• Smart Structures and Systems
• /
• v.24 no.5
• /
• pp.669-681
• /
• 2019

Bridge collapses may deliver a huge impact on our society in a very negative way. Out of many reasons why bridges collapse, poor maintenance is becoming a main contributing factor to many recent collapses. Furthermore, the aging of bridges is able to make the situation much worse. In order to prevent this unwanted event, it is indispensable to conduct continuous bridge monitoring and timely maintenance. Visual inspection is the most widely used method, but it is heavily dependent on the experience of the inspectors. It is also time-consuming, labor-intensive, costly, disruptive, and even unsafe for the inspectors. In order to address its limitations, in recent years increasing interests have been paid to the use of unmanned aerial vehicles (UAVs), which is expected to make the inspection process safer, faster and more cost-effective. In addition, it can cover the area where it is too hard to reach by inspectors. However, this strategy is still in a primitive stage because there are many things to be addressed for real implementation. In this paper, a typical procedure of bridge inspection using UAVs consisting of three phases (i.e., pre-inspection, inspection, and post-inspection phases) and the detailed tasks by phase are described. Also, three major challenges, which are related to a UAV's flight, image data acquisition, and damage identification, respectively, are identified from a practical perspective (e.g., localization of a UAV under the bridge, high-quality image capture, etc.) and their possible solutions are discussed by examining recently developed or currently developing techniques such as the graph-based localization algorithm, and the image quality assessment and enhancement strategy. In particular, deep learning based algorithms such as R-CNN and Mask R-CNN for classifying, localizing and quantifying several damage types (e.g., cracks, corrosion, spalling, efflorescence, etc.) in an automatic manner are discussed. This strategy is based on a huge amount of image data obtained from unmanned inspection equipment consisting of the UAV and imaging devices (vision and IR cameras).

• Korean Journal of Artificial Intelligence
• /
• v.5 no.2
• /
• pp.15-25
• /
• 2017

Recently, technologies are being developed to recognize and authenticate users using bioinformatics to solve information security issues. Biometric information includes face, fingerprint, iris, voice, and vein. Among them, face recognition technology occupies a large part. Face recognition technology is applied in various fields. For example, it can be used for identity verification, such as a personal identification card, passport, credit card, security system, and personnel data. In addition, it can be used for security, including crime suspect search, unsafe zone monitoring, vehicle tracking crime.In this thesis, we conducted a study to recognize faces by detecting the areas of the face through a computer webcam. The purpose of this study was to contribute to the improvement in the accuracy of Recognition of Face Based on CNN Algorithms. For this purpose, We used data files provided by github to build a face recognition model. We also created data using CNN algorithms, which are widely used for image recognition. Various photos were learned by CNN algorithm. The study found that the accuracy of face recognition based on CNN algorithms was 77%. Based on the results of the study, We carried out recognition of the face according to the distance. Research findings may be useful if face recognition is required in a variety of situations. Research based on this study is also expected to improve the accuracy of face recognition.

• Journal of IKEEE
• /
• v.23 no.2
• /
• pp.642-651
• /
• 2019

One of the most important research topics on intelligent transportation systems in recent years is detecting and recognizing a license plate. The license plate has a unique identification data on vehicle information. The existing vehicle traffic control system is based on a stop and uses a loop coil as a method of vehicle entrance/exit recognition. The method has the disadvantage of causing traffic jams and rising maintenance costs. We propose to exploit differential image of camera background instead of loop coil as an entrance/exit recognition method of vehicles. After entrance/exit recognition, we detect the candidate images of license plate using the morphological characteristics. The license plate can finally be detected using SVM(Support Vector Machine). Letter and numbers of the detected license plate are recognized using CNN(Convolutional Neural Network). The experimental results show that the proposed algorithm has a higher recognition rate than the existing license plate recognition algorithm.

• Journal of Ocean Engineering and Technology
• /
• v.33 no.3
• /
• pp.289-299
• /
• 2019

Various sizes of ROVs are being utilized in offshore industrial, scientific, and military applications all around the world. Because of innovative developments in science and technology, image acquisition devices such as sonar devices and cameras have been reduced in size and their performance has been improved. Thus, we can expect better accuracy and higher resolution even in the case of exploration using a small ROV. The purpose of this paper is to prepare a standard procedure for the identification of unidentified hazardous materials found during the National Oceanographic Survey. In this paper, we propose an IDEF (Integrated DEFinition) method modeling technique to identify unidentified targets using a small ROV. In accordance with the proposed procedure, an ROV survey was carried out on target No.16 with a four-ton-class fishing boat as a support vessel on September 18th of 2018 in the sea near Daebu Island. Unidentified targets, which were not known by the multi-beam data obtained from the ship, could be identified as concrete pipes by analyzing the HD camera and high-resolution sonar images acquired by the ROV. The whole proposed procedure could be verified, and the survey with the small ROV required about 10 days to identify the target in one place.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.6
• /
• pp.33-38
• /
• 2016

