• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.365-381
• /
• 2023

The existing vision-based techniques for inspection and condition assessment of civil infrastructure are mostly manual and consequently time-consuming, expensive, subjective, and risky. As a viable alternative, researchers in the past resorted to deep learning-based autonomous damage detection algorithms for expedited post-disaster reconnaissance of structures. Although a number of automatic damage detection algorithms have been proposed, the scarcity of labeled training data remains a major concern. To address this issue, this study proposed a semi-supervised learning (SSL) framework based on consistency regularization and cross-supervision. Image data from post-earthquake reconnaissance, that contains cracks, spalling, and exposed rebars are used to evaluate the proposed solution. Experiments are carried out under different data partition protocols, and it is shown that the proposed SSL method can make use of unlabeled images to enhance the segmentation performance when limited amount of ground truth labels are provided. This study also proposes DeepLab-AASPP and modified versions of U-Net++ based on channel-wise attention mechanism to better segment the components and damage areas from images of reinforced concrete buildings. The channel-wise attention mechanism can effectively improve the performance of the network by dynamically scaling the feature maps so that the networks can focus on more informative feature maps in the concatenation layer. The proposed DeepLab-AASPP achieves the best performance on component segmentation and damage state segmentation tasks with mIoU scores of 0.9850 and 0.7032, respectively. For crack, spalling, and rebar segmentation tasks, modified U-Net++ obtains the best performance with Igou scores (excluding the background pixels) of 0.5449, 0.9375, and 0.5018, respectively. The proposed architectures win the second place in IC-SHM2021 competition in all five tasks of Project 2.

• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.430-439
• /
• 2015

The demand of violence detection techniques using a video analysis to help prevent crimes is increasing recently. Many researchers have studied vision based behavior recognition but, violent behavior analysis techniques usually focus on violent scenes in television and movie content. Many methods previously published usually used both a color(e.g., skin and blood) and motion information for detecting violent scenes because violences usually involve blood scenes in movies. However, color information (e.g., blood scenes) may not be useful cues for violence detection in surveillance videos, because they are rarely taken in real world situations. In this paper, we propose a method of violent behavior detection in surveillance videos using motion vectors such as flow vector magnitudes and changes in direction except the color information. In order to evaluate the proposed algorithm, we test both USI dataset and various real world surveillance videos from YouTube.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.53-59
• /
• 2008

Recently, vision-based hand gesture recognition techniques have been developed for assisting elderly and disabled people to control home appliances. Frequently occurred problems which lower the hand gesture recognition rate are due to the inter-person variation and intra-person variation. The recognition difficulty caused by inter-person variation can be handled by using user dependent model and model selection technique. And the recognition difficulty caused by intra-person variation can be handled by using fuzzy logic. In this paper, we propose multivariate fuzzy decision tree learning and classification method for a hand motion recognition system for multiple users. When a user starts to use the system, the most appropriate recognition model is selected and used for the user.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.3
• /
• pp.249-256
• /
• 2016

Recently, a number of techniques to ensure the free walking for the visually impaired and transportation vulnerable have been studied. As a device for free walking, there are such as a smart cane and smart glasses to use the computer vision, ultrasonic sensor, acceleration sensor technology. In a typical technique, such as techniques for finds object and detect obstacles and walking area and recognizes the symbol information for notice environment information. In this paper, we studied recognization algorithm of the selected symbols that are required to visually impaired, with the deep learning algorithm. As a results, Use CNN(Convolutional Nueral Network) technique used in the field of deep-learning image processing, and analyzed by comparing through experimentation with various deep learning architectures.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.331-334
• /
• 2010

This paper proposes a new design of a video-base fire detection system using texture and color spatial distribution information. The video sequences used are taken in different days with different lighting conditions having different backgrounds. The time complexity of most previous vision-based fire detection techniques are very high due to lengthy programing. To overcome the problems of lengthy codes and time complexity, in this algorithm, at first we normalize the video image frames by size and color information. Then the spatial distribution of the color information is used to extract the candidate regions, later using visual texture of the fire, we detect the fire regions. The experimental results show an real-time fire detection over thousands of image frames, and have higher detection rate when compared to the conventional fire detection techniques.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.10 no.4
• /
• pp.593-599
• /
• 2022

