• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.172-174
• /
• 2009

This paper describes an implementation method for the 'People Counting System' which detects and tracks moving people using a fixed single camera. This system proposes the method of improving performances by compensating weakness of existing algorithm. For increasing effect of detection, this system uses Single Gaussian Background Modeling which is more robust at noise and has adaptiveness. It minimizes unnecessarily detected area that is a limitation of the detecting method by using the background differences. And this system prevents additional detecting problems by removing shadow. Also, This system solves the problems of segmentation and union of people by using a new method. This method can work appropriately, if the angle of camera would not strictly vertical or the direction of shadow were lopsided. Also, by using integration System, it can solve a number of special cases as many as possible. For example, if the system fails to tracking, it will detect the object again and will make it possible to count moving people.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1337-1342
• /
• 2019

The Automatic Korean license plate recognition (AKLPR) is used in many fields. For many applications, high recognition rate and fast processing speed of ALPR are important. Recent advances in deep learning have improved the accuracy and speed of object detection and recognition, and CNN (Convolutional Neural Network) has been applied to ALPR. The ALPR is divided into the stage of detecting the LP region and the stage of detecting and recognizing the character in the LP region, and each step is implemented with separate CNN. In this paper, we propose a single stage CNN architecture to recognize license plate characters at high speed while keeping high recognition rate.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.4
• /
• pp.325-334
• /
• 2001

It is shown that the multiscale prewhitening matched filter for detecting Gaussian objects in Markov noise can be implemented by the undecimated wavelet transform with a biorthogonal spline wavelet. If the object to be detected is Gaussian shaped and its scale coincides with one of those computed by the wavelet transform, and if the background noise is truly Markov, then optimum detection is realized by thresholding the appropriate details image. Our detection algorithm is applied to the digitized mammograms for detecting microcalcifications. However, microcalcifications are not exactly Gaussian shaped and its background noise may not be Markov. In order to campensate for these discrepancy, Hotelling observer is employed, which is applied to feature vectors comprised of 3-octave wavelet coefficients.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.965-967
• /
• 2003

Fuzzy Controller is a system that displays a person's thoughts using membership function and IF-THEN rules. With the help of specialists' knowledge, rule bases can be explained in easy language. Furthermore Fuzzy Controller has strong resistance against turbulence. Its performance is especially prominent when targets cannot be measured in mathematic methods because the fuzzy controller can measure the output using only the relations between the input and output. With the increasing influence of multimedia on our daily lives, vision plays bigger role both in industries and personal lives. Like wise vision is being used in many areas such as detecting and identifying objects. It is difficult to detect and control targets because there is a delay in the calculating when using vision in detecting and controlling objects in large quantity. In this paper we showed how to use fuzzy controller in minimizing the calculation process, controlling target objects and moving view window instead of applying input variation through vision. Ball beam, which has strong nonlinear, was used as the target object and DSP320C6711 IDK by TI(Texas Instruments) company was for the benefit of speedy calculation and vision data operation.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.18 no.1
• /
• pp.47-56
• /
• 2008

This paper presents a detecting technique for the improvement in quality by appling the various vibrational characteristics theory. The object of this study is to objectively point out faulty gear by developing the program which can be used to analyze and predict the vibrational characteristics caused by gear wear, deformation and nick of auto-transmission. The fault detection methods by vibrational signal analysis of gear have been progressed in the various fields of industry. These methods have the advantage of being easy to attach the accelerometer without discontinuance of the structure. But not all the methods are efficient for finding early faults. So in the thesis, we completed development of the inspection system of vibration by appling the most efficient detecting methods and verified the system's reliability through experiments.

