• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.383-392
• /
• 2023

Post-earthquake building condition assessment is crucial for subsequent rescue and remediation and can be automated by emerging computer vision and deep learning technologies. This study is based on an endeavour for the 2nd International Competition of Structural Health Monitoring (IC-SHM 2021). The task package includes five image segmentation objectives - defects (crack/spall/rebar exposure), structural component, and damage state. The structural component and damage state tasks are identified as the priority that can form actionable decisions. A multi-task Convolutional Neural Network (CNN) is proposed to conduct the two major tasks simultaneously. The rest 3 sub-tasks (spall/crack/rebar exposure) were incorporated as auxiliary tasks. By synchronously learning defect information (spall/crack/rebar exposure), the multi-task CNN model outperforms the counterpart single-task models in recognizing structural components and estimating damage states. Particularly, the pixel-level damage state estimation witnesses a mIoU (mean intersection over union) improvement from 0.5855 to 0.6374. For the defect detection tasks, rebar exposure is omitted due to the extremely biased sample distribution. The segmentations of crack and spall are automated by single-task U-Net but with extra efforts to resample the provided data. The segmentation of small objects (spall and crack) benefits from the resampling method, with a substantial IoU increment of nearly 10%.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.692-702
• /
• 2017

Face detection using the LBP based feature descriptor has issues in that it can not represent spatial information between facial shape and facial components such as eyes, nose and mouth. To address these issues, in previous research, a facial image was divided into a number of square sub-regions. However, since the sub-regions are divided into different numbers and sizes, the division criteria of the sub-region suitable for the database used in the experiment is ambiguous, the dimension of the LBP histogram increases in proportion to the number of sub-regions and as the number of sub-regions increases, the sensitivity to facial orientation rotation increases significantly. In this paper, we present a novel facial region segmentation method that can solve in-plane rotation issues associated with LBP based feature descriptors and the number of dimensions of feature descriptors. As a result, the proposed method showed detection accuracy of 99.0278% from a single facial image rotated in orientation.

• Journal of Internet Computing and Services
• /
• v.18 no.5
• /
• pp.39-46
• /
• 2017

In this paper, we proposes method of vanishing point detection using orthogonality of vanishing point, under the "Manhattan World" assumption that the structure of the city is mostly grid and vanishing point are orthogonal to each other. The feature that the vanishing point are orthogonal to each other can be useful for inferring the missing point that are not detected among the three vanishing point, and prevent the vanishing point detected close to the other vanishing point. In this paper, we detect Vertical vanishing point through statistical approach and detect Horizontal and Front vanishing point through structural approach. Experimental results show that the proposed method improves the detection accuracy of the vanishing point compared with the existing method.

• International Journal of Precision Engineering and Manufacturing
• /
• v.5 no.1
• /
• pp.27-35
• /
• 2004

In the field of machine vision using a single camera mounted on a mobile robot, although the detection and tracking of moving objects from a moving observer, is complex and computationally demanding task. In this paper, we propose a new scheme for a mobile robot to track and capture a moving object using images of a camera. The system consists of the following modules: data acquisition, feature extraction and visual tracking, and trajectory generation. And a single camera is used as visual sensors to capture image sequences of a moving object. The moving object is assumed to be a point-object and projected onto an image plane to form a geometrical constraint equation that provides position data of the object based on the kinematics of the active camera. Uncertainties in the position estimation caused by the point-object assumption are compensated using the Kalman filter. To generate the shortest time trajectory to capture the moving object, the linear and angular velocities are estimated and utilized. The experimental results of tracking and capturing of the target object with the mobile robot are presented.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.8
• /
• pp.57-66
• /
• 2011

In this paper, it is proposed for algorithm to detect human efficiently using a edge symmetry and gradient directional characteristics in realtime by the feature extraction in a single input image. Proposed algorithm is composed of three stages, preprocessing, region partition of human candidates, verification of candidate regions. Here, preprocessing stage is strong the image regardless of the intensity and brightness of surrounding environment, also detects a contour with characteristics of human as considering the shape features size and the condition of human for characteristic of human. And stage for region partition of human candidates has separated the region with edge symmetry for human and size in the detected contour, also divided 1st candidates region with applying the adaboost algorithm. Finally, the candidate region verification stage makes excellent the performance for the false detection by verifying the candidate region using feature vector of a gradient for divided local area and classifier. The results of the simulations, which is applying the proposed algorithm, the processing speed of the proposed algorithms is improved approximately 1.7 times, also, the FNR(False Negative Rate) is confirmed to be better 3% than the conventional algorithm which is a single structure algorithm.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.3
• /
• pp.693-698
• /
• 2018