In this study, a crack monitoring system capable of detecting cracks based on image processing techniques was developed to effectively check cracks, which are the main damage of concrete structures, and a program capable of imaging and analyzing cracks was developed using machine vision. This system provides objective and quantitative data by replacing the appearance inspection that checks cracks with the naked eye. The verification of the development system was applied to the construction site of a self-healing concrete water tank to monitor the crack and the amount of change in the crack width according to age. In the case of crack width detected by image analysis, the difference from the measured value using a digital microscope was up to 0.036 mm, and the crack healing effect of self-healing concrete could be confirmed through the reduction of crack width.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.240-251
• /
• 2016

This paper presents a real-time indoor location and pose estimation method that utilizes simple artificial markers and image analysis techniques for the purpose of warehouse automation. The conventional indoor localization methods cannot work robustly in warehouses where severe environmental changes usually occur due to the movement of stocked goods. To overcome this problem, the proposed framework places artificial markers having different interior pattern on the predefined position of the warehouse floor. The proposed algorithm obtains marker candidate regions from a captured image by a simple binarization and labeling procedure. Then it extracts maker interior pattern information from each candidate region in order to decide whether the candidate region is a true marker or not. The extracted interior pattern information and the outer boundary of the marker are used to estimate location and heading angle of the localization system. Experimental results show that the proposed localization method can provide high performance which is almost equivalent to that of the conventional method using an expensive LIDAR sensor and AMCL algorithm.

• Journal of the Korean Society of Systems Engineering
• /
• v.6 no.2
• /
• pp.47-57
• /
• 2010

Taylor and Ford in the 1910s led to the "scientific management" for the entire industry from the manufacturing spread of TQM Total Quality Management has been structured as a management efficiency, such as 6-Sigma techniques were developed. SW development also introduces the idea, such as CMMI and SPICE-based process management, management practices have evolved. However, in recent years to increase the knowledge of workers in the manufacturing process oriented management approach is under serious challenge. Business performance or productivity will be varied depending all motivation, human relationship, job involvement rather than simply putting a lot of time. Especially in the SW industry which is depending on human resource, Creativity should be limited in traditional management methods. Recently, Google and Apple, Cisco and global advanced companies adopt a human relationship management. Their productivity and creativity in product development has been successful by giving autonomy and motivation, enthusiasm and vision to tile employees. Human relationship management since the mid-1990s, appears as a new paradigm so called Agile process in the field of SW development. Agile processes emphasis on light, flexible and responding to changes immediately in the business environment step away from traditional management approach which is the heavy and complicated process. In this paper, agile project management concepts and practices which is applied to industry will be examined.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.568-571
• /
• 1997

Recently, the number of techniques for analyzing medical images has been increasing in computer vision, employing X-ray CT images, ultrasound images, MR images, moire topographic images, etc. Spinal deformity is a serious problem especially for teenagers and medical doctors inspect moire topographic images of their backs visually for the primary screening. If a subject is normal, the moire image is almost symmetric with respect to the middle line of the subject's back, otherwise it shows asymmetric shape. In this paper, an image analysis technique is described for discriminating suspicious cases from normal in human spinal deformity by recognizing asymmetric moire images of human backs. The principal axes which are sensitive to asymmetry of the moire image are extracted at two parts on a subject's back and their angles are evaluated with respect to the detected middle line of the back. The two angles compose a 2-D feature space and inspected cases are divided into two clusters in the space by a linear discriminant function based on the Mahalanobis distance. Given 120 cases, 60 normal and 60 abnormal, the leave-out method was applied for the recognition and 75% recognition rate was achieved.

• Proceedings of the IEEK Conference
• /
• 2004.08c
• /
• pp.857-861
• /
• 2004

This paper describes preliminary results we have obtained in developing a computer vision system based on active IR illumination for real time gaze tracking for interactive graphic display. Unlike most of the existing gaze tracking techniques, which often require assuming a static head to work well and require a cumbersome calibration process for each person, our gaze tracker can perform robust and accurate gaze estimation without calibration and under rather significant head movement. This is made possible by a new gaze calibration procedure that identifies the mapping from pupil parameters to screen coordinates using the Generalized Regression Neural Networks (GRNN). With GRNN, the mapping does not have to be an analytical function and head movement is explicitly accounted for by the gaze mapping function. Furthermore, the mapping function can generalize to other individuals not used in the training. The effectiveness of our gaze tracker is demonstrated by preliminary experiments that involve gaze-contingent interactive graphic display.