• Journal of IKEEE
• /
• v.16 no.4
• /
• pp.356-363
• /
• 2012

Information technology improves convenience, safety, and performance of automobiles. Recently, a lot of algorithms are studied to provide safety and environment information for driving, and traffic sign recognition is one of them. It can provide important information for safety driving. In this paper, we propose a method for traffic sign detection and identification concentrating on reducing the computation time. First, potential traffic signs are segmented by color threshold, and a polygon approximation algorithm is used to detect appropriate polygons. The potential signs are compared with the template signs in the database using SURF and ORB feature matching method.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.6
• /
• pp.453-464
• /
• 2019

Recently, as the demand for 3D geospatial information increases, the importance of rapid and accurate data construction has increased. Although many studies have been conducted to register UAV (Unmanned Aerial Vehicle) imagery based on LiDAR (Light Detection and Ranging) data, which is capable of precise 3D data construction, studies using LiDAR data embedded in MMS (Mobile Mapping System) are insufficient. Therefore, this study compared and analyzed 9 matching algorithms based on feature points for registering reflectance image converted from LiDAR point cloud intensity data acquired from MMS with image data from UAV. Our results indicated that when the SIFT (Scale Invariant Feature Transform) algorithm was applied, it was able to stable secure a high matching accuracy, and it was confirmed that sufficient conjugate points were extracted even in various road environments. For the registration accuracy analysis, the SIFT algorithm was able to secure the accuracy at about 10 pixels except the case when the overlapping area is low and the same pattern is repeated. This is a reasonable result considering that the distortion of the UAV altitude is included at the time of UAV image capturing. Therefore, the results of this study are expected to be used as a basic research for 3D registration of LiDAR point cloud intensity data and UAV imagery.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.11a
• /
• pp.161-164
• /
• 2011

영상 매칭은 컴퓨터 비전에서 기초적인 기술로써 영상 추적, 물체인식 등 다양한 분양에서 많이 사용되고 있다. 하지만 스케일, 시점변화, 조명 변화에 강인한 매칭점을 찾는 것은 어려운 일이다. 이러한 문제점을 보완하기 위해 SURF(Scale Invariant Feature Transform), SIFT(Speed up Robust Features) 등의 알고리즘이 제안 되었지만, 여전히 조명변화에 불안정하고 정확하지 못한 성능을 보인다. 본 논문에서는 이러한 조명변화에 대한 문제점을 해결하기 위해 히스토그램 평활화를 이용하여 영상을 보정 후, SURF를 통한 영상 매칭을 하였다. 열악한 조명환경 내에서 촬영된 영상에서 SURF를 이용하여 표현자(Descriptor)를 생성 할 때 특징점이 잘 추출되지 않는 문제점을 해결하기 위하여 히스토그램 평활화를 이용하였고, 보정 후 특징점 개수가 많이 증가하는 것을 보여 확인하였다. 기존의 SURF와 개량된 SURF를 조명이 서로 다른 영상간의 매칭 성능을 비교함으로써 제안한 알고리즘의 우수성을 확인하였다

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.699-702
• /
• 2015

다중의 영상을 이용하여 하나의 파노라마 영상을 제작하는 기법은 컴퓨터 비전, 컴퓨터 그래픽스 등과 같은 여러 분야에서 널리 연구되고 있다. 파노라마 영상은 하나의 카메라에서 얻을 수 있는 영상의 한계, 즉 예를 들어 화각, 화질, 정보량 등의 한계를 극복할 수 있는 좋은 방법으로서 가상현실, 로봇비전 등과 같이 광각의 영상이 요구되는 다양한 분야에서 응용될 수 있다. 파노라마 영상은 단일 영상과 비교하여 보다 큰 몰입감을 제공한다는 점에서 큰 의미를 갖는다. 현재 다양한 파노라마 영상 제작 기법들이 존재하지만, 대부분의 기법들이 공통적으로 파노라마 영상을 구성할 때 각 영상에 존재하는 특징점 및 대응점을 검출하는 방식을 사용하고 있다. 본 논문에서 사용한 SURF(Speeded Up Robust Features) 알고리즘은 영상의 특징점을 검출할 때 영상의 흑백정보와 지역 공간 정보를 활용하는데, 영상의 크기 변화와 시점 검출에 강하며 SIFT(Scale Invariant Features Transform) 알고리즘에 비해 속도가 빠르다는 장점이 있어서 널리 사용되고 있다. 본 논문에서는 두 영상 사이 또는 하나의 영상과 여러 영상 사이에 대응되는 매칭을 계산하여 파노라마영상을 생성하는 처리 방법을 구현하고 기술하였다.

