• Journal of Digital Contents Society
• /
• v.7 no.1
• /
• pp.67-74
• /
• 2006

In current video-conferencing systems. user's face movements are restricted by fixed camera, therefore it is inconvenient to users. To solve this problem, tracking of face movements is needed. Tracking using whole face needs much computing time and whole face is difficult to define as an one feature. Thus, using several feature points in face is more desirable to track face movements efficiently. This paper addresses an effective eye location algorithm which is essential process of automatic human face tracking system for natural video-conferencing. The location of eye is very important information for face tracking, as eye has most clear and simplest attribute in face. The proposed algorithm is applied to candidate face regions from the face region extraction. It is not sensitive to lighting conditions and has no restriction on face size and face with glasses. The proposed algorithm shows very encouraging results from experiments on video-conferencing environments.

• The KIPS Transactions:PartB
• /
• v.18B no.4
• /
• pp.213-220
• /
• 2011

This paper proposes an effective, four-stage smoke detection method based on video that provides emergency response in the event of unexpected hazards in early fire-alarming systems. In the first phase, an approximate median method is used to segment moving regions in the present frame of video. In the second phase, a color segmentation of smoke is performed to select candidate smoke regions from these moving regions. In the third phase, a feature extraction algorithm is used to extract five feature parameters of smoke by analyzing characteristics of the candidate smoke regions such as area randomness and motion of smoke. In the fourth phase, extracted five parameters of smoke are used as an input for a K-nearest neighbor (KNN) algorithm to identify whether the candidate smoke regions are smoke or non-smoke. Experimental results indicate that the proposed four-stage smoke detection method outperforms other algorithms in terms of smoke detection, providing a low false alarm rate and high reliability in open and large spaces.

• Journal of Bio-Environment Control
• /
• v.20 no.4
• /
• pp.277-282
• /
• 2011

We carried out shape recognition. We found out cucumber's feature shape by means of neural network and back propagation algorithm. We developed an algorithm which finds object position and shape in real image and we gained following conclusion as a result. It was processed for feature shape extraction of cucumber to detect automatic. The output pattern rates of the miss-detected objects was 0.1~4.2% in the output pattern which was recognized as cucumber. We were gained output pattern according to image resolution $445{\times}363$, $501{\times}391$, $450{\times}271$, $297{\times}421$. It was appeared that no change was detected. When learning pattern was increased to 25, miss-detection ratio was 16.02%, and when learning pattern had 2 pattern, it didn't detect 8 cucumber in 40 images.

• Smart Structures and Systems
• /
• v.32 no.1
• /
• pp.23-35
• /
• 2023

Steel bolted joint is an important part of steel structure, and its damage directly affects the bearing capacity and durability of steel structure. Currently, the existing research mainly focuses on the identification of corroded bolts and corroded bolts respectively, and there are few studies on multiple states. A detection framework of corroded and loosened bolts is proposed in this study, and the innovations can be summarized as follows: (i) Vision Transformer (ViT) is introduced to replace the third and fourth C3 module of you-only-look-once version 5s (YOLOv5s) algorithm, which increases the attention weights of feature channels and the feature extraction capability. (ii) Three states of the steel bolts are considered, including corroded bolt, bolt missing and clean bolt. (iii) Line segment detector (LSD) is introduced for bolt rotation angle calculation, which realizes bolt looseness detection. The improved YOLOv5s model was validated on the dataset, and the mean average precision (mAP) was increased from 0.902 to 0.952. In terms of a lab-scale joint, the performance of the LSD algorithm and the Hough transform was compared from different perspective angles. The error value of bolt loosening angle of the LSD algorithm is controlled within 1.09%, less than 8.91% of the Hough transform. Furthermore, the proposed framework was applied to fullscale joints of a steel bridge in China. Synthetic images of loosened bolts were successfully identified and the multiple states were well detected. Therefore, the proposed framework can be alternative of monitoring steel bolted joints for management department.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.2
• /
• pp.111-119
• /
• 2013

It is essential and fundamental to extract boundary information of target object via massive three-dimensional point data acquired from laser scanner. Especially extracting boundary information of manmade features such as buildings is quite important because building is one of the major components consisting complex contemporary urban area, and has artificially defined shape. In this research, extended ${\chi}$-algorithm using geometry information of point data was proposed to extract boundary information of building from three-dimensional point data consisting building. The proposed algorithm begins with composing Delaunay triangulation process for given points and removes edges satisfying specific conditions process. Additionally, to make whole boundary extraction process efficient, we used Sweep-hull algorithm for constructing Delaunay triangulation. To verify the performance of the proposed extended ${\chi}$-algorithm, we compared the proposed algorithm with Encasing Polygon Generating Algorithm and ${\alpha}$-Shape Algorithm, which had been researched in the area of feature extraction. Further, the extracted boundary information from the proposed algorithm was analysed against manually digitized building boundary in order to test accuracy of the result of extracting boundary. The experimental results showed that extended ${\chi}$-algorithm proposed in this research proved to improve the speed of extracting boundary information compared to the existing algorithm with a higher accuracy for detecting boundary information.