Understanding of current features of collapsed buildings, terrain, and other infrastructures is a critical issue for disaster site managers. On the other hand, a comprehensive site investigation of current location of survivors buried under the remains of a building is a difficult task for disaster managers due to the difficulties in acquiring the various information on the disaster sites. To overcome these circumstances, such as large disaster sites and limited capability of rescue workers, this study makes use of a drone (unmanned aerial vehicle) to effectively obtain current image data from large disaster areas. The framework of 3D model reconstruction of disaster sites using aerial imagery acquired by drones was also presented. The proposed methodology is expected to assist fire fighters and workers on disaster sites in making a rapid and accurate identification of the survivors under collapsed buildings.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.13 no.4
• /
• pp.55-63
• /
• 2007

The Group Digital Surveillance System for Fishery Safety and Security (GDSS-F2S) is to provide the target tracking information and the target identification information in order to secure an huge aquaculture farm-field from a thief. The two information, however, is not enough to indict the thief due to the lack of lawful evidences for the crime actions. To overcome this problem, we consider the target image information as one of solutions after discussion with the effective countermeasure tools for the crime actions with scenario-based analysis according to the geological feature of aquaculture farm-field. To capture the real-time image for the trespassing targets in the aquaculture farm-field area, we developed the image capture system which is consists of ultra sensitive CCD(Charge-Coupled Device) camera with 0.0001 Lux and supplementary devices. As results from the field tests for GDSS-F2S with image capture system, the high definite images of the vehicle number plate and shape, person's actions and features are obtainable not only day time but also very dark night without moon light. Thus it is cleary known that the improved GDSS-F2S with image capture system can provide much enough lawful evidences for the crime actions of targets.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.7
• /
• pp.622-629
• /
• 2019

Recently, the government is taking new approaches to change the fact that the accident rate and accident death rate of the construction industry account for a high percentage of the whole industry. Especially, it is investing heavily in the development of construction technology that is fused with ICT technology in line with the current trend of the 4th Industrial Revolution. In order to cope with this situation, this paper proposed a concept to recognize and share the work situation information between the construction machine driver and the surrounding worker to enhance the safety in the place where construction machines are operated. In order to realize the part of the concept, we applied image processing technology using camera based on artificial intelligence to earth-moving work. Especially, we implemented an algorithm that can recognize the surrounding worker's circumstance and identify the risk situation through the experiment using the compaction equipment. and image processing algorithm based on YOLO-v3. This algorithm processes 15.06 frames per second in video and can recognize danger situation around construction machine with accuracy of 90.48%. We will contribute to the prevention of safety accidents at the construction site by utilizing this technology in the future.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.93-101
• /
• 2024

Accurate field crop classification is essential for various agricultural applications, yet existing methods face challenges due to diverse crop types and complex field conditions. This study aimed to address these issues by combining support vector machine (SVM) models with multi-seasonal unmanned aerial vehicle (UAV) images, texture information extracted from Gray Level Co-occurrence Matrix (GLCM), and RGB spectral data. Twelve high-resolution UAV image captures spanned March-October 2021, while field surveys on three dates provided ground truth data. We focused on data from August (-A), September (-S), and October (-O) images and trained four support vector classifier (SVC) models (SVC-A, SVC-S, SVC-O, SVC-AS) using visual bands and eight GLCM features. Farm maps provided by the Ministry of Agriculture, Food and Rural Affairs proved efficient for open-field crop identification and served as a reference for accuracy comparison. Our analysis showcased the significant impact of hyperparameter tuning (C and gamma) on SVM model performance, requiring careful optimization for each scenario. Importantly, we identified models exhibiting distinct high-accuracy zones, with SVC-O trained on October data achieving the highest overall and individual crop classification accuracy. This success likely stems from its ability to capture distinct texture information from mature crops.Incorporating GLCM features proved highly effective for all models,significantly boosting classification accuracy.Among these features, homogeneity, entropy, and correlation consistently demonstrated the most impactful contribution. However, balancing accuracy with computational efficiency and feature selection remains crucial for practical application. Performance analysis revealed that SVC-O achieved exceptional results in overall and individual crop classification, while soybeans and rice were consistently classified well by all models. Challenges were encountered with cabbage due to its early growth stage and low field cover density. The study demonstrates the potential of utilizing farm maps and GLCM features in conjunction with SVM models for accurate field crop classification. Careful parameter tuning and model selection based on specific scenarios are key for optimizing performance in real-world applications.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.67 no.4
• /
• pp.274-284
• /
• 2022

To use kenaf (Hibiscus cannabinus L.) as a fiber and livestock feed, a high-yielding variety needs to be identified. For this, accurate phenotyping of plant height is required for this breeding purpose due to the strong relationship between plant height and yield. Plant height can be estimated using RGB images from unmanned aerial vehicles (UAV-RGB) and photogrammetry based on Structure from Motion (SfM) algorithms. In kenaf, accurate measurement of height is limited because kenaf stems have high flexibility and its height is easily affected by wind, growing up to 3 ~ 4 m. Therefore, we aimed to identify a method suitable for the accurate estimation of plant height of kenaf and investigate the feasibility of using the UAV-RGB-derived plant height map. Height estimation derived from UAV-RGB was improved using multi-point calibration against the five different wooden structures with known heights (30, 60, 90, 120, and 150 cm). Using the proposed method, we analyzed the variation in temporal height of 23 kenaf cultivars. Our results demontrated that the actual and estimated heights were reliably comparable with the coefficient of determination (R²) of 0.80 and a slope of 0.94. This method enabled the effective identification of cultivars with significantly different heights at each growth stages.