• 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.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.1
• /
• pp.43-54
• /
• 1996

This paper presents new heuristic search algorithms for searching rectilinear r(L1), link metric, and combined shortest paths in the presence of orthogonal obstacles. The GMD(GuidedMinimum Detour) algorithm combines the best features of maze-running algorithms and line-search algorithms. The SGMD(Line-by-Line GuidedMinimum Detour)algorithm is a modiffication of the GMD algorithm that improves efficiency using line-by-line extensions. Our GMD and LGMD algorithms always find a rectilinear shortest path using the guided A search method without constructing a connection graph that contains a shortest path. The GMD and the LGMD algorithms can be implemented in O(m＋eloge＋NlogN) and O(eloge＋NlogN) time, respectively, and O(e＋N) space, where m is the total number of searched nodes, is the number of boundary sides of obstacles, and N is the total number of searched line segment. Based on the LGMD algorithm, we consider not only the problems of finding a link metric shortest path in terms of the number of bends, but also the combined L1 metric and Link Metric shortest path in terms of the length and the number of bands.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.12 s.177
• /
• pp.61-69
• /
• 2005

This paper presents an efficient method of extracting line segments from the occupancy grids in a grid map. The grid map is composed of 2-D grids that have both the occupancy and orientation probabilities using sonar sensors. We evaluate the orientation information of every grid when the occupancy probability of the grid is updated from sonar range data. To find the shape of an object in the map from orientation information, the orientations are clustered into several groups according to their values. The line segments are, then, extracted from the clusters based on Hough transform. Finally, a feature-based map is built with these line segments. The proposed method is illustrated with the results produced by sets of experiments in an indoor environment.

• The Journal of Korea Robotics Society
• /
• v.9 no.3
• /
• pp.140-146
• /
• 2014

This paper introduces a dual-arm robot painter system which is capable of sketching a camera-captured image with short line segments. To express various curved edges in the image by combining line segments, we first apply edge detection algorithm to the entire image, split the edged image into small boxed pieces, and then apply Hough Transformation to each piece so that the edges inside the piece can be approximated with short line segments. To draw the picture within a reasonable time, we designed a simple dual-arm robot system and controlled both arms concurrently according to linear interpolation algorithm. From the experiments, we could verify that simple linear motions can describe various images effectively with a unique brush style.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.20 no.3
• /
• pp.13-20
• /
• 1983

A method for the detecting defined vertices is described in this paper. An alogrithm detecting vertex position by means of calculating an error and distinguishing the defined inner and outer corners by the chain code of line segments is described. To calculate the error, virtual links are detected by means of a jointing relations of line segments for a contour. And so an error is calculated by measuring a minimum distance from a jointing point between the line segments to virtual link. As a result, this method is more flexible and effective than conventional Freeman's method.

• International journal of advanced smart convergence
• /
• v.11 no.1
• /
• pp.1-10
• /
• 2022

Single-view reconstruction (SVR) is a fundamental method in computer vision. Often used for reconstructing human-made environments, the Manhattan world assumption presumes that planes in the real world exist in mutually orthogonal directions. Accordingly, this paper addresses an automatic SVR algorithm for Manhattan worlds. A method for estimating the directions of planes using graph-cut optimization is proposed. After segmenting an image from extracted line segments, the data cost function and smoothness cost function for graph-cut optimization are defined by considering the directions of the line segments and neighborhood segments. Furthermore, segments with the same depths are grouped during a depth-estimation step using a minimum spanning tree algorithm with the proposed weights. Experimental results demonstrate that, unlike previous methods, the proposed method can identify complex Manhattan structures of indoor and outdoor scenes and provide the exact boundaries and intersections of planes.

• Advances in concrete construction
• /
• v.16 no.2
• /
• pp.79-89
• /
• 2023

The occurrence of unexpected horizontal offset in the instrument or target will result in accumulated horizontal deviation in segment alignment with traditional short-line match method. A geometry control method, the four-point method, is developed for precast segmental bridges to avoid the influences of unexpected horizontal offset. The concept of the four-point method is elucidated. Furthermore, the detailed instruments and instructions are introduced. Finally, the four-point method is validated through a practical engineering application. According to the survey data, after short-line match precast construction, the vertical deviations on both sides vary between -5 mm and 5 mm in almost all segments, and the horizontal deviations vary between -4 mm and 4 mm in all segments. Without on-site adjustment, the maximum vertical and horizontal closure gaps are 12.3 and 26.1 mm, respectively. The four-point method is suggested to alleviate the issues associated with relatively poor soil conditions in casting yard.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.17 no.4
• /
• pp.622-637
• /
• 1993

