• 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.

• 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.

• 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.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.85-86
• /
• 2008

로봇은 오도메터리 정보를 이용해 위치추정을 할 수 있다. 그러나 주행하는 동안 발생되는 슬립현상에 의해 오도메터러 정보만으로는 로봇의 정확한 위치추정을 할 수 없다. 정확한 위치추정을 위해서 관성센서를 이용하여 오도메터리 정보를 보정한 위치추정 방법이 있다. 실내 이동로봇에 적용하려면 관성센서는 소형이어야 하는데, 그에 따라 노이즈는 심해지고, 정확성도 낮아지는 문제가 있나. 그래서 현재까지는 이런 문제를 갖고 있는 관성센서를 실내 이동로봇의 위치추정의 정확성을 높이기 위해 비관성센서 또는 카메라 영상을 조합하는 연구들을 하고 있다. 그러나 이러한 연구들은 대부분 관성센서 성능 실험과 시뮬레이션에 결론을 내리고 있어 실제 실험에 따른 정확성을 확인할 수 없다. 또한 최근 영상 SIFT 알고리즘을 적용한 SLAM 연구에서도 나타나는 문제는 이동로봇의 위치추정의 부정확성이다. 따라서 본 논문은 SLAM에서 문제가 되는 위치추정의 부정확성을 최소화하기 위해 자이로와 가속도계를 이용하여 정학한 위치추정을 하고자 한다.

• 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 KIISE
• /
• v.42 no.6
• /
• pp.764-768
• /
• 2015

Requirement of effective image handling methods such as image retrieval has been increasing with the rising production and consumption of multimedia data. In this paper, a method of constructing more effective descriptor is proposed for robust keypoint based image retrieval. The proposed method uses information embedded in the first order and second order derivative images, in addition to the scale space image, for the descriptor construction. The performance of multi-image descriptor is evaluated in terms of the similarities in keypoints with a public domain image database that contains various image transformations. The proposed descriptor shows significant improvement in keypoint matching with minor increase of the length.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1877-1885
• /
• 2015

This paper presents a new Nearest-Neighbors based weighted representation for images and weighted K-Nearest-Neighbors (WKNN) classifier to improve the precision of image classification using the Bag of Visual Words (BOVW) based models. Scale-invariant feature transform (SIFT) features are firstly extracted from images. Then, the K-means++ algorithm is adopted in place of the conventional K-means algorithm to generate a more effective visual dictionary. Furthermore, the histogram of visual words becomes more expressive by utilizing the proposed weighted vector quantization (WVQ). Finally, WKNN classifier is applied to enhance the properties of the classification task between images in which similar levels of background noise are present. Average precision and absolute change degree are calculated to assess the classification performance and the stability of K-means++ algorithm, respectively. Experimental results on three diverse datasets: Caltech-101, Caltech-256 and PASCAL VOC 2011 show that the proposed WVQ method and WKNN method further improve the performance of classification.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.364-380
• /
• 2016

The most popular approach in object classification is based on the bag of visual-words model, which has several fundamental problems that restricting the performance of this method, such as low time efficiency, the synonym and polysemy of visual words, and the lack of spatial information between visual words. In view of this, an object classification based on weakly supervised E2LSH and saliency map weighting is proposed. Firstly, E2LSH (Exact Euclidean Locality Sensitive Hashing) is employed to generate a group of weakly randomized visual dictionary by clustering SIFT features of the training dataset, and the selecting process of hash functions is effectively supervised inspired by the random forest ideas to reduce the randomcity of E2LSH. Secondly, graph-based visual saliency (GBVS) algorithm is applied to detect the saliency map of different images and weight the visual words according to the saliency prior. Finally, saliency map weighted visual language model is carried out to accomplish object classification. Experimental results datasets of Pascal 2007 and Caltech-256 indicate that the distinguishability of objects is effectively improved and our method is superior to the state-of-the-art object classification methods.

• The Journal of the Korea Contents Association
• /
• v.9 no.2
• /
• pp.43-50
• /
• 2009

We proposed similarity detection method of the video frame data that extracts the feature data of own video frame and creates the 1-D signal in this paper. We get the similar frame boundary and make the representative frames within the frame boundary to extract the similarity extraction between video. Representative frames make blurring frames and extract the feature data using DOG values. Finally, we convert the feature data into the 1-D signal and compare the contents similarity. The experimental results show that the proposed algorithm get over 0.9 similarity value against noise addition, rotation change, size change, frame delete, frame cutting.

• Advances in Automotive Engineering
• /
• v.1 no.1
• /
• pp.143-152
• /
• 2018

In this study an economical image stitching algorithm for use in automotive industry is developed for retrofittable panoramic image assistance applications. The aim of this project is to develop a driving assistance system known as Panoramic Parking Assistance (PPA) which is cheap, retrofittable and compatible for every type of automobiles. PPA generates bird's eye view image using cameras installed on the automobiles. Image stitching requires to get bird's eye view position of the vehicle. Panoramic images are wide area images that cannot be available by taking one shot, attained by stitching the overlapping areas. To achieve correct stitching many algorithms are used. This study includes some type of these algorithms and presents a simple one that is economical and practical. Firstly, the mathematical model of a wide view of angle camera is provided. Then distorted image correction is performed. Stitching is implemented by using the SIFT and SURF algorithms. It has been seen that using such algorithms requires complex image processing knowledge and implementation of high quality digital processors, which would be impracticle and costly for automobile use. Thus a simpler algorithm has been developed to decrase the complexity. The proposed algorithm uses one matching point for every couple of images and has ease of use and does not need high power processors. To show the efficiency, images coming from four distinct cameras are stitched by using the algorithm developed for the study and usability for automotive application is analyzed.