• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.237-250
• /
• 2022

Structural health monitoring (SHM) plays an important role in ensuring the safety and functionality of critical civil infrastructure. In recent years, numerous researchers have conducted studies to develop computer vision and machine learning techniques for SHM purposes, offering the potential to reduce the laborious nature and improve the effectiveness of field inspections. However, high-quality vision data from various types of damaged structures is relatively difficult to obtain, because of the rare occurrence of damaged structures. The lack of data is particularly acute for fatigue crack in steel bridge girder. As a result, the lack of data for training purposes is one of the main issues that hinders wider application of these powerful techniques for SHM. To address this problem, the use of synthetic data is proposed in this article to augment real-world datasets used for training neural networks that can identify fatigue cracks in steel structures. First, random textures representing the surface of steel structures with fatigue cracks are created and mapped onto a 3D graphics model. Subsequently, this model is used to generate synthetic images for various lighting conditions and camera angles. A fully convolutional network is then trained for two cases: (1) using only real-word data, and (2) using both synthetic and real-word data. By employing synthetic data augmentation in the training process, the crack identification performance of the neural network for the test dataset is seen to improve from 35% to 40% and 49% to 62% for intersection over union (IoU) and precision, respectively, demonstrating the efficacy of the proposed approach.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.2
• /
• pp.160-167
• /
• 2023

This study focuses on the development of a Last-Mile delivery service using unmanned vehicles to deliver goods directly to the end consumer utilizing drones to perform autonomous delivery missions and an image-based precision landing algorithm for handoff to a robot in an intermediate facility. As the logistics market continues to grow rapidly, parcel volumes increase exponentially each year. However, due to low delivery fees, the workload of delivery personnel is increasing, resulting in a decrease in the quality of delivery services. To address this issue, the research team conducted a study on a Last-Mile delivery service using unmanned vehicles and conducted research on the necessary technologies for drone-based goods transportation in this paper. The flight scenario begins with the drone carrying the goods from a pickup location to the rooftop of a building where the final delivery destination is located. There is a handoff facility on the rooftop of the building, and a marker on the roof must be accurately landed upon. The mission is complete once the goods are delivered and the drone returns to its original location. The research team developed a mission planning algorithm to perform the above scenario automatically and constructed an algorithm to recognize the marker through a camera sensor and achieve a precision landing. The performance of the developed system has been verified through multiple trial operations within ETRI.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.463-465
• /
• 2021

Currently, the inspection method printed on food packages and boxes is to sample only a few products and inspect them with human eyes. Such a sampling inspection has the limitation that only a small number of products can be inspected. Therefore, accurate inspection using a camera is required. This paper proposes a deep learning object recognition technology model, which is an artificial intelligence technology, as a method for detecting the defects of expiration date printed on the product packaging. Using the Faster R-CNN (region convolution neural network) model, the color images, converted gray images, and converted binary images of the printed expiration date are trained and then tested, and each detection rates are compared. The detection performance of expiration date printed on the package by the proposed method showed the same detection performance as that of conventional vision-based inspection system.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.66 no.4
• /
• pp.27-39
• /
• 2024

Soil texture is determined by the proportions of sand, silt, and clay within the soil, which influence characteristics such as porosity, water retention capacity, electrical conductivity (EC), and pH. Traditional classification of soil texture requires significant sample preparation including oven drying to remove organic matter and moisture, a process that is both time-consuming and costly. This study aims to explore an alternative method by developing an AI model capable of predicting soil texture from images of pre-sorted soil samples using computer vision and deep learning technologies. Soil samples collected from agricultural fields were pre-processed using sieve analysis and the images of each sample were acquired in a controlled studio environment using a smartphone camera. Color distribution ratios based on RGB values of the images were analyzed using the OpenCV library in Python. A convolutional neural network (CNN) model, built on PyTorch, was enhanced using Digital Image Processing (DIP) techniques and then trained across nine distinct conditions to evaluate its robustness and accuracy. The model has achieved an accuracy of over 80% in classifying the images of pre-sorted soil samples, as validated by the components of the confusion matrix and measurements of the F1 score, demonstrating its potential to replace traditional experimental methods for soil texture classification. By utilizing an easily accessible tool, significant time and cost savings can be expected compared to traditional methods.