The Purposes of this study were to investigate the significant correlation among the length changes of body surface total lines and between the length changes of body surface total lines and those of component body surface segment lines, and to reveal anticipated relation among body surface length changes by the lower limb movement including all movement direction of hip joint, knee joint & ankle joint for the more functional clothing making & designing. 10 Crosswise & 5 lengthwise body surface total lines and 48 crosswise & 39 lengthwise body surface segment lines of 26 female college students aged from 18 to 24 years were measured directly on the body surface and analyzed by ANOYA & Multiple Comparison Test(Tukey), and the length changes of them were calculated as the difference of the mean length at Fl movement from the mean length at each movement and were analyzed by PEARSON CORRELATION. The results were as following : 1. Correlation among the length changes of body surface total lines (1) Correlation among the length changes of body surface total lines significantly changed by the movement ; 1) The more GA5 expanded, the more GA6 & GA7 each expanded, and the more GA18 expanded, the more GA1 & GA3 each expanded. 2) The more GA15 expanded, the less GA14 each contracted. 3) The more GA7 expanded, the larger GA17 contracted. 4) The more GA1 & GA18 expanded, the larger GA16 contracted, and the larger GM contracted, the less GA16 contracted. (2) Only GA7 and GA17(at F4) showed high (over r=0.7) correlation coefficient, But others' correlation coefficients were r=0.4~0.7. (3) Correlation coefficients among & between girth items and length items 1) Correlation coefficients among girth items were shown + ; between GA3 and GA4, GA5, GA8, between GA5 and GA6, GA7, GA9 each, between GA1 and GA6 and between GA4 and GA7. 2) Correlation coefficients among length items were shown + or - ; shown + between GA14 and GA15 and between GA17 and GA16 ; but Shown - Between GAlS and GA16. 3) Correlation coefficients between girth items and length items were mainly shown - : shown-between GA1 and GA16, GA17, between, GA4 and GA16, between GA6, GA7 each and GA17, between GA8 and GA18 ; but shown + between GA1, GA3 each and GA18 and between GA8 and GA14 were shown +. 2. Correlation between the length changes of body surface total lines and those of component body surface segment lines. (1) All correlation coefficients were + except A147 of GA14. (2) Correlation coefficient over r=0.7 was shown ; between GA3 and CB3, A35 each, between GA5 and A054, between GA6 and A63, between GA7 and A72, A74 each, between GA8 and A83, A84 each, between GA15 and A153, between GA16 and Al64, Al65 each, between GA18 and A189 : but was not shown between GA4, GA17 and it's component body surface segment lines each. (3) Characteristics of correlation between the length changes of body surface total lines and those of body surface segment lines ; 1) If significant correlation of body surface total lines were expansion parts, it's component body surface segment lines was also expansion segment and the otherwise were the same. But exception was shown between expansion line GA3 and A031 (at F4), between GA18 and AlS9 (at F6) and between GA14 and A147, so to speak GA3 & lines and GA14 was contraction total line oppositely A147 was expansion. 2) The more GA3, GAlS expanded, the less A031, A189 contracted. 3) The more GA14 contracted, the more A147 expanded. 4) All correlation except the above 2), 3), the more total lines (GA1, GA3, GA5, GA15, GA16, GA18) expanded, the more segment lines (A15, CB1, A31, A34, CB3, A52, A54, A153, A169, A181) expanded, or the larger total lines (GA14, GA16, GA17) contracted, the larger segment lines (A141, A142, A161, A164, A165, A172) contracted.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.2
• /
• pp.447-454
• /
• 2011

Power-line interference(PLI) can distort certain regions in analysing the ECG signal. In particular, the regions such as P and R wave that are important element in diagnosing with arrhythmia is expressed as different type of noise according to the case whether power-line frequency is multiples of sampling frequency and or not. Noise characteristics is also divided into linearity and non-linearity. In this paper, adaptive subtraction method for removing variable PLI of ECG signal is proposed. We classify the multiple relationship between power line and sampling frequency as Multiple and Non-multiple. PLI of Linear segment is extracted through moving average filter, PLI of non-linear segment is extracted through the interference component that is extracted in the linear segment and stored in the temporary buffer. The performance of P wave and R wave detection is evaluated by using 119 data record of MIT-BIH arrhythmia database. The achieved scores indicate P wave detection rate of 97.91%, R wave detection rate of 96.66% and P wave detection rate of 99.01%, R wave detection rate of 97.93% accuracy respectively for Notch filter and proposed subtraction method.

• International Journal of Highway Engineering
• /
• v.16 no.5
• /
• pp.133-142
• /
• 2014

PURPOSES : The objective was to develop the advanced method which could not explain each observation's specific characteristic in the present negative binomial method that results in under-estimation of the standard error(t-value inflation) and affects the confidence of whole derived results. METHODS : This study dealt with traffic accidents occurring within interchange segment on highway main line with RPNB(Random Parameter Negative Binomial) method that enables to take account of heterogeneity. RESULTS : As a result, AADT and lighting installation type on the road were revealed to have random parameter and in terms of other geometric variables, all were derived as fixed parameter(same effect on every segment). Also, marginal effects were adapted to analyze the relative effects on traffic accidents. CONCLUSIONS : This study proves that RPNB method which considers each observation's specific characteristics is better fitted to the accident data with geometrics. Thus, it is recommended that RPNB model or other methods which could consider the heterogeneity needs to be adapted in accident analysis.