• Publications of The Korean Astronomical Society
• /
• v.38 no.2
• /
• pp.91-98
• /
• 2023

We present a novel method that can enhance the detection success rate of interstellar objects. Interstellar objects are objects that are not gravitationally bound to our solar system and thus are believed to have originated from other planetary systems. Since the finding of two interstellar objects, 1l/'Oumuamua in 2017 and 2l/Borisov in 2019, much attention has been paid to finding new interstellar objects. In this paper, we propose the use of Heliospheric Imagers (HIs) for the survey of interstellar objects. In particular, we show HI data taken from Solar TErrestrial RElation Observatory/Sun Earth Connection Coronal and Heliospheric Investigation and demonstrate their ability to detect 'Oumuamua-like interstellar objects. HIs are designed to monitor and study space weather by observing the solar wind traveling through interplanetary space. HIs provide the day-side observations and thus it can dramatically enlarge the observable sky range when combined with the traditional night-side observations. In this paper, we first review previous methods for detecting interstellar objects and demonstrate that HIs can be used for the survey of interstellar objects.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.1
• /
• pp.45-53
• /
• 2020

Conventional Convolutional Neural Network(CNN) algorithms have limitations in detecting small objects in large image. In this paper, we propose an improved model which is based on Region Of Interest(ROI) selection and image dividing technique. We prepared YOLOv3 / Faster R-CNN algorithms which are transfer-learned by airfield and aircraft datasets. Also we prepared large images for testing. In order to verify our model, we selected airfield area from large image as ROI first and divided it in two power n orders. Then we compared the aircraft detection rates by number of divisions. We could get the best size of divided image pieces for efficient small object detection derived from the comparison of aircraft detection rates. As a result, we could verify that the improved CNN algorithm can detect small object in large images.

• Journal of Advanced Navigation Technology
• /
• v.24 no.3
• /
• pp.192-197
• /
• 2020

Recently, the technologies related to autonomous drive has studying the goal for safe operation and prevent accidents of vehicles. There is radar and camera technologies has used to detect obstacles in these autonomous vehicle research. Now a day, the method for using LiDAR sensor has considering to detect nearby objects and accurately measure the separation distance in the autonomous navigation. It is calculates the distance by recognizing the time differences between the reflected beams and it allows precise distance measurements. But it also has the disadvantage that the recognition rate of object in the atmospheric environment can be reduced. In this paper, point cloud data by triangular functions and Line Regression model are used to implement measurement algorithm, that has improved detecting objects in real time and reduce the error of measuring separation distances based on improved reliability of raw data from LiDAR sensor. It has verified that the range of object detection errors can be improved by using the Python imaging library.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.4
• /
• pp.851-859
• /
• 2011

In this paper, we propose the method that automatically extracts the silhouette and the joints of consecutive input image, and track joints to trace object for interaction between human and computer. Also the proposed method presents the action of human being to map human body using joints. To implement the algorithm, we model human body using 14 joints to refer to body size. The proposed method converts RGB color image acquired through a single camera to hue, saturation, value images and extracts body's silhouette using the difference between the background and input. Then we automatically extracts joints using the corner points of the extracted silhouette and the data of body's model. The motion of object is tracted by applying block-matching method to areas around joints among all image and the human's motion is mapped using positions of joints. The proposed method is applied to the test videos and the result shows that the proposed method automatically extracts joints and effectively maps human body by the detected joints. Also the human's action is aptly expressed to reflect locations of the joints

• The Journal of the Korea Contents Association
• /
• v.7 no.2
• /
• pp.63-72
• /
• 2007

The traffic sign on the road should be easy to distinguishable even from far, and should be recognized in a short time. As traffic sign is a very important object which provides important information for the drivers to enhance safety, it has to attract human's attention among any other objects on the road. This paper proposes a new method of detecting the area of traffic sign, which uses attention module on the assumption that we attention our gaze on the traffic sign at first among other objects when we drive a car. In this paper, we analyze the previous studies of psycophysical and physiological results to get what kind of features are used in the process of human's object recognition, especially color processing, and with these results we detected the area of traffic sign. Various kinds of traffic sign images were tested, and the results showed good quality(average 97.8% success).