• Journal of information and communication convergence engineering
• /
• v.12 no.2
• /
• pp.128-134
• /
• 2014

In this paper, we present a graphics processing unit (GPU)-based matching technique for the purpose of fast feature matching between different images. The scale invariant feature transform algorithm developed by Lowe for various feature matching applications, such as stereo vision and object recognition, is computationally intensive. To address this problem, we propose a matching technique optimized for GPUs to perform computations in less time. We optimize GPUs for fast computation of keypoints to make our system quick and efficient. The proposed method uses a self-organizing map feature matching technique to perform efficient matching between the different images. The experiments are performed on various image sets to examine the performance of the system under varying conditions, such as image rotation, scaling, and blurring. The experimental results show that the proposed algorithm outperforms the existing feature matching methods, resulting in fast feature matching due to the optimization of the GPU.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.1
• /
• pp.52-57
• /
• 2007

In this paper we proposed multi-directional matching windows combined by multi-dimensional feature vector matching, which uses not only intensity values but also multiple feature values, such as variance, first and second derivative of pixels. Multi-dimensional feature vector matching has the advantage of compensating the drawbacks of area-based stereo matching using one feature value, such as intensity. We define matching cost of a pixel by the minimum value among eight multi-dimensional feature vector distances of the pixels expanded in eight directions having the interval of 45 degrees. As best stereo matches, we determine the two points with the minimum matching cost within the disparity range. In the experiment we used aerial imagery and IKONOS satellite imagery and obtained more accurate matching results than that of conventional matching method.

• The KIPS Transactions:PartB
• /
• v.19B no.2
• /
• pp.113-122
• /
• 2012

This paper presents a new stereo matching technique which is based on the matching of feature windows and feature links. The proposed method uses the FAST feature detector to find image features in stereo images and determines the correspondences of the detected features in the stereo images. We define a feature window which is an image region containing several image features. The proposed technique consists of two matching steps. First, a feature window is defined in a standard image and its correspondence is found in a reference image. Second, the corresponding features between the matched windows are determined by using the feature link technique. If there is no correspondence for an image feature in the standard image, it's disparity is interpolated by neighboring feature sets. We evaluate the accuracy of the proposed technique by comparing our results with the ground truth of in a stereo image database. We also compare the matching accuracy and computation time with two conventional feature-based stereo matching techniques.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.772-775
• /
• 2006

Muilti-dimensional feature vector matching algorithm uses multiple features such as intensity, gradient, variance, first or second derivative of a pixel to find correspondence pixels in stereo images. In this paper, we proposed a new method for adjusting automatically the weight of feature in multi-dimensional feature vector matching considering sharpeness of a pixel in feature vector distance curve. The sharpeness consists of minimum and maximum vector distances of a small window mask. In the experiment we used IKONOS satellite stereo imagery and obtained accurate matching results comparable to the manual weight-adjusting method.

• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.414-417
• /
• 1993

The methods for stereo matching are divided into two techniques: area-based matching and feature-based matching. To find corresponding points by area-based method, it takes a lot of time because there are many points to be matched. Feature-based matching algorithm is often used because with this method it matches only some feature points so that the processing time is fast even though it requires interpolation after matching. In this paper, we propose the smart technique by which we makes features simpler than conventional methods to match an image pair by feature-based matching algorithm.

• Journal of the Institute of Convergence Signal Processing
• /
• v.14 no.4
• /
• pp.217-221
• /
• 2013

Recently, researches for methods of generating binary feature descriptors have been actively done. Since matching of binary feature descriptors uses Hamming distance which is based on bit operations, it is much more efficient than that of previous general feature descriptors which uses Euclidean distance based on real number operations. However, since increase in the number of features linearly drops matching speed, in applications such as object tracking where real-time applicability is a must, there has been an increasing demand for methods of further improving the matching speed of binary feature descriptors. In this regard, this paper proposes a method that improves the matching speed greatly while maintaining the matching accuracy by splitting high dimensional binary feature descriptors to several low dimensional ones and sequentially analyzing their partial Hamming distances. To evaluate the efficiency of the proposed method, experiments of comparison with previous matching methods are conducted. In addition, this paper discusses schemes of generating binary feature descriptors for maximizing the performance of the proposed method. Based on the analysis on the performance of several generation schemes, we try to find out the most effective scheme.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.12-14
• /
• 2005

