• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.4
• /
• pp.201-208
• /
• 2015

This paper proposes a method for detecting the direction indicator shown in the road surface efficiently from the black box system installed on the vehicle. In the proposed method, the direction indicators are detected by inverse perspective mapping(IPM) and bag of visual features(BOF)-based NN classifier. In order to apply the proposed method to real-time environments, the candidated regions of direction indicator in an image only performs IPM, and BOF-based NN is used for the classification of feature information from direction indicators. The results of applying the proposed method to the road surface direction indicators detection and recognition, the detection accuracy was presented at least about 89%, and the method presents a relatively high detection rate in the various road conditions. Thus it can be seen that the proposed method is applied to safe driving support systems available.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.672-674
• /
• 2011

Edge contains important information to analyze the characteristics of the images. Edge detection has been a lot utilized in areas such as computer vision and image processing etc.. And sobel, prewitt, roberts are representative methods among the initially used methods. Although these conventional methods easily detect large change points of slope of brightness, optional directional edge detection abilities of conventional edge detection are not efficient. Therefore, in this paper, to complement the shortcomings of existing edge detection method, we proposed adaptive edge detection method considering direction information. through simulatioopn, we verify abilities of our method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.5
• /
• pp.665-671
• /
• 2010

This paper propose the DDEGST(divergent-direction-emphasis generalized symmetry transform) which emphasis the symmetry of divergent intensity orientation for effective target extraction in FLIR(forward looking infra-red) images. In the proposed method, we use the exponential function instead of cosine function as a phase weight function in the generalized symmetry transform for effective target extraction in FLIR images which contain a target with higher intensity than a background intensity. To evaluate the performance of the proposed method, we compare the proposed mehtod with conventional GST method in experiments. We prove that the proposed method have better performance in IR images.

• Journal of Internet Computing and Services
• /
• v.14 no.6
• /
• pp.117-124
• /
• 2013

In this paper, we present a new method which efficiently estimates a face direction from a sequences of input video images in real time fashion. For this work, the proposed method performs detecting the facial region and major facial features such as both eyes, nose and mouth by using the Haar-like feature, which is relatively not sensitive against light variation, from the detected facial area. Then, it becomes able to track the feature points from every frame using optical flow in real time fashion, and determine the direction of the face based on the feature points tracked. Further, in order to prevent the erroneously recognizing the false positions of the facial features when if the coordinates of the features are lost during the tracking by using optical flow, the proposed method determines the validity of locations of the facial features using the template matching of detected facial features in real time. Depending on the correlation rate of re-considering the detection of the features by the template matching, the face direction estimation process is divided into detecting the facial features again or tracking features while determining the direction of the face. The template matching initially saves the location information of 4 facial features such as the left and right eye, the end of nose and mouse in facial feature detection phase and reevaluated these information when the similarity measure between the stored information and the traced facial information by optical flow is exceed a certain level of threshold by detecting the new facial features from the input image. The proposed approach automatically combines the phase of detecting facial features and the phase of tracking features reciprocally and enables to estimate face pose stably in a real-time fashion. From the experiment, we can prove that the proposed method efficiently estimates face direction.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.20 no.1
• /
• pp.132-137
• /
• 2006

The second part of paper related rotor failure is to evaluate that the axial magnetic flux measurement could be used as a tool of the condition monitoring system for the induction motor and to develope the diagnostic algorithm for the various fault in the electric motors. The magnetic leakage flux signal is captured by the flux coil located at the end of motor without the disturbance of the operation. And the signal is analyzed both time and frequency domain to detect the failure of the motor. Specific signature can be described in tin and frequency domain for each fault of the motor. The experimental test found that the rotor failures - broken rotor bar, broken end ing and rotor eccentricity, could be detected from the spectrum with high resolution. The method of detecting the rotor fault was found by analysing the specific frequency and the sideband of the rotor bar pass frequency from axial leakage flux spectrum. In addition the optimal flux coil and measuring equipment for the axial leakage flux measurement was verified and the diagnostic method for the detection of the rotor related failure was developed.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.7-8
• /
• 2015

본 논문에서는 선박의 기적소리 방향 검출을 위한 시스템을 개발한다. 제안하는 시스템은 4개의 마이크로폰으로부터 기적 소리를 입력받아 원하는 주파수 대역의 신호만 통과하도록 디지털 필터링된다. 필터링된 신호로부터 8 방향의 기적소리 방향 탐지가 가능한 알고리즘을 제안한다. 또한, DSP를 이용하여 제안된 시스템의 프로토타입을 구현하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.440-445
• /
• 2007

