• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.11a
• /
• pp.209-212
• /
• 2009

본 논문에서는 MDCT기반의 오디오 특징과 영상 특징을 이용하여 축구 동영상의 하이라이트를 효과적으로 요약하는 방식을 제안한다. 제안하는 방식에서는 입력되는 축구 동영상을 비디오 신호와 오디오 신호로 분리한 후에, 분리된 연속적인 오디오 신호를 압축영역의 MDCT계수를 통해 이벤트 사운드별로 분류하여 오디오 이벤트 후보구간을 추출한다. 입력된 비디오 신호에서는 장면 전환점을 추출하고 추출된 장면 전환점으로부터 페널티 영역을 검출한다. 검출된 오디오 이벤트 후보구간과 검출된 페널티 영역장면을 함께 결합하여 축구 동영상의 이벤트 장면을 검출한다. 검출된 페널티 영역 장면을 통해 검출된 이벤트 구간을 다른 이벤트 구간보다 더 높은 우선순위를 갖는 하이라이트로 선정하여 요약본이 생성된다. 생성된 하이라이트 요약본의 평가는 precision과 recall을 통해 정확도를 평가하였다.

• Korean Journal of Remote Sensing
• /
• v.30 no.6
• /
• pp.769-776
• /
• 2014

It is necessary to detect the feature points existing simultaneously in both images and then find the corresponding relationship between the detected feature points. We propose a new feature detector based on geometric mean of two eigenvalues of gradient matrix which is able to measure the change of pixel intensities. The corner response of the proposed detector is proportional to the geometric mean and also the difference of two eigenvalues in the case of same geometric mean. We analyzed the localization error of the feature detection using aerial image and artificial image with various types of corners. The localization error of the proposed detector was smaller than that of the typical corner detector, Harris detector.

• Journal of the Korea Society of Computer and Information
• /
• v.8 no.2
• /
• pp.37-43
• /
• 2003

The purpose of this thesis is to detect multiple vehicles using sequence image analysis at process that detect forward vehicles and lane from sequential color images. Detection of vehicles candidate area uses shadow characteristic and edge information in one frame. And, method to detect multiple vehicles area analyzes Estimation of Vehicle(EOV) and Accumulated Similarity Function(ASF) of vehicles candidate areas that exist in sequential images and examine possibility to be vehicles. Most researches detected a forward vehicles in road images but this research presented method to detect several vehicles and apply enough in havy traffic. To verify the effects of the proposed method, we capture the road images with notebook and CCD camera for PC and present the results such as processing time, accuracy and vehicles detection in the images.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.449-450
• /
• 2007

오래 전 부터 영상처리와 컴퓨터 비전은 많은 분야에 응용되고 발전 되어 왔다. 그러한 기술 중에 최근 각광 받고 있는 그래프 짓(Graph cut) 알고리즘은 에너지함수를 최소화 하는 가장 강력한 최적화 기법중 하나이다. 그리고 일반적으로 Sobel, Prewitt, Roberts, Canny 에지(edge) 검출기 등은 영상처리에서 영상상의 에지를 검출하기 위해 이미 널리 사용되고 발전되어 온 기술이다. 물체에서의 윤곽만 검출하기 위해서는 우리가 원하지 않는 영상 위의 에지도 검출되기 때문에 예지 검출기만으로는 물체의 윤곽만을 검출하는 것은 불가능하다. 우리는 물체의 윤곽만 검출하기를 원하기 때문에 그래프 컷과 에지 검출기의 알고리즘을 결합하면 이러한 문제를 해결 할 수 있다는 것을 제안한다. 이 논문에서는 그래프 컷 알고리즘과 에지 검출기에 관해 간략하게 기술하고 그 결과를 보일 것이다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.15 no.4
• /
• pp.135-140
• /
• 2014

