillator block and the photosensor, and images of all scintillation pixels were separated and acquired. However, loss of light may occur through the light guide, which eventually affects the quality of the image due to a decrease in energy resolution. Therefore, in this study, a detector was designed that can separate scintilltion pixels better by using a reflector on the side of the light guide and can secre excellent energy resolution by minimizing light loss. For comparative evaluation with previous studies, flood images were obtained through DETECT2000 capable of light simulation, and the degree of separation and light collection rate were evaluated. When a reflector was used on the side of the light guide, all materials showed excellent separation regardless of the material of the light guide, which showed better separation results than previous studies. In addition, the light collection rate was more that five times better when the reflector was applied than when it wa not. If this detector is applied to a small animal positron emission tomography, it will be possilbe to secre excellent image quality through excellent spatial resolution and energy resolution.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.5
• /
• pp.213-224
• /
• 2009

This paper presents a new algorithm for estimating a driver's physical condition using real-time vision system and performs experimentation for real facial image data. The system relies on a face recognition to robustly track the center points and sizes of person's two pupils, and two side edge points of the mouth. The face recognition constitutes the color statistics by YUV color space together with geometrical model of a typical face. The system can classify the rotation in all viewing directions, to detect eye/mouth occlusion, eye blinking and eye closure, and to recover the three dimensional gaze of the eyes. These are utilized to determine the carelessness and drowsiness of the driver. Finally, experimental results have demonstrated the validity and the applicability of the proposed method for the estimation of a driver's physical condition.

• Journal of Digital Convergence
• /
• v.11 no.2
• /
• pp.215-220
• /
• 2013

They are well-known geometric properties of a circle that the perpendicular bisector of a chord passes through the center of a circle, and the intersection of the perpendicular bisectors of any two chords is its center. This paper is related to a fast pupil detection method capable of detecting the center and the radius of a pupil using these geometric properties at high speed when detecting the pupil region for iris segmentation. The proposed method is characterized as rapidly detecting the center and the radius of the pupil, extracting the candidate points of the circle in human eye images using morphological operations, and finding two chords using four points on the circular edge, and taking the intersection of the perpendicular bisectors of these two chords for its center. The proposed method can not only detect the center and the radius of a pupil rapidly but also find partially occluded pupils in human eye images.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.1
• /
• pp.126-136
• /
• 2014

In the Advanced Driver Assistance Systems (ADAS) of smart vehicle and Intelligent Transportation System (ITS) for to detect the boundary of lane is being studied a lot of Hough Transform. This method detects correctly recognition the lane. But recognition rate can fall due to detecting straight lines outside of the lane. In order to solve this problems, this paper proposed an algorithm to recognize the lane boundaries and the accumulator cells in Hough space. Based on proposed algorithm, we develop application for Android was developed by H/W verification. Users of smart phone devices could use lane detection and lane departure warning systems for driver's safety whenever and wherever. Software verification using the OpenCV showed efficiency recognition correct rate of 93.8% and hardware real-time verification for an application development in the Android phone showed recognition correct rate of 70%.