• 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.

• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.475-491
• /
• 2021

With the recent increase in available high-resolution (< ~1 m) satellite SAR images, the demand for precise registration of SAR images is increasing in various fields including change detection. The registration between high-resolution SAR images acquired in different look angle is difficult due to speckle noise and geometric distortion caused by the characteristics of SAR images. In this study, registration is performed in two stages, coarse and fine, using the x-band SAR data imaged at staring spotlight mode of TerraSAR-X. For the coarse registration, a method combining the adaptive sampling method and SAR-SIFT (Scale Invariant Feature Transform) is applied, and three rigid methods (NCC: Normalized Cross Correlation, Phase Congruency-NCC, MI: Mutual Information) and one non-rigid (Gefolki: Geoscience extended Flow Optical Flow Lucas-Kanade Iterative), for the fine registration stage, was performed for performance comparison. The results were compared by using RMSE (Root Mean Square Error) and FSIM (Feature Similarity) index, and all rigid models showed poor results in all image combinations. It is confirmed that the rigid models have a large registration error in the rugged terrain area. As a result of applying the Gefolki algorithm, it was confirmed that the RMSE of Gefolki showed the best result as a 1~3 pixels, and the FSIM index also obtained a higher value than 0.02~0.03 compared to other rigid methods. It was confirmed that the mis-registration due to terrain effect could be sufficiently reduced by the Gefolki algorithm.

• Journal of KIISE:Software and Applications
• /
• v.37 no.8
• /
• pp.641-646
• /
• 2010

This paper presents algorithms for real-time navigation of a humanoid robot with a stereo vision but no other sensors. Using the algorithms, a robot can recognize its 3D environment by retrieving SIFT features from images, estimate its position through the Kalman filter, and plan its path to reach a destination avoiding obstacles. Our approach focuses on estimating the robot’s central walking path trajectory rather than its actual walking motion by using an approximate model. This strategy makes it possible to apply mobile robot localization approaches to humanoid robot localization. Simple collision free path planning and motion control enable the autonomous robot navigation. Experimental results demonstrate the feasibility of our approach.

• Journal of Internet of Things and Convergence
• /
• v.2 no.4
• /
• pp.15-20
• /
• 2016

This paper describes the construction of knowledge data retrieval management system based on medical image CT. The developed system is aimed to improve the efficiency of the hospital by reading the medical images using the intelligent retrieval technology and diagnosing the patient 's disease name. In this study, the medical image DICOM file of PACS is read, the image is processed, and feature values are extracted and stored in the database. We have implemented a system that retrieves similarity by comparing new CT images required for medical treatment with the feature values of other CTs stored in the database. After converting 100 CT dicom provided for academic research into JPEG files, Code Book Library was constructed using SIFT, CS-LBP and K-Mean Clustering algorithms. Through the database optimization, the similarity of the new CT image to the existing data is searched and the result is confirmed, so that it can be utilized for the diagnosis and diagnosis of the patient.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.1
• /
• pp.81-88
• /
• 2015

Various satellite sensors having ranges of the visible, infrared, and thermal wavelengths have been launched due to the improvement of hardware technologies of satellite sensors development. According to the development of satellite sensors with various wavelength ranges, the fusion and integration of multisensor images are proceeded. Image matching process is an essential step for the application of multisensor images. Some algorithms, such as SIFT and SURF, have been proposed to co-register satellite images. However, when the existing algorithms are applied to extract matching points between optical and thermal images, high accuracy of co-registration might not be guaranteed because these images have difference spectral and spatial characteristics. In this paper, location of control points in a reference image is extracted by SURF, and then, location of their corresponding pairs is estimated from the correlation of the local similarity. In the case of local similarity, phase correlation method, which is based on fourier transformation, is applied. In the experiments by simulated, Landsat-8, and ASTER datasets, the proposed algorithm could extract reliable matching points compared to the existing SURF-based method.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.11
• /
• pp.43-52
• /
• 2014

In this paper, we propose the target detection method using image displacement, and classification method using SURF(Speeded Up Robust Features) feature points and BAS(Beam Angle Statistics) in infrared images. The SURF method that is a typical correspondence matching method in the area of image processing has been widely used, because it is significantly faster than the SIFT(Scale Invariant Feature Transform) method, and produces a similar performance. In addition, in most SURF based object recognition method, it consists of feature point extraction and matching process. In proposed method, it detects the target area using the displacement, and target classification is performed by using the geometry of SURF feature points. The proposed method was applied to the unmanned target detection/recognition system. The experimental results in virtual images and real images, we have approximately 73~85% of the classification performance.