As the digital image devices are widely used, interests in the software- and the hardware-related image processing become higher and the image processing techniques are applied in various fields such as object recognition, object detection, fingerprint recognition, and etc. For the edge detections Sobel, Prewitt, Laplacian, Roberts and Canny detectors are used and these existing methods can excellently detect the edges of the images without noise. However, in the images corrupted by the impulse noise, these methods are insufficent in noise elimination characteristics, showing unsatisfactory edge detection. Therefore in this paper, in order to obtain excellent edge detection characteristics in the corrupted image by the impulse noise, an detection algorithm is porposed, which uses the central pixel of mask divided by four regions along the axis, calculates the estimated mask according to the representing pixel values in each regions, and detects the final edges by applying the estimates mask and the new directional one.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.6
• /
• pp.97-106
• /
• 2010

In this paper, lane and curvature detection algorithm based on the curve template matching method is proposed. To eliminate the perspective effect of the original image, the input image is transformed to a top view image. From this top view image, its edge image is created. To increase the accuracy of detection, a novel edge detection method, which shows a strength in lane detection, is proposed. In the first step, straight lanes are detected from the edge image, and then the Curve Template Matching(CTM) method is applied to detect the curved lanes and to find their curvatures. Since the proposed CTM method uses only the simple equations, such as line and circle equations, to detect the curved lane, the algorithm is simple. Moreover, we used the detected lane information in the previous frames to detect the current frame's lanes, the detection results become more reliable. The proposed algorithm has been tested in various road conditions (highway, urban street, night time highway, etc.). Experimental results show that the proposed algorithm can process about 70 frames per second with the successful lane detection rate over 95% and curvature detection rate about 90%.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.733-736
• /
• 2000

멀티미디어 데이터베이스에서 장면전환 영역을 검출하는 것은 검색과 색인을 위해서 필수적이다. 동영상에서 장면전환 영역은 단순한 장면전환과 점진적인 장면전환으로 나눌 수 있다. 단순한 장면전환은 다음 장면과 구별이 쉬우나, 점진적인 장면전환은 그 구별이 쉽지 않다. 본 논문에서는 압축된 동영상에서 점진적인 장면전환 영역을 검출하는 효과적인 방법을 제시한다. 제안된 알고리즘은 MPEG-1으로 압축된 동영상에서 DC계수를 추출하고, 부호화된 휘도 블럭의 개수를 추출하여 점진적 장면전환 영역을 검출한다. 제안된 알고리즘의 성능은 장면이 점진적으로 바뀌는 영역을 찾아내는 정확도를 기반으로 분석하였다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.46 no.5
• /
• pp.427-435
• /
• 2018

Many countries are trying to deploy satellite surveillance systems for their national defense, and one of these system uses optical systems to observe the satellites above their territories. The optical satellite surveillance system requires the coordinates of the satellites in an acquired image and expects that those coordinates to be delivered to the tracking system. The proposed method detects the satellite sources in a high-resolution image with fast image processing for the optical surveillance system. To achieve faster detection, the proposed method reduces the size of the original image and approximates the trajectory of a satellite, so image processing methods are only applied to the nearby area of the approximated trajectory in the original image. The proposed method shows the similar detection performance faster than the previous method.

• Journal of Korea Multimedia Society
• /
• v.16 no.2
• /
• pp.169-179
• /
• 2013

Change detection algorithms take two image frames and return the locations of newly introduced objects which cause differences between the images. This paper presents a new change detection method, which classifies intensity changes due to introduced objects, reflected light and shadow from the objects to their neighborhood, and the noise, and exactly localizes the introduced objects. For classification and localization, first we analyze the histogram of the intensity difference between two images, and estimate multiple threshold values. Second we estimate candidate object boundaries using the gradient difference between two images. Using those threshold values and candidate object boundaries, we segment the frame difference image into multiple regions. Finally we classify whether each region belongs to the introduced objects or not using textures in the region. Experiments show that the proposed method exactly localizes the objects in various scenes with different lighting.

• Journal of Korea Multimedia Society
• /
• v.9 no.2
• /
• pp.160-171
• /
• 2006

In this paper, we propose a face detection method using region segmentation to deal with complex images that have various environmental changes such as mixed background and light changes. To reduce the detection error rate due to background elements of the images, we segment the images with the JSEG method. We choose candidate regions of face based on the ratio of skin pixels from the segmented regions. From the candidate regions we detect face regions by using location and color information of eyes and eyebrows. In the experiment, the proposed method works well with the images that have several faces and different face size as well as mixed background and light changes.