본 논문에서는, 폐 종류 음영검출에 대해서 다중해상도 필터를 에너지 차분 영상에 적용하여 기존 방법과의 비교평가 및 폐 종류 음영검출 자체에 관하여 그 검출성능에 영향을 주는 요인을 선택해서 분석을 하였다. 다시말해서, 폐 종류 음영 검출자체에 관해서 복수의 분석인자를 선택해서 복수의 관점에서 성능을 분석하였다. 즉, 영상 인자로서 보통 X선 영상 및 에너지 차분영상을, 검출필터 인자로서 라플라시안-가우시안 필터, 최소방향 차분필터 및 본 연구에서 제안하는 다중해상도 필터를 선택해서 분석을 하였다. 그 결과, 폐 종류 음영검출에 있어서 에너지 차분 영상의 유효성, 최소방향 차분필터의 보통 X선 영상에서의 효과 및 다중해상도 필터의 에너지 차분 영상에 있어서의 유효성을 식견으로서 터득하게 되었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.361-363
• /
• 2001

반도체 패키지의 마킹검사(marking inspection)를 위해서는 입력 영상으로부터 검사할 패키지의 정확만 위치 검출과 패키지 윗면에 나타난 제작사 로고, 문자, Pin1 딤플의 추출이 필수적이다. 본 연구는 마킹검사를 위한 선행 연구로 마킹검사를 수행할 때, 검사할 IC 패키지의 위치와 방향을 정확하게 검출하는 것을 목적으로 하고 있다. IC 패키지의 외곽을 구성하는 리드의 명도 값은 트레이의 명도 값과 큰 차이를 나타낸다. 그러나 IC 패키지의 방향을 나타내는 Pin1 딤플은 배경과 동일한 색상으로 다만 약간 오목하게 들어가서 명도 값의 차이가 미세하다. 이러한 두 가지 상이한 특징을 효과적으로 처리하기 위하여 적응적 다중 이진화 방법을 제시하였다. 76개의 명도 영상에 대한 실험 결과 제안된 이진화 방법은 매우 효과적이었으며, 이진화된 영상으로부터 IC 패키지의 정확한 위치 검출과 방향 확인이 가능하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.289-292
• /
• 2002

동영상 검색 시스템은 사용자가 전체 동영상 정보를 한눈에 파악할 수 있어야 한다. 필요한 경우 원하는 지점부터 직접 재생할 수 있도록 해야 한다. 이에 대한 많은 연구가 수행되고 있다. 그러나 데이터를 처리하는데 시간이 오래 걸리는 등의 몇가지 문제점이 있다. 따라서 본 논문은 내용기반 색인에 기초가 될 동영상의 장면전환점 검출에 관한 효과적인 방법을 제안하였다. 제안된 방법은 프레임의 수평방향, 수직방향 또는 대각선 방향으로 나누어 일정한 픽셀 값을 추출하여 정지영상으로 변환하였다. 각각의 프레임에서 추출한 픽셀의 칼라값을 저장하고 MSE(Mean Square Error)를 이용하여 일정한 임계값에 도달하지 못한 프레임을 장면전환점으로 검출하였다. 검출된 장면전환점을 이용하여 변화된 프레임의 장면전환을 검색하는 시스템을 구현하였다.

• Journal of the Korean Magnetics Society
• /
• v.23 no.1
• /
• pp.18-25
• /
• 2013

MFL PIG (Magnetic Flux Leakage Pipeline Inspection Gauge) is called the system which detects the defect for underground pipelines by using magnetic flux leakage method in nondestructive testing. This method is very suitable for testing pipelines because pipeline has high magnetic permeability. MFL PIG generates the magnetic fields to the pipe axially oriented, and detect the signal of leakage flux by using hall sensor. However, MFL PIG is hard to detect the axially oriented crack with small size because the magnetic flux leakage is not enough to be occurred. To detect the small size and axially oriented crack, the circumferential MFL (CMFL) PIG is being proposed and it can maximize the leakage flux for the axial crack by performing magnetic fields circumferentially on the pipe. In this paper, CMFL PIG is applied to detect the axially oriented crack with small size and the analysis for the distribution and the amplitude of the leakage flux signal is performed by using three dimensional finite element method. From sensing signals, the method how to determine the shape of axially oriented cracks is proposed and verified with experiment.