• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.421-422
• /
• 2006

Using the still image through the camera reports which the moving object tracking system. Moving object direction detected to compare the two difference images. And base block set at moving object. Matching area set current difference image. The edge image of prior frame and current frame implement the moving object tracking system to block matching.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(4)
• /
• pp.54-57
• /
• 2000

In this paper, we propose a new interpolation method by using the motion between two moving image frames. In the proposed method, the movement is detected by using neighborhood pixels of target pixel in the past frame and the present frame. Then, H-shaped pseudomedian filter (below HPMED) is used for the still part of the image and Delta-shaped interpolation filter (below $\Delta$-shaped) for used in the moving part of the image. We detect the movement by comparing the differences between pixels in 4${\times}$5 window of the past frame and the present frame; the difference has a critical value. We simultaneously accomplish checking PSNR(peak signal noise ratio) and subjective assessment that is placed the focus on edge characteristic for assessment of result in computer simulation. The results show that the proposed adaptive method is better than the conventional methods.

• 한국멀티미디어학회논문지
• /
• 제17권4호
• /
• pp.420-432
• /
• 2014

In detection of moving objects from video sequences, an essential process for intelligent visual surveillance, the cast shadows accompanying moving objects are different from background so that they may be easily extracted as foreground object blobs, which causes errors in localization, segmentation, tracking and classification of objects. Most of the previous research results about moving cast shadow detection and removal usually utilize color information about objects and scenes. In this paper, we proposes a novel cast shadow removal method of moving objects in gray level video data for visual surveillance application. The proposed method utilizes observations about edge patterns in the shadow region in the current frame and the corresponding region in the background scene, and applies Laplacian edge detector to the blob regions in the current frame and the corresponding regions in the background scene. Then, the product of the outcomes of application determines moving object blob pixels from the blob pixels in the foreground mask. The minimal rectangle regions containing all blob pixles classified as moving object pixels are extracted. The proposed method is simple but turns out practically very effective for Adative Gaussian Mixture Model-based object detection of intelligent visual surveillance applications, which is verified through experiments.

• 융합신호처리학회논문지
• /
• 제19권4호
• /
• pp.192-198
• /
• 2018

최근 드론의 활용이 여러 방면에서 급격하게 증가하고 있다. 드론은 원격으로 표적을 효율적으로 촬영할 수 있어 감시와 보안 시스템에 유용하다. 본 논문은 드론을 이용한 움직이는 차량을 검출하는 세 가지 방법을 연구한다. 배경 영상, 선행 프레임, 또는 이동 평균 프레임과 현재 프레임과의 감산 기법을 이용한 표적 검출을 비교한다. 프레임 감산 후 형태학적 필터링을 적용하여 검출률을 높이고 오보율을 감소시킨다. 또한 표적의 크기를 알고 있다는 가정 하에 영역크기 비교를 통하여 오경보 영역을 제거한다. 실험에서는 움직이는 3대의 자동차를 드론으로 촬영하여 앞서 제시한 방법에 따라 표적을 검출하고 각각 검출율과 오보율을 구하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2106-2111
• /
• 2003

In this paper we discuss an algorithm for a real time transmission of moving color images on the TCP/IP network using wavelet transform and neural network. The image frames received from the camera are two-level wavelet-trans formed in the server, and are transmitted to the client on the network. Then, the client performs the inverse wavelet-transform using only the received pieces of each image frame within the prescribed time limit to display the moving images. When the TCP/IP network is busy, only a fraction of each image frame will be delivered. When the line is free, the whole frame of each image will be transferred to the client. The receiver warns the sender of the condition of traffic congestion in the network by sending a special short frame for this specific purpose. The sender can respond to this information of warning by simply reducing the data rate which is adjusted by a back-propagation neural network. In this way we can send a stream of moving images adaptively adjusting to the network traffic condition.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 A
• /
• pp.203-206
• /
• 2003

In this paper we discuss an algorithm for a real time transmission of moving color images on the TCP/IP network using wavelet transform and neural network. The image frames received from the camera are two-level wavelet-transformed in the server, and are transmitted to the client on the network. Then, the client performs the inverse wavelet-fransform using only the received pieces of each image frame within the prescribed time limit to display the moving images. When the TCP/IP network is busy, only a fraction of each image frame will be delivered. When the line is free, the whole frame of each image will be transferred to the client. The receiver warns the sender of the condition of traffic congestion in the network by sending a special short frame for this specific purpose. The sender can respond to this condition of warning by simply reducing the data rate which is adjusted by a back-propagation neural network. In this way we can send a stream of moving images adaptively adjusting to the network traffic condition.

