• 한국정보통신학회논문지
• /
• 제10권8호
• /
• pp.1373-1379
• /
• 2006

움직임 객체의 추출은 비디오 서비스 등에서 주요한 연구목적 중의 하나이다. 본 논문은 블록 움직임 벡터를 이용하여 움직임 객체를 추출하는 새로운 기법을 제시한다. 이를 위하여, 1) 사후 확률 밀도와 Gibbs 랜덤필드의 이용하여 블록 움직임 벡터를 결정하고, 2) 2-D 히스토그램을 바탕으로 전역 움직임을 구하고, 3) 경계 블록 분할 단계를 통해 객체 추출을 달성한다. 제안된 알고리듬은 특히 압축된 비디오 신호의 움직임 객체에 특히 유용하게 이용될 수 있다. 제안된 알고리듬을 여러 가지 영상에 적용한 결과 양호한 결과를 얻을 수 있었다.

• 한국측량학회지
• /
• 제40권2호
• /
• pp.79-89
• /
• 2022

드론을 이용하여 촬영한 영상은 소규모 지역에 대하여 고품질의 3차원 공간정보를 빠르게 구축할 수 있어 신속한 의사결정이 필요한 분야에 적용되고 있다. 드론 영상을 기반으로 공간정보를 구축하기 위해서는 인접한 드론 영상 간에 특징점 추출하고 영상 매칭을 수행하여 영상 간의 관계를 결정할 필요가 있다. 이에 본 연구에서는 드론을 이용하여 촬영한 주차장과 호수가 공존하는 지역, 건물이 있는 도심 지역, 자연 지형의 들판 지역의 3가지 대상지역을 선정하고 AKAZE (Accelerated-KAZE), BRISK (Binary Robust Invariant Scalable Keypoints), KAZE, ORB(Oriented FAST and Rotated BRIEF), SIFT (Scale Invariant Feature Transform), and SURF (Speeded Up Robust Features) 알고리즘의 성능을 분석하였다. 특징점 추출 알고리즘의 성능은 추출된 특징점의 분포, 매칭점의 분포, 소요시간, 그리고 매칭 정확도를 비교하였다. 주차장과 호수가 공존하는 지역에서는 BRISK 알고리즘의 속도가 신속하였으며, SURF 알고리즘이 특징점과 매칭점의 분포도와 매칭 정확도에서 우수한 성능을 나타내었다. 건물이 있는 도심 지역에서는 AKAZE 알고리즘의 속도가 신속하였으며 SURF 알고리즘이 특징점과 매칭점의 분포도와 매칭 정확도에서 우수한 성능을 나타내었다. 자연 지형의 들판 지역에서는 SURF 알고리즘의 특징점, 매칭점이 드론으로 촬영한 영상 전반적으로 고르게 분포되어 있으나 AKAZE 알고리즘이 가장 높은 매칭 정확도와 신속한 속도를 나타내었다.

• 한국생산제조학회지
• /
• 제22권3호
• /
• pp.452-458
• /
• 2013

Over the past several years, many studies have been carried out in the field of 3D data inspection systems. Several attempts have been made to improve the quality of manufactured parts. The introduction of laser sensors for inspection has made it possible to acquire data at a remarkably high speed. In this paper, a robust inspection technique for detecting defects in 3D pressed parts using laser-scanned data is proposed. Point cloud data are segmented for the extraction of features. These segmented features are used for shape matching during the localization process. An iterative closest point (ICP) algorithm is used for the localization of the scanned model and CAD model. To achieve a higher accuracy rate, the ICP algorithm is modified and then used for matching. To enhance the speed of the matching process, aKd-tree algorithm is used. Then, the deviation of the scanned points from the CAD model is computed.

• 반도체디스플레이기술학회지
• /
• 제15권2호
• /
• pp.61-65
• /
• 2016

Facial feature detection is a fundamental function in the field of computer vision such as security, bio-metrics, 3D modeling, and face recognition. There are many algorithms for the function, active shape model is one of the most popular local texture models. This paper addresses issues related to face detection, and implements an efficient extraction algorithm for extracting the facial feature points to use on iOS platform. In this paper, we extend the original ASM algorithm to improve its performance by four modifications. First, to detect a face and to initialize the shape model, we apply a face detection API provided from iOS CoreImage framework. Second, we construct a weighted local structure model for landmarks to utilize the edge points of the face contour. Third, we build a modified model definition and fitting more landmarks than the classical ASM. And last, we extend and build two-dimensional profile model for detecting faces within input images. The proposed algorithm is evaluated on experimental test set containing over 500 face images, and found to successfully extract facial feature points, clearly outperforming the original ASM.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2005년도 추계종합학술대회
• /
• pp.599-602
• /
• 2005

