• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.89-98
• /
• 2009

In the field of computer vision, image mosaicking is a common method for effectively increasing restricted the field of view of a camera by combining a set of separate images into a single seamless image. Image mosaicking based on feature points has recently been a focus of research because of simple estimation for geometric transformation regardless distortions and differences of intensity generating by motion of a camera in consecutive images. Yet, since most feature-point matching algorithms extract feature points using gray values, identifying corresponding points becomes difficult in the case of changing illumination and images with a similar intensity. Accordingly, to solve these problems, this paper proposes a method of image mosaicking based on feature points using color information of images. Essentially, the digital values acquired from a digital color camera are converted to values of a virtual camera with distinct narrow bands. Values based on the surface reflectance and invariant to the chromaticity of various illuminations are then derived from the virtual camera values and defined as color-invariant values invariant to changing illuminations. The validity of these color-invariant values is verified in a test using a Macbeth Color-Checker under simulated illuminations. The test also compares the proposed method using the color-invariant values with the conventional SIFT algorithm. The accuracy of the matching between the feature points extracted using the proposed method is increased, while image mosaicking using color information is also achieved.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.5
• /
• pp.741-749
• /
• 2022

Major space agencies are planning for the rover-based lunar exploration since water-ice was detected in permanently shadowed regions (PSR). Although sunlight does not directly reach the PSRs, it is expected that reflected sunlight sustains a certain level of low-light environment. In this research, the indoor testbed was made to simulate the PSR's lighting and topological conditions, to which low light enhancement methods (CLAHE, Dehaze, RetinexNet, GLADNet) were applied to restore image brightness and color as well as to investigate their influences on the performance of feature extraction and matching methods (SIFT, SURF, ORB, AKAZE). The experiment results show that GLADNet and Dehaze images in order significantly improve image brightness and color. However, the performance of the feature extraction and matching methods were improved by Dehaze and GLADNet images in order, especially for ORB and AKAZE. Thus, in the lunar exploration, Dehaze is appropriate for building 3D topographic map whereas GLADNet is adequate for geological investigation.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1003-1004
• /
• 2008

In this paper, we propose a 3D modeling method using Laser Slit Beam and Stereo Camera. We can get depth information of image by analyzing projected Laser Slit Beam on object. 3D modeling is demanded exquisite merge of 3D data. In our approach, we can get the depth image where the reliability is high. Each reconstructed 3D modeling is combined by the sink information which is acquired by SIFT (Scale Invariant Feature Transform) Algorithm. We perform experiments using indoor images. The results show that the proposed method works well in indoor environments

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.222-225
• /
• 2011

영상 매칭은 컴퓨터 비전에서 중요한 기초 기술 중에 하나이다. 하지만 스케일, 회전, 조명, 시점변화에 강인한 대응점을 찾는 것은 쉬운 작업이 아니다. 이러한 문제점을 보안하기 위해서 스케일 불변 특징 변환(Scale Invariant Feature Transform) 고속의 강인한 특징 추출(Speeded up robust features) 알고리즘등에 제안되었지만, 시점 변화에 있어서 취약한 문제점을 나타냈다. 본 논문에서는 이런 문제점을 해결하기 위해서 시점 변화에 강인한 알고리즘을 제안하였다. 시점 변화에 강인한 영상매칭을 위해서 원본 영상과 질의 영상간 유사도 높은 특징점들의 호모그래피 변환을 이용해서 질의 영상을 원본 영상과 유사하게 보정한 뒤에 매칭을 통해서 시점 변화에 강인한 알고리즘을 구현하였다. 시점이 변화된 여러 영상을 통해서 기존 SIFT,SURF와 성능과 수행 시간을 비교 함으로서, 본 논문에서 제안한 알고리즘의 우수성을 입증 하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.11
• /
• pp.5506-5521
• /
• 2017

Three-dimensional video (3DV), as the new generation of video format standard, can provide the viewers with a vivid screen sense and a realistic stereo impression. Meanwhile the view synthesis has become an important issue for 3DV application. Differently from the conventional methods based on depth, in this paper we propose a new view synthesis algorithm, which can employ the correlation among views and warp in the image domain only. There are mainly two contributions. One is the incorporation of sobel edge points into feature extraction and matching, which can obtain a better stable homography and then a visual comfortable synthesis view compared to SIFT points only. The other is a novel image blending method proposed to obtain a better synthesis image. Experimental results demonstrate that the proposed method can improve the synthesis quality both in subjectivity and objectivity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.1
• /
• pp.213-231
• /
• 2014

