• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.849-852
• /
• 2000

본 논문은 배경이 고정되지 않은 복잡한 동영상에서의 물체 추적을 위하여 다중 모델 색상 히스토그램 역투영(Multi Model Color Histogram Back-projection)방법을 제안한다. 색상 히스토그램 역투영(Color Histogram Back-projection)을 이용하면 카메라의 움직임 때문에 발생하는 배경의 변화에 관계없이 물체를 추적할 수 있다. 기존의 방법은 추적하려는 물체에 대해 하나의 모델만을 적용했기 때문에, 배경영역 색분포의 영향을 많이 받는다. 이를 해결하기 위해 다중 모델 색상 히스토그램 역투영 방법을 이용하였다. 이 방법은 추적하려는 물체에 대해 여러 개의 모델을 구하여 각각에 대해 색상 히스토그램 역투영을 수행한다 또한 역투영 이진 영상에서 물체의 위치를 결정하기 위한 수평, 수직 프로젝션 방법의 문제점을 레이블링(Labeling)을 사용하여 보완하였다.

• Journal of Korea Multimedia Society
• /
• v.14 no.2
• /
• pp.171-181
• /
• 2011

A vision-based method for positioning and orienting of pallets is presented in this paper, which guides autonomous forklifts to engage pallets automatically. The method uses a single camera mounted on the fork carriage instead of two cameras for stereo vision that is conventionally used for positioning objects in 3D space. An image back-projection technique for determining the orient of a pallet without any fiducial marks is suggested in tins paper, which projects two feature lines on the front plane of the pallet backward onto a virtual plane that can be rotated around a given axis in 3D space. We show the fact that the rotation angle of the virtual plane on which the back-projected feature lines are parallel can be used to describe the orient of the pallet front plane. The position of the pallet is determined by using ratio of the distance between the back-projected feature lines and their real distance on the pallet front plane. Through a test on real pallet images, we found that the proposed method was applicable to real environment practically in real-time.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.103-107
• /
• 2013

In this paper, A real-time lane tracking algorithm is proposed for lane departure warning system. To eliminate perspective effect, input image is converted into Bird's View by inverse perspective mapping. Next, suitable features are extracted for lane detection. Lane feature that correspond to area of interest and RANSAC are used to detect lane candidates. And driving lane is decided by clustering of lane candidates. Finally, detected lane is tracked using the Kalman filter. Experimental results show that the proposed algorithm can be processed within 30ms and its detection rate is approximately 90% on the highway in a variety of environments such as day and night.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.157-168
• /
• 2023

Image segmentation and supervised classification techniques are widely used to monitor the ground surface using high-resolution remote sensing images. In order to classify various objects, a process of defining a class corresponding to each object and selecting samples belonging to each class is required. Existing methods for extracting class samples should select a sufficient number of samples having similar intensity characteristics for each class. This process depends on the user's visual identification and takes a lot of time. Representative samples of the class extracted are likely to vary depending on the user, and as a result, the classification performance is greatly affected by the class sample extraction result. In this study, we propose an image classification technique that minimizes user intervention when extracting class samples by applying the histogram back-projection technique and has consistent intensity characteristics of samples belonging to classes. The proposed classification technique using histogram back-projection showed improved classification accuracy in both the experiment using hue subchannels of the hue saturation value transformed image from Compact Advanced Satellite 500-1 imagery and the experiment using the original image compared to the technique that did not use histogram back-projection.

• Journal of KIISE:Software and Applications
• /
• v.34 no.3
• /
• pp.266-274
• /
• 2007

This paper proposes a new reconstruction method of high-resolution facial image from a low-resolution facial image based on top-down machine learning and recursive error back-projection. A face is represented by a linear combination of prototypes of shape and that of texture. With the shape and texture information of each pixel in a given low-resolution facial image, we can estimate optimal coefficients for a linear combination of prototypes of shape and those that of texture by solving least square minimizations. Then high-resolution facial image can be obtained by using the optimal coefficients for linear combination of the high-resolution prototypes. In addition, a recursive error back-projection procedure is applied to improve the reconstruction accuracy of high-resolution facial image. The encouraging results of the proposed method show that our method can be used to improve the performance of the face recognition by applying our method to reconstruct high-resolution facial images from low-resolution images captured at a distance.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.512-515
• /
• 2010

환경오염으로 인해 아토피 등의 피부질환이 증가하고 있으며 이에 국내에서는 인터넷을 통한 아토피 진단 서비스는 많다. 하지만 단순한 설문조사 형식으로 진단에 대한 객관성을 유지하기 어려워 신뢰도가 낮다. 이에 본 논문은 컴퓨터 비전 인식 기술을 활용하여, 컴퓨터에서 처리가능한 아토피 환자의 환부 영상을 수집 및 진단하는 시스템을 개발한다. 아토피 진단 시스템은 환부 영상을 사용자로부터 입력받아 색상값에 대한 히스토그램을 만들어 정규화한다. 다음으로 정규화된 히스토그램의 확률적 분포를 이용해 역투영한 결과 영상을 만들어 내게 되며 이 역투영 영상을 바탕으로 피부색을 제외한 부분을 아토피 침범 영역이라 판단하게 된다. 최종적으로는 입력 영상으로부터 얻어진 침범 영역, 문진을 이용한 점수를 이용하여 SCORAD 지수 스코어링 하게 된다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.3
• /
• pp.475-482
• /
• 2023

Synthetic Aperture Radar (SAR), which provides images of targets using radio signals, enables monitoring at all times regardless of weather conditions. In this paper, the SAR system was installed on the test aircraft to collect SAR raw data on the ground and the sea, and the results of image formation using the backprojection algorithm were presented.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.11
• /
• pp.2492-2498
• /
• 2013

In this paper, A lane tracking algoritm is proposed for lane departure warning system. To eliminate perspective effect, input image is converted into Bird's View by inverse perspective mapping. Next, suitable features are extracted for lane detection. Using clustering and lane similarity function with noise suppression features are extracted. Finally, lane model is calculated using RANSAC and lane model is tracked using Kalman Filter. Experimental results show that the proposed algorithm can be processed within 20ms and its detection rate approximately 90% on the highway in a variety of environments.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.7
• /
• pp.81-89
• /
• 2017

Autofocus(AF) Method is essential to overcome the performance degradation due to motion measurement errors under airborne SAR environment. In this paper, back-projection algorithm(BPA) is applied to SAR raw data acquired under the squinted mode, and preprocessing algorithm of AF for BPA is investigated. To apply AF to SAR image effectively, image backplane rotation method and doppler location alignment function for BPA are proposed. The proposed method is applied to SAR raw data acquired in a flight test and shows excellent performance improvement in real data.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.30 no.4
• /
• pp.324-329
• /
• 2010

Fuel rods using in nuclear power plants consist of uranium dioxide pellets enclosed in zirconium alloy(zircaloy) tubes. It is vitally important for the pellet surface to remain free from pits, cracks and chipping defects after it is loaded into the tubes to prevent local hot spots during reactor operation. This paper investigates the feasibility study for detecting surface flaws of pellets contained within nuclear fuel rod through X-ray tomography simulation. Reconstructed images used by parallel and fan-beam filtered back projection method were presented and confirmed the accessibility between simulation data and MPS(missing pellet surface) image data.