본 연구에서는 패션 디자인 분야에서 완성된 의상의 모델 사진을 활용해 다양한 원단을 직접 Draping함으로써 새로운 디자인을 창출할 수 있고 직접 샘플이나 시제품을 제작하지 않고도 시뮬레이션만으로 의상 작품을 확인 할 수 있도록 하였다. 또한 모델과 원단 이미지에 대한 데이터베이스를 구축하여 실시간으로 Mapping 결과를 확인할 수 있으며, 모델 사진과 원단 이미지의 자연스러운 Draping을 구현하기 위해 영역(Path)추출 알고리즘, 워프(Warp)알고리즘, 명암 추출과 적용 알고리즘을 이용한 2.5D Mapping 시스템을 개발 하였다.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.977-985
• /
• 2020

Aiming at the problem of complex feature extraction and low accuracy in human action recognition, this paper proposed a network structure combining batch normalization algorithm with GoogLeNet network model. Applying Batch Normalization idea in the field of image classification to action recognition field, it improved the algorithm by normalizing the network input training sample by mini-batch. For convolutional network, RGB image was the spatial input, and stacked optical flows was the temporal input. Then, it fused the spatio-temporal networks to get the final action recognition result. It trained and evaluated the architecture on the standard video actions benchmarks of UCF101 and HMDB51, which achieved the accuracy of 93.42% and 67.82%. The results show that the improved convolutional neural network has a significant improvement in improving the recognition rate and has obvious advantages in action recognition.

• 한국통신학회논문지
• /
• 제21권8호
• /
• pp.1885-1896
• /
• 1996

This paper describes the implementation of the AVT(Automatic video Tracker) using ASIC. The basic tracking algorithm is based on the spatio-temporal gradient method, and adaptive window sizing, track state decision algorithm were also realized. Newly developed ASIC performs recursive image filtering, extraction of spatio-temporal gradient/gradient functions of image in field rate. Using the FPGA/ASIC, the tracker was simply realized in one board type which can be easily applied to various image system. We conformed ASIC operation by computer simulation and tested the system in real tracking situations. From the result, the system can track the moving target which has a velocity of 2-3 pixel/field and a size of varying from 2 to 128 pixes. Also fast refresh rateof motion estimation(60Hz) improves the characteristics of servoing system which forms feedback loop with the tracker.

• 한국멀티미디어학회논문지
• /
• 제21권4호
• /
• pp.478-484
• /
• 2018

The choice of the motion features influences the result of the human action recognition method directly. Many factors often influence the single feature differently, such as appearance of the human body, environment and video camera. So the accuracy of action recognition is restricted. On the bases of studying the representation and recognition of human actions, and giving fully consideration to the advantages and disadvantages of different features, the Dense Trajectories(DT) algorithm is a very classic algorithm in the field of behavior recognition feature extraction, but there are some defects in the use of optical flow images. In this paper, we will use the improved Dense Trajectories(iDT) algorithm to optimize and extract the optical flow features in the movement of human action, then we will combined with Support Vector Machine methods to identify human behavior, and use the image in the KTH database for training and testing.

• 한국통신학회논문지
• /
• 제25권7A호
• /
• pp.1076-1083
• /
• 2000

Vehicle license plate recognition identifies vehicle as a unique, and have many applications in traffic monitoring field. In this paper, a vertical edge based algorithm to extract license plate within input gray-scale image is proposed. A size-and-shape filter based on seed-filling algorithm is applied to remove the edges that are impossible to be the vertical edges of license plate. Then the remaining edges are matched with each other according to some restricted conditions so as to locate license plate in input image. After license plate is extracted. normalized and segmented, the characters on it are recognized by template matching method. Experimental results show that the proposed algorithm can deal with license plates in normal shape effectively, as well as the license plates that are out of shape due to the angle of view.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.653-655
• /
• 2005

More than 70 percent of terrestrial territory of Korea is mountainous areas where degradation becomes serious year by year due to illegal tombs, expanding golf courses and stone mine development. We elaborate the potential usage of high resolution image for the monitoring of the phenomena. We made the classification of tombs and the statistical radiometric characteristics of graves were identified from this project. The graves could be classified to 4 groups from the field survey. As compared with grouping data after clustering and discriminant analysis, the two results coincided with each other. Object-oriented classification algorithm for feature extraction was theoretically researched in this project. And we did a pilot project, which was performed with mixed methods. That is, the conventional methods such as unsupervised and supervised classification were mixed up with the new method for feature extraction, object-oriented classification method. This methodology showed about $60\%$ classification accuracy for extracting tombs from satellite imagery. The extraction of tombs' geographical coordinates and graves themselves from satellite image was performed in this project. The stone mines and golf courses are extracted by NDVI and GVI. The accuracy of classification was around 89 percent. The location accuracy showed extraction of tombs from one-meter resolution image is cheaper and quicker way than GPS method. Finally we interviewed local government officers and made analyses on the current situation of mountainous area management and potential usage of KOMPSAT-II images. Based on the requirement analysis, we developed software, which is to management and monitoring system for mountainous area for local government.