• 한국컴퓨터정보학회논문지
• /
• 제16권8호
• /
• pp.57-66
• /
• 2011

본 논문에서는 단일 입력 영상에서 특징을 추출하여 실시간으로 에지 대칭과 기울기의 방향성 특징을 이용하여 효과적으로 사람을 검출하는 알고리즘을 제안한다. 제안된 알고리즘은 전처리, 사람 후보 영역 분할, 후보 영역 검증인 3단계로 구성되었다. 여기서 전처리 단계는 주변 조도 환경과 밝기에 강인하고, 사람의 특징인 모양 특징 크기, 사람의 조건을 고려한 사람의 특성을 가진 윤곽선을 검출한다. 그리고 사람 후보 영역 분할 단계는 검출된 윤곽선에서 사람의 에지 대칭성과 크기를 가지고 영역을 분리하고, 에이타부스트 알고리즘을 적용하여 1차 후보 영역을 분할한다. 마지막으로 후보 영역 검증 단계는 분할된 국소 영역에 대한 기울기의 특징 벡터 및 분류기를 이용하여 후보 영역을 검증하여 오검출의 성능을 우수하게 한다. 제안된 알고리즘을 적용하여 모의실험을 한 결과, 제안된 알고리즘은 단일 알고리즘을 적용한 기존 알고리즘 보다 처리 속도가 약 1.7배 정도 개선되었으며, FNR(False Negative Rate)은 3% 정도 우수함을 확인하였다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2016년도 하계학술대회
• /
• pp.306-308
• /
• 2016

신호등 검출은 지능형 교통 시스템에서 매우 중요하며 최근 신호등 검출 관련한 연구가 활발히 진행 중이다. 하지만 기존의 신호등검출 알고리듬의 문제점은 조명의 변화에 민감하다는 문제점이 있다. 이러한 문제점을 해결하기 위하여 본 논문에서는 다음과 같은 신호등 검출 알고리듬을 제안한다. 먼저 제안하는 색상지도와 HSV(Hue-Saturation-Value)를 이용하여 신호등의 후보를 검출한다. 검출한 신호등의 후보로부터 HOG(Histogram of Oriented Gradient) 서술자를 이용하여 특징을 추출한 다음 최종적으로 선형 SVM(Support Vector Machine)을 이용하여 신호등을 검출하는 알고리듬을 제안한다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2008년도 제39차 동계학술발표논문집 16권2호
• /
• pp.207-210
• /
• 2009

Edge detection is an important process in low level image processing. But many proposed methods for edge detection are not very robust to the image noise and are not flexible for different images. To solve the both problems, an algorithm is proposed which eliminate the noise by mean shift algorithm in advance, and then adaptively determine the double thresholds based on gradient histogram and minimum interclass variance, With this algorithm, it can fade out almost all the sensitive noise and calculate the both thresholds for different images without necessity to setup any parameter artificially, and choose edge pixels by fuzzy algorithm.

• 전기학회논문지P
• /
• 제64권3호
• /
• pp.193-198
• /
• 2015

A large number of vision applications rely on matching keypoints across images. Pedestrian detection is under constant pressure to increase both its quality and speed. Such progress allows for new application. A higher speed enables its inclusion into large systems with extensive subsequent processing, and its deployment in computationally constrained scenarios. In this paper, we focus on improving the speed of pedestrian detection using HOG(histogram of oriented gradient) and multi frame operation which is robust to illumination changes in cluttering images. The result of our simulation indicates that the detection rate and speed of the proposed method is much faster than that of conventional HOG and differential images.

• 전기학회논문지P
• /
• 제64권3호
• /
• pp.187-192
• /
• 2015

Detecting human in images is a challenging task owing to their variable appearance and the wide range of poses the they can adopt. The first need is a robust feature set that allows the human form to be discriminated cleanly, even in cluttered background under difficult illumination. A large number of vision application rely on matching keypoints across images. These days, the deployment of vision algorithms on smart phones and embedded device with low memory and computation complexity has even upped the ante: the goal is to make descriptors faster compute, more compact while remaining robust scale, rotation and noise. In this paper we focus on improving the speed of pedestrian(walking person) detection using Histogram of Oriented Gradient(HOG) descriptors provide excellent performance and tracking using kalman filter.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1994년도 추계학술대회
• /
• pp.9-13
• /
• 1994

The Heat Anisotropic Diffusion Method has shown very effective for the contour detection of 2-D echocardiogram. To implement this algorithm, we have to choose the parameter C, K, and the threshold level. The choice of C and K are not very sensitive for the good edge detection of the echocardiogram, however the choice of the threshold level is very critical. Until now the threshold level is chosen by the trial and error method. In this paper, we present an automatic threshold decision method from the histogram of the gradient of boundary-like pixels.

• 한국멀티미디어학회논문지
• /
• 제18권10호
• /
• pp.1164-1171
• /
• 2015

The edge preserving method is important for image storage and geometric transformation. In this paper, we propose a new edge preserving method using HOG-Guide filter for image segmentation. In our approach, we extract edge information using gradient histogram to set HOG guide line. Then, we use HOG guide line to smooth image. With two to four iterations of smoothing operations, we finally obtain desirable edge preserved image. Our experimental results showed good performances showing that our proposed method is better than other methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.838-841
• /
• 2005

DNA Chip is able to show DNA-Data that includes diseases of sample to User by using complementary characters of DNA. So this paper studied Neural Network algorithm for Image data processing of DNA-chip. DNA chip outputs image data of colors and intensities of lights when some sample DNA is putted on DNA-chip, and we can classify pattern of these image data on user pc environment through artificial neural network and some of image processing algorithms. Ultimate aim is developing of pattern classifying algorithm, simulating this algorithm and so getting information of one's diseases through applying this algorithm. Namely, this paper study artificial neural network algorithm for classifying pattern of image data that is obtained from DNA-chip. And, by using histogram, gradient edge, ANN and learning algorithm, we can analyze and classifying pattern of this DNA-chip image data. so we are able to monitor, and simulating this algorithm.

• 정보학연구
• /
• 제12권4호
• /
• pp.1-10
• /
• 2009

The robustness of communication service should be guaranteed to validate its security of the whole service not just high performance. One kind of practical test-beds is the chinese communication service based on SIM Card and GSM. In paper, we try to experiment the possibility of SIM cards clone in various mobile communications using 2G in china, and hence discovered the security vulnerabilities such as the incoming outgoing, SMS service and additional services on the mobile phones using clone SIM cards. The experiments show that chinese communication service should be prepared the Fraud Management System against the cloning SIM card. and furthermore, regulations related to the communication service should be tuned the realistic security environments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• pp.3534-3549
• /
• 2020

The traditional method of smoke image recognition has low accuracy. For this reason, we proposed an algorithm based on the good group of IMFOA which is GMFOA to optimize the parameters of SVM. Firstly, we divide the motion region by combining the three-frame difference algorithm and the ViBe algorithm. Then, we divide it into several parts and extract the histogram of oriented gradient and volume local binary patterns of each part. Finally, we use the GMFOA to optimize the parameters of SVM and multiple kernel learning algorithms to Classify smoke images. The experimental results show that the classification ability of our method is better than other methods, and it can better adapt to the complex environmental conditions.