• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.4
• /
• pp.65-74
• /
• 2021

In order to efficiently inspect rapidly increasing old tunnels in many well-developed countries, many inspection methodologies have been proposed using imaging equipment and image processing. However, most of the existing methodologies evaluated their performance on a clean concrete surface with a limited area where other objects do not exist. Therefore, this paper proposes a 6-step framework for tunnel crack detection deep learning model development. The proposed method is mainly based on negative sample (non-crack object) training and Cascade Mask R-CNN. The proposed framework consists of six steps: searching for cracks in images captured from real tunnels, labeling cracks in pixel level, training a deep learning model, collecting non-crack objects, retraining the deep learning model with the collected non-crack objects, and constructing final training dataset. To implement the proposed framework, Cascade Mask R-CNN, an instance segmentation model, was trained with 1561 general crack images and 206 non-crack images. In order to examine the applicability of the trained model to the real-world tunnel crack detection, field testing is conducted on tunnel spans with a length of about 200m where electric wires and lights are prevalent. In the experimