• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.9
• /
• pp.49-55
• /
• 2019

This paper presents a marker image evaluation method based on analysis of object distribution in images and classification of images with repetitive patterns for effective marker-based augmented reality (AR) system development. We measure the variance of feature point coordinates to distinguish marker images that are vulnerable to occlusion, since object distribution affects object tracking performance according to partial occlusion in the images. Moreover, we propose a method to classify images suitable for object recognition and tracking based on the fact that the distributions of descriptor vectors among general images and repetitive-pattern images are significantly different. Comprehensive experiments for marker images confirm that the proposed marker image evaluation method distinguishes images vulnerable to occlusion and repetitive-pattern images very well. Furthermore, we suggest that scale-invariant feature transform (SIFT) is superior to speeded up robust features (SURF) in terms of object tracking in marker images. The proposed method provides users with suitability information for various images, and it helps AR systems to be realized more effectively.

• Journal of Korea Multimedia Society
• /
• v.16 no.9
• /
• pp.1057-1066
• /
• 2013

Personal verification using finger-knuckle-print(FKP) uses lines and creases at the finger-knuckle area, so the orientation information of texture is an important feature. In this paper, we propose an effective FKP verification method which extracts keypoints using SIFT algorithm and matches the keypoints by vector similarity. The vector is defined as a direction vector which connects a keypoint extracted from a query image and a corresponding keypoint extracted from a reference image. Since the direction vector is created by a pair of local keypoints, the direction vector itself represents only a local feature. However, it has an advantage of expanding a local feature to a global feature by comparing the vector similarity among vectors in two images. The experimental results show that the proposed method is superior to the previous methods based on orientation codes.

• 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.

• Journal of Internet Computing and Services
• /
• v.20 no.4
• /
• pp.91-102
• /
• 2019

In autonomous driving systems, the ability to classify pedestrians in images captured by cameras is very important for pedestrian safety. In the past, after extracting features of pedestrians with HOG(Histogram of Oriented Gradients) or SIFT(Scale-Invariant Feature Transform), people classified them using SVM(Support Vector Machine). However, extracting pedestrian characteristics in such a handcrafted manner has many limitations. Therefore, this paper proposes a method to classify pedestrians reliably and effectively using CNN's(Convolutional Neural Network) deep features and transfer learning. We have experimented with both the fixed feature extractor and the fine-tuning methods, which are two representative transfer learning techniques. Particularly, in the fine-tuning method, we have added a new scheme, called M-Fine(Modified Fine-tuning), which divideslayers into transferred parts and non-transferred parts in three different sizes, and adjusts weights only for layers belonging to non-transferred parts. Experiments on INRIA Person data set with five CNN models(VGGNet, DenseNet, Inception V3, Xception, and MobileNet) showed that CNN's deep features perform better than handcrafted features such as HOG and SIFT, and that the accuracy of Xception (threshold = 0.5) isthe highest at 99.61%. MobileNet, which achieved similar performance to Xception and learned 80% fewer parameters, was the best in terms of efficiency. Among the three transfer learning schemes tested above, the performance of the fine-tuning method was the best. The performance of the M-Fine method was comparable to or slightly lower than that of the fine-tuningmethod, but higher than that of the fixed feature extractor method.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.45 no.6
• /
• pp.49-59
• /
• 2008

SIFT(Scale Invariant Feature Transform) is an algorithm to extract vectors at pixels around keypoints, in which the pixel colors are very different from neighbors, such as vortices and edges of an object. The SIFT algorithm is being actively researched for various image processing applications including 3-D image constructions, and its most computation-intensive stage is a keypoint localization. In this paper, we develope a fixed-point model of the keypoint localization and propose its efficient hardware architecture for embedded applications. The bit-length of key variables are determined based on two performance measures: localization accuracy and error rate. Comparing with the original algorithm (implemented in Matlab), the accuracy and error rate of the proposed fixed point model are 93.57% and 2.72% respectively. In addition, we found that most of missing keypoints appeared at the edges of an object which are not very important in the case of keypoints matching. We estimate that the hardware implementation will give processing speed of $10{\sim}15\;frame/sec$, while its fixed point implementation on Pentium Core2Duo (2.13 GHz) and ARM9 (400 MHz) takes 10 seconds and one hour each to process a frame.

• Journal of Korea Multimedia Society
• /
• v.14 no.10
• /
• pp.1243-1251
• /
• 2011

This paper proposes a new vehicle model recognition using scale invariant feature transform to car's headlights image. Proposed vehicle model recognition raises the accuracy using "homogeneity" calculated from the distribution of features. In the experiment with 400 test images taken from 54 different vehicles, proposed method has 90% recognition rate and 16.45 homogeneity.

• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.231-233
• /
• 2009

The object recognition is one of the major computer vision fields. The object recognition using features(SIFT) is finding common features in input images and query images. But the object recognition using feature methods has suffered of difficulties due to heavy calculations when resizing input images and query images. In this paper, we focused on speed up finding features in the images. we proposed method using block segmentation and histogram. Block segmentation used diving input image and than histogram decided correlation between each 1]lock and query image. This paper has confirmed that tile matching time reduced for object recognition since reducing block.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.11
• /
• pp.4534-4555
• /
• 2015

We propose a robust object cataloging method using multiple locally distinct heterogeneous features for aiding image retrieval. Due to challenges such as variations in object size, orientation, illumination etc. object recognition is extraordinarily challenging problem. In these circumstances, we adapt local interest point detection method which locates prototypical local components in object imageries. In each local component, we exploit heterogeneous features such as gradient-weighted orientation histogram, sum of wavelet responses, histograms using different color spaces etc. and combine these features together to describe each component divergently. A global signature is formed by adapting the concept of bag of feature model which counts frequencies of its local components with respect to words in a dictionary. The proposed method demonstrates its excellence in classifying objects in various complex backgrounds. Our proposed local feature shows classification accuracy of 98% while SURF,SIFT, BRISK and FREAK get 81%, 88%, 84% and 87% respectively.

• International Journal of Contents
• /
• v.9 no.2
• /
• pp.1-7
• /
• 2013

This paper proposes an efficient matching algorithm based on ASIFT (Affine Scale-Invariant Feature Transform) which is fully invariant to affine transformation. In our approach, we proposed a method of reducing similar measure matching cost and the number of outliers. First, we combined the Manhattan and Chessboard metrics replacing the Euclidean metric by a linear combination for measuring the similarity of keypoints. These two metrics are simple but really efficient. Using our method the computation time for matching step was saved and also the number of correct matches was increased. By applying an Optimized Random Sampling Algorithm (ORSA), we can remove most of the outlier matches to make the result meaningful. This method was experimented on various combinations of affine transform. The experimental result shows that our method is superior to SIFT and ASIFT.

• Journal of Radiation Industry
• /
• v.7 no.2_3
• /
• pp.121-126
• /
• 2013

The new algorithm technique is necessary to incorporate for analyzing and evaluating extreme condition like a nuclear accident. In this study, the combined methodology for measuring the three-dimensional space was compared with SIFT (Scale Invariant Feature Transform) and SURF (Speeded-Up Robust Feature) algorithm. The suggested method can be used for the acquisition of spatial information using the robot vision in the districted area of the nuclear facilities. As a result, these data would be helpful for identify the damaged part, degree of damage and determination of recovery sequences.