This paper proposes a vehicle detection method for parking areas using unmanned aerial vehicles (UAVs) and using YOLOv2, which is a recent, known, fast, object-detection real-time algorithm. The YOLOv2 convolutional network algorithm can calculate the probability of each class in an entire image with a one-pass evaluation, and can also predict the location of bounding boxes. It has the advantage of very fast, easy, and optimized-at-detection performance, because the object detection process has a single network. The sliding windows methods and region-based convolutional neural network series detection algorithms use a lot of region proposals and take too much calculation time for each class. So these algorithms have a disadvantage in real-time applications. This research uses the YOLOv2 algorithm to overcome the disadvantage that previous algorithms have in real-time processing problems. Using Darknet, OpenCV, and the Compute Unified Device Architecture as open sources for object detection. a deep learning server is used for the learning and detecting process with each car. In the experiment results, the algorithm could detect cars in a dense area using UAVs, and reduced overhead for object detection. It could be applied in real time.

• The Journal of Engineering Geology
• /
• v.5 no.3
• /
• pp.277-288
• /
• 1995

Fracture detection has always been very attractive to the log, because it is important in many of our prospecting activities, e.g. in understanding the underground rock formation and also the fluid flow as a high permeability path. This paper demonstrates the use of high resolution borehole acoustic scanner for the detection of fractures. The tool, known as Televiewer, is the first acoustic borehole imaging system to use a focussed beam. The acoustic beams generated by a single transducer are sent toward the borehole wall, scanning the wall in a tight helix as the tool moves along the borehole. The amplitudes and travel times of the reflected signals are then measured, which produces the corresponding images. The highly resolved amplitude image allows to recognize various size of fractures and in addition to derive the rock strength from the image. Meanwhile, the travel time image itself can be directly converted to a precise caliper image, providing detailed information of deviations of the borehole shape. It also allows correction of and explanations for amplitude variations. Field measurements were carried Out at the Cheongyang study sites in Korea to illustrate the efficiency of the televiewer log.

• Journal of the Korean Society for information Management
• /
• v.25 no.2
• /
• pp.49-68
• /
• 2008

In many information retrieval experiments, the data fusion techniques have been used to achieve higher effectiveness in comparison to the single evidence-based retrieval. However, there had not been many image retrieval studies using the data fusion techniques especially in combining retrieval results based on multiple retrieval methods. In this paper, we describe how the image retrieval effectiveness can be improved by combining two sets of the retrieval results using the Sobel operator-based edge detection and the Self Organizing Map(SOM) algorithms. We used the clip art images from a commercial collection to develop a test data set. The main advantage of using this type of the data set was the clear cut relevance judgment, which did not require any human intervention.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.476-479
• /
• 2003

The Rough transform (HT) is often used for extracting global features in binary images, for example curve and line segments, from local features such as single pixels. The HT is useful due to its insensitivity to missing edge points and occlusions, and robustness in noisy images. However, it possesses some disadvantages, such as time and memory consumption due to the number of input data and the selection of an optimal and efficient resolution of the accumulator space can be difficult. Another problem of the HT is in the difficulty of peak detection due to the discrete nature of the image space and the round off in estimation. In order to resolve the problem mentioned above, a possibilistic C-means approach to clustering [1] is used to cluster neighboring peaks. Several experimental results are given.

• Proceedings of the KIEE Conference
• /
• 2000.11d
• /
• pp.761-764
• /
• 2000

This paper presents a Fuzzy Neural Network (FNN) system to decide whether or not the right information of lanes can be extracted from gray-level images of road scene. The decision of noisy level of input images has been required because much noises usually deteriorates the performance of feature detection based on image processing and lead to erroneous results. As input parameters to FNN, eight noisiness indexes are constructed from a cumulative distribution function (CDF) and proved the indexes being classifiers of images as the good and the bad corrupted by sources of noise by correlation analysis between input images and the indexes. Considering real-time processing and discrimination efficiency, the proposed FNN is structured by eight input parameters, three fuzzy variables and single output. We conduct much experiments and show that our system has comparable performance in terms of false-positive rates.