• Journal of Korea Multimedia Society
• /
• v.16 no.2
• /
• pp.254-268
• /
• 2013

This paper presents an augmented reality (AR) based rehabilitation exercise system to enhance the motor function of the hands for the paretic/hemi-paretic patient. The existing rehabilitation systems rely on mechanical apparatus for palsy rehabilitation, but we aim to use the rehabilitation system at home with easy configuration and minimized equipment by the computer vision based approach. The proposed method evaluates the interaction status of the fingertip action by using the position and the contact of the fingertip markers. We obtain the 2D positions of the fingertip markers from a single camera, and then transform the 3D positions from the calibrated camera space by using an ARToolKit marker. We adopt simple geometric calculation by the conversion of the 2D interest points into the 3D interaction points for the simple interactive task in AR environment. Some experimental results show that the proposed method is practical and simply applicable to the applications with personal AR interaction.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.345-354
• /
• 2005

A mobile manipulator - a serial connection of a mobile robot and a task robot - is a very useful system to achieve various tasks in dangerous environment, because it has the higher performance than a fixed base manipulator in terms of its operational workspace size as well as efficiency. A method for estimating the position of an object in the Cartesian coordinate system based upon the geometrical relationship between the image captured by 2-DOF active camera mounted on mobile robot and the real object, is proposed. With this Position estimation, a method of determining an optimal path for the mobile manipulator from the current position to the position of object estimated by the image information using homogeneous matrices. Finally, the corresponding joint parameters to make the desired displacement are calculated to capture the object through the control of a manipulator. The effectiveness of proposed method is demonstrated by the simulation and real experiments using the mobile manipulator.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.18 no.3
• /
• pp.285-293
• /
• 2009

Thermal infrared cameras have been conducted actively in various application areas, such as military, medical service, industries and cars. Because of their characteristic of sensing the radiant heat emitted from subjects in the range of long-wavelength($3{\sim}5{\mu}m$ or $8{\sim}12{\mu}m$), and of materializing a vision system, when general optics materials are used, they don't react to the light in the range of long-wavelength, and can't display their optic functions. Therefore, the materials with the feature of higher refractive index, reacting to the range of long-wavelength, are to be used. The kinds of materials with the characteristic of higher refractive index are limited, and their features are close to those of metals. Because of these metallic features, the existing producing method of optical systems were direct manufacturing method using grinding method or CAD/CAM, which put limit on productivity and made it difficult to properly cope with the increasing demand of markets. GASIR, a material, which can be molded easily, was selected among infrared ray optics materials in this study, and the optical system was designed with two Aspheric lenses. Because the lenses are molded in the environment of high temperature and high pressure, they require a special metallic pattern. The metallic pattern was produced with materials with ultra hardness that can stand high temperature and high pressure. As for the lens mold, GMP(Glass Molding Press) of the linear transfer method was used in order to improve the productivity of optical systems for thermal infrared cameras, which was the goal of this paper.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.11
• /
• pp.1088-1095
• /
• 2009

In this paper, we describe the reorientation method of distorted road sign by using projection transformation for improving recognition rate of road sign. RSR (Road Sign Recognition) is one of the most important topics for implementing driver assistance in intelligent transportation systems using pattern recognition and vision technology. The RS (Road Sign) includes direction of road or place name, and intersection for obtaining the road information. We acquire input images from mounted camera on vehicle. However, the road signs are often appeared with rotation, skew, and distortion by perspective camera. In order to obtain the correct road sign overcoming these problems, projection transformation is used to transform from 4 points of image coordinate to 4 points of world coordinate. The 4 vertices points are obtained using the trajectory as the distance from the mass center to the boundary of the object. Then, the candidate areas of road sign are transformed from distorted image by using homography transformation matrix. Internal information of reoriented road signs is segmented with arrow and the corresponding indicated place name. Arrow area is the largest labeled one. Also, the number of group of place names equals to that of arrow heads. Characters of the road sign are segmented by using vertical and horizontal histograms, and each character is recognized by using SAD (Sum of Absolute Difference). From the experiments, the proposed method has shown the higher recognition results than the image without reorientation.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.18 no.1
• /
• pp.137-145
• /
• 2004

In this paper, a new algorithm for the segmentation of the multi moving objects at the 3 dimension space and the method of measuring the distance from the camera to the moving object by using stereo video monitoring system is proposed. It get the input image of left and right from the stereo video monitoring system, and the area of the multi moving objects segmented by using adaptive threshold and PRA(pixel recursive algorithm). Each of the object segmented by window mask, then each coordinate value and stereo disparity of the multi moving objects obtained from the window masks. The distance of the multi moving objects can be calculated by this disparity, the feature of the stereo vision system and the trigonometric function. From the experimental results, the error rate of a distance measurement be existed within 7.28％, therefore, in case of implementation the proposed algorithm, the stereo security system, the automatic moving robot system and the stereo remote control system will be applied practical application.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.1
• /
• pp.142-152
• /
• 2016

GPS is not able to be used for indoor positioning and currently most of techniques emerging to overcome the limit of GPS utilize private wireless networks. However, these methods require high costs for installation and maintenance, and they are inappropriate to be used in the place where precise positioning is needed as in indoor parking lots. This paper proposes a vehicular indoor positioning method based on QR-code recognition. The method gets an absolute coordinate through QR-code scanning, and obtain the location (an relative coordinate) of a black-box camera using the tilt and roll angle correction through affine transformation, scale transformation, and trigonometric function. Using these information of an absolute coordinate and an relative one, the precise position of a car is estimated. As a result, average error of 13.79cm is achieved and it corresponds to just 27.6% error rate in contrast to 50cm error of the recent technique based on wireless networks.