Existing image search systems allow users to search images by keywords, or by example images through content-based image retrieval (CBIR). On the other hand, users might learn more relevant textual information about an image from its text captions or surrounding contexts within documents or Web pages. Without such contexts, it's difficult to extract semantic description directly from the image content. In this paper, we propose an annotation watermarking system for users to embed text descriptions, and retrieve more relevant textual information from similar images. First, tags associated with an image are converted by two-dimensional code and embedded into the image by discrete wavelet transform (DWT). Next, for images without annotations, similar images can be obtained by CBIR techniques and embedded annotations can be extracted. Specifically, we use global features such as color ratios and dominant sub-image colors for preliminary filtering. Then, local features such as Scale-Invariant Feature Transform (SIFT) descriptors are extracted for similarity matching. This design can achieve good effectiveness with reasonable processing time in practical systems. Our experimental results showed good accuracy in retrieving similar images and extracting relevant tags from similar images.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1505-1514
• /
• 2022

Image matching is a crucial preprocessing step for effective utilization of multi-temporal and multi-sensor very high resolution (VHR) satellite images. Deep learning (DL) method which is attracting widespread interest has proven to be an efficient approach to measure the similarity between image pairs in quick and accurate manner by extracting complex and detailed features from satellite images. However, Image matching of VHR satellite images remains challenging due to limitations of DL models in which the results are depending on the quantity and quality of training dataset, as well as the difficulty of creating training dataset with VHR satellite images. Therefore, this study examines the feasibility of DL-based method in matching pair extraction which is the most time-consuming process during image registration. This paper also aims to analyze factors that affect the accuracy based on the configuration of training dataset, when developing training dataset from existing multi-sensor VHR image database with bias for DL-based image matching. For this purpose, the generated training dataset were composed of correct matching pairs and incorrect matching pairs by assigning true and false labels to image pairs extracted using a grid-based Scale Invariant Feature Transform (SIFT) algorithm for a total of 12 multi-temporal and multi-sensor VHR images. The Siamese convolutional neural network (SCNN), proposed for matching pair extraction on constructed training dataset, proceeds with model learning and measures similarities by passing two images in parallel to the two identical convolutional neural network structures. The results from this study confirm that data acquired from VHR satellite image database can be used as DL training dataset and indicate the potential to improve efficiency of the matching process by appropriate configuration of multi-sensor images. DL-based image matching techniques using multi-sensor VHR satellite images are expected to replace existing manual-based feature extraction methods based on its stable performance, thus further develop into an integrated DL-based image registration framework.

• Journal of Platform Technology
• /
• v.6 no.4
• /
• pp.26-33
• /
• 2018

In this paper, we propose an image retrieval algorithm for real-time processing and design it as hardware. The proposed method is based on the classification of BoWs(Bag of Words) algorithm and proposes an image search algorithm using bit stream. K-fold cross validation is used for the verification of the algorithm. Data is classified into seven classes, each class has seven images and a total of 49 images are tested. The test has two kinds of accuracy measurement and speed measurement. The accuracy of the image classification was 86.2% for the BoWs algorithm and 83.7% the proposed hardware-accelerated software implementation algorithm, and the BoWs algorithm was 2.5% higher. The image retrieval processing speed of BoWs is 7.89s and our algorithm is 1.55s. Our algorithm is 5.09 times faster than BoWs algorithm. The algorithm is largely divided into software and hardware parts. In the software structure, C-language is used. The Scale Invariant Feature Transform algorithm is used to extract feature points that are invariant to size and rotation from the image. Bit streams are generated from the extracted feature point. In the hardware architecture, the proposed image retrieval algorithm is written in Verilog HDL and designed and verified by FPGA and Design Compiler. The generated bit streams are stored, the clustering step is performed, and a searcher image databases or an input image databases are generated and matched. Using the proposed algorithm, we can improve convenience and satisfaction of the user in terms of speed if we search using database matching method which represents each object.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.554-556
• /
• 2006

A key component for autonomous mobile robot is to localize ifself. In this paper we suggest a vision-based localization and compensation of robot's location using ultrasound. Mobile robot travels along wall and searches each feature in indoor environment and transformed absolute coordinates of actuality environment using these points and builds a map. And we obtain information of the environment because mobile robot travels along wall. Localzation search robot's location candidate point by ultrasound and decide position among candidate point by features matching.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.3
• /
• pp.459-470
• /
• 2013

The discovery of nearest neighbors, without training in advance, has many applications, such as the formation of mosaic images, image matching, image retrieval and image stitching. When the quantity of data is huge and the number of dimensions is high, the efficient identification of a nearest neighbor (NN) is very important. This study proposes a variation of the KD-tree - the arbitrary KD-tree (KDA) - which is constructed without the need to evaluate variances. Multiple KDAs can be constructed efficiently and possess independent tree structures, when the amount of data is large. Upon testing, using extended synthetic databases and real-world SIFT data, this study concludes that the KDA method increases computational efficiency and produces satisfactory accuracy, when solving NN problems.