• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.2
• /
• pp.79-89
• /
• 2022

Images taken using drones have been applied to fields that require rapid decision-making as they can quickly construct high-quality 3D spatial information for small regions. To construct spatial information based on drone images, it is necessary to determine the relationship between images by extracting keypoints between adjacent drone images and performing image matching. Therefore, in this study, three study regions photographed using a drone were selected: a region where parking lots and a lake coexisted, a downtown region with buildings, and a field region of natural terrain, and the performance of 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) algorithms were analyzed. The performance of the keypoints extraction algorithms was compared with the distribution of extracted keypoints, distribution of matched points, processing time, and matching accuracy. In the region where the parking lot and lake coexist, the processing speed of the BRISK algorithm was fast, and the SURF algorithm showed excellent performance in the distribution of keypoints and matched points and matching accuracy. In the downtown region with buildings, the processing speed of the AKAZE algorithm was fast and the SURF algorithm showed excellent performance in the distribution of keypoints and matched points and matching accuracy. In the field region of natural terrain, the keypoints and matched points of the SURF algorithm were evenly distributed throughout the image taken by drone, but the AKAZE algorithm showed the highest matching accuracy and processing speed.

• Journal of Korea Multimedia Society
• /
• v.22 no.12
• /
• pp.1404-1414
• /
• 2019

Educational books commonly use some copyrighted images with various kinds of deformation for helping students understanding. When using several copyrighted images made by merging or editing distortion in legal, we need to pay a charge to original copyright holders for each image. In this paper, we propose an efficient matching algorithm by separating each copyrighted image with the merged and edited type including rotation, illumination change, and change of size. We use the Oriented FAST and Rotated BRIEF (ORB) method as a basic feature matching scheme. To improve the matching accuracy, we design a new MIN-MAX similarity in matching stage. With the distorted dataset, the proposed method shows up-to 97% of precision in experiments. Also, we demonstrate that the proposed similarity measure also outperforms compared to other measure which is commonly used.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.11a
• /
• pp.1-4
• /
• 2012

영상 매칭 기술은 컴퓨터 비전 분야에서 다양하게 응용될 수 있는 기초적인 기술 중에 하나이다. 대표적인 영상 매칭 기술인 SIFT나 SURF는 강인한 영상 매칭 성능을 나타내지만 계산량이 방대하여 실시간 기술에 사용될 수 없는 문제점을 가진다. 최근에 ORB나 BRISK는 FAST 특징점 검출기와 BRIEF 특징점 표현자를 조합하여 실시간 영상 매칭을 가능하게 하면서 기존의 영상 매칭 기술과 견줄만한 성능을 나타내었다. 본 논문에서는 FAST와 BRIEF를 수정하여 영상 왜곡에 강인하면서 실시간으로 매칭을 수행할 수 있는 영상 매칭 알고리즘을 제안한다. 노이즈에 강인하면서 스케일 변화를 고려하기 위하여 특징점 후보 영역을 제한하고 스케일 공간을 생성하여 특징점을 검출한다. 또한 영상의 회전 변화에 강인한 영상 매칭을 가능하게 하기 위하여 주변 픽셀 패턴의 Gradient로 특징점 방향을 결정하여 픽셀 밝기 값 비교로 이진 특징점 표현자를 생성한다. 제안하는 영상 매칭 알고리즘은 적은 계산량으로 기존의 알고리즘보다 우수한 영상 매칭 성능을 나타낸다. 특별히 노이즈가 존재하는 영상의 매칭에서 노이즈의 영향에 강인한 매칭 성능을 보여준다.

• International Journal of Advanced Culture Technology
• /
• v.7 no.4
• /
• pp.321-326
• /
• 2019

As AI technology is recently introduced into various fields, it is being applied to the fashion field. This paper proposes a system for recommending cody clothes suitable for a user's selected clothes. The proposed system consists of user app, cody recommendation module, and server interworking of each module and managing database data. Cody recommendation system classifies clothing images into 80 categories composed of feature combinations, selects multiple representative reference images for each category, and selects 3 full body cordy images for each representative reference image. Cody images of the representative reference image were determined by analyzing the user's preference using Google survey app. The proposed algorithm classifies categories the clothing image selected by the user into a category, recognizes the most similar image among the classification category reference images, and transmits the linked cody images to the user's app. The proposed system uses the ResNet-50 model to categorize the input image and measures similarity using ORB and HOG features to select a reference image in the category. We test the proposed algorithm in the Android app, and the result shows that the recommended system runs well.