• Korean Journal of Remote Sensing
• /
• v.27 no.1
• /
• pp.33-41
• /
• 2011

In the information communication technology, it is world-widely apparent that trend movement from internet web to smartphone app by users demand and developers environment. So it needs kinds of appropriate technological responses from geo-spatial domain regarding this trend. However, most cases in the smartphone app are the map service and location recognition service, and uses of geo-spatial contents are somewhat on the limited level or on the prototype developing stage. In this study, app for extraction of corner point features using geo-spatial imagery and their linkage to database system are developed. Corner extraction is based on Harris algorithm, and all processing modules in database server, application server, and client interface composing app are designed and implemented based on open source. Extracted corner points are applied LOD(Level of Details) process to optimize on display panel. Additional useful function is provided that geo-spatial imagery can be superimposed with the digital map in the same area. It is expected that this app can be utilized to automatic establishment of POI (Point of Interests) or point-based land change detection purposes.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.3
• /
• pp.439-448
• /
• 1996

Extraction and selection of the informative features play a central role in pattern recognition. This paper describes a modified back-propagation algorithm that performs selection of the informative features and trains a neural network simultaneously. The algorithm is mainly composed of three repetitive steps : training, connection pruning, and input unit elimination. Afer initial training, the connections that have small magnitude are first pruned. Any unit that has a small number of connections to the hidden units is deleted,which is equivalent to excluding the feature corresponding to that unit.If the error increases,the network is retraned,again followed by connection pruning and input unit elimination.As a result,the algorithm selects the most im-portant features in the measurement space without a transformation to another space.Also,the selected features are the most-informative ones for the classification,because feature selection is tightly coupled with the classifi-cation performance.This algorithm helps avoid measurement of redundant or less informative features,which may be expensive.Furthermore,the final network does not include redundant parameters,i.e.,weights and biases,that may cause degradation of classification performance.In applications,the algorithm preserves the most informative features and significantly reduces the dimension of the feature vectors whiout performance degradation.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2005.05a
• /
• pp.345-349
• /
• 2005

Massive amount of satellite image processing such asglobal/continental-level analysis and monitoring requires automated and speedy georegistration. There could be two major automated approaches: (1) rigid mathematical modeling using sensor model and ephemeris data; (2) heuristic co-registration approach with respect to existing reference image. In case of ETM+, the accuracy of the first approach is known as RMSE 250m, which is far below requested accuracy level for most of satellite image processing. On the other hands, the second approach is to find identical points between new image and reference image and use heuristic regression model for registration. The latter shows better accuracy but has problems with expensive computation. To improve efficiency of the coregistration approach, the author proposed a pre-qualified matching algorithm which is composed of feature extraction with canny operator and area matching algorithm with correlation coefficient. Throughout the pre-qualification approach, the computation time was significantly improved and make the registration accuracy is improved. A prototype was implemented and tested with the proposed algorithm. The performance test of 14 TM/ETM+ images in the U.S. showed: (1) average RMSE error of the approach was 0.47 dependent upon terrain and features; (2) the number average matching points were over 15,000; (3) the time complexity was 12 min per image with 3.2GHz Intel Pentium 4 and 1G Ram.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.181-185
• /
• 2006

Image co-registration is the process of overlaying two images of the same scene, one of which represents a reference image, while the other is geometrically transformed to the one. In order to improve efficiency and effectiveness of the co-registration approach, the author proposed a pre-qualified area matching algorithm which is composed of feature extraction with canny operator and area matching algorithm with cross correlation coefficient. For refining matching points, outlier detection using studentized residual was used and iteratively removes outliers at the level of three standard deviation. Throughout the pre-qualification and the refining processes, the computation time was significantly improved and the registration accuracy is enhanced. A prototype of the proposed algorithm was implemented and the performance test of 3 Landsat images of Korea showed: (1) average RMSE error of the approach was 0.436 Pixel (2) the average number of matching points was over 38,475 (3) the average processing time was 489 seconds per image with a regular workstation equipped with a 3 GHz Intel Pentium 4 CPU and 1 Gbytes Ram. The proposed approach achieved robustness, full automation, and time efficiency.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.109-112
• /
• 1999

Image segmentation is the critical first step in image information extraction for computer vision systems. Clustering methods have been used extensively in color image segmentation. Most analytic fuzzy clustering approaches are divided from the fuzzy c-means(FCM) algorithm. The FCM algorithm uses fie probabilistic constraint that the memberships of a data point across classes sum to 1. However, the memberships resulting from the FCM do not always correspond to the intuitive concept of degree of belonging or compatibility. Moreover, the FCM algorithm has considerable trouble under noisy environments in the feature space. Recently, a possibilistic approach to clustering(PCM) for solving above problems was proposed. In this paper, we used the PCM for color image segmentation. This approach differs from existing fuzzy clustering methods for color image segmentation in that the resulting partition of the data can be interpreted as a possibilistic partition. So, the problems in the FCM can be solved by the PCM. But, the clustering results by the PCM are not smoothly bounded, and they often have holes. The region growing was used as a postprocessing after smoothing the noise points in the pixel seeds. In our experiments, we illustrate that the PCM us reasonable than the FCM in noisy environments.