In this paper, we proposed an temporal error concealment (EC) using the proposed boundary matching method and the adaptive block matching method. The proposed boundary matching method improves the spatial correlation of the macroblocks (MBs) by reusing the pixels of the concealed MB to estimate a motion vector of a error MB. The adaptive block matching method inspects the horizontal edge and the vertical edge feature of a error MB surroundings, and it conceals the error MBs in reference to more stronger edge feature. This improves video quality by raising edge connection feature of the error MBs and the neighborhood MBs. In particular, we restore a lost MB as the unit of 8${\times}$16 block or 16${\times}$8 block by using edge feature from the surrounding macroblocks. Experimental results show that the proposed algorithm gives better results than the conventional algorithms from a subjective and an objective viewpoint.

• Korean Journal of Remote Sensing
• /
• v.36 no.4
• /
• pp.545-555
• /
• 2020

This paper focuses on automatic image registration between EO (Electro-Optical) and IR (InfraRed) satellite images with different spectral properties using block-based approach and simple preprocessing technique to enhance the performance of feature matching. If unpreprocessed EO and IR images from Kompsat-3A satellite were applied to local feature matching algorithms(Scale Invariant Feature Transform, Speed-Up Robust Feature, etc.), image registration algorithm generally failed because of few detected feature points or mismatched pairs despite of many detected feature points. In this paper, we proposed a new image registration method which improved the performance of feature matching with block-based registration process on 9-divided image and pre-processing technique based on adaptive histogram equalization. The proposed method showed better performance than without our proposed technique on visual inspection and I-RMSE. This study can be used for automatic image registration between various images acquired from different sensors.

• Journal of Information Processing Systems
• /
• v.12 no.2
• /
• pp.183-195
• /
• 2016

This paper presents a complete method for vehicle detection and tracking in a fixed setting based on computer vision. Vehicle detection is performed based on Scale Invariant Feature Transform (SIFT) feature matching. With SIFT feature detection and matching, the geometrical relations between the two images is estimated. Then, the previous image is aligned with the current image so that moving vehicles can be detected by analyzing the difference image of the two aligned images. Vehicle tracking is also performed based on SIFT feature matching. For the decreasing of time consumption and maintaining higher tracking accuracy, the detected candidate vehicle in the current image is matched with the vehicle sample in the tracking sample set, which contains all of the detected vehicles in previous images. Most remarkably, the management of vehicle entries and exits is realized based on SIFT feature matching with an efficient update mechanism of the tracking sample set. This entire method is proposed for highway traffic environment where there are no non-automotive vehicles or pedestrians, as these would interfere with the results.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.12
• /
• pp.2363-2371
• /
• 2015

In this paper, we propose a new feature matching algorithm which is robust to the viewpoint change by using the FAST(Features from Accelerated Segment Test) feature detector and the SIFT(Scale Invariant Feature Transform) feature descriptor. The original FAST algorithm unnecessarily results in many feature points along the edges in the image. To solve this problem, we apply the principal curvatures for refining it. We use the SIFT descriptor to describe the extracted feature points and calculate the homography matrix through the RANSAC(RANdom SAmple Consensus) with the matching pairs obtained from the two different viewpoint images. To make feature matching robust to the viewpoint change, we classify the matching pairs by calculating the Euclidean distance between the transformed coordinates by the homography transformation with feature points in the reference image and the coordinates of the feature points in the different viewpoint image. Through the experimental results, it is shown that the proposed algorithm has better performance than the conventional feature matching algorithms even though it has much less computational load.