• 한국콘텐츠학회논문지
• /
• 제11권4호
• /
• pp.51-56
• /
• 2011

본 논문은 명암 변화가 심한 비디오 시퀀스에 대해 효율적인 동영상 압축기법을 제안한다. 제안한 알고리즘에서는 화면간의 명암 변화 변수들을 추정하고 지역적인 움직임 보상을 수행한다. 밝기 보상이 필요한 화면을 검출하기 위하여 연속되는 두 프레임간의 히스토그램의 크로스 엔트로피를 계산하여 프레임 분류를 하고 명암 변화가 심한 화면에 대해서만 밝기 보상을 수행하여 명암 변화가 심하지 않은 경우에 발생할 수 있는 불필요한 계산량을 줄였다. 명암 변화가 심한 비디오 시퀀스에 대한 실험결과 제안한 알고리즘은 기존의 알고리즘에 비해 적은 계산량으로 높은 PSNR (peak signal to noise ratio) 성능을 나타내었다.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2009년도 춘계학술대회 논문집
• /
• pp.681-688
• /
• 2009

This paper deals with a bearing faults localization technique based on holographic approach by visualizing sound radiated from the faults. The main idea stems from the phenomenon that bearing faults in a moving vehicle generate impulsive sound. To visualize fault signal from the moving vehicle, we can use the moving frame acoustic holography [H.-S. Kwon and Y.-H. Kim, "Moving frame technique for planar acoustic holography," J. Acoust. Soc. Am. 103(4), 1734-1741, 1998]. However, it is not easy to localize faults only by applying the method. This is because the microphone array measures noise (for example, noise from other parts of the vehicle and the wind noise) as well as the fault signal while the vehicle passes by the array. To reduce the effect of noise, we propose two ideas which utilize the characteristics of fault signal. The first one is to average holograms for several frequencies to reduce the random noise. The second one is to apply the partial field decomposition algorithm [K.-U. Nam, Y.-H. Kim, "A partial field decomposition algorithm and its examples for near-field acoustic holography," J. of Acoust. Soc. Am. 116(1), 172-185, 2004] to the moving source, which can separate the fault signal and noise. Basic theory of those methods is introduced and how they can be applied to localize bearing faults is demonstrated. Experimental results via a miniature vehicle showed how well the proposed method finds out the location of source in practice.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.678-681
• /
• 2004

In this paper, efficient tracking of a moving object using optimal representative blocks is implemented by a mobile robot with a pan-tilt camera. The key idea comes from the fact that when the image size of moving object is shrunk in an image frame according to the distance between the camera of mobile robot and the moving object, the tracking performance of a moving object can be improved by changing the size of representative blocks according to the object image size. Motion estimation using Edge Detection(ED) and Block-Matching Algorithm(BMA) is often used in the case of moving object tracking by vision sensors. However these methods often miss the real-time vision data since these schemes suffer from the heavy computational load. In this paper, the optimal representative block that can reduce a lot of data to be computed, is defined and optimized by changing the size of representative block according to the size of object in the image frame to improve the tracking performance. The proposed algorithm is verified experimentally by using a two degree-of-freedom active camera mounted on a mobile robot.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2003년도 추계종합학술대회 논문집
• /
• pp.281-284
• /
• 2003

본 연구에서는 이동 객체 추적 시스템의 전처리 과정으로 움직임 영역을 검출하는 방법을 제안한다. 연속되는 영상으로부터 시간적으로 차이가 있는 두 개의 프레임을 얻은 후 이들의 이진 차영상을 구함으로서 움직임 영역을 검출한다. 차영상을 이용하는 경우 이전 프레임에서의 객체 영역과 현재 프레임에서의 객체 영역이 모두 검출된다. 추적 시스템에서는 카메라의 이동에 따라 배경이 변화되기 때문에 어느 영역이 객체의 현재 위치인지를 결정하는 방법이 필요하다. 이를 위해 본 연구에서는 현재 프레임의 이진 에지영상을 구하고 이것을 차영상과 논리적인 AND 연산을 수행한다. 실험 결과 이동 객체의 움직임 영역을 정확히 검출할 수 있음을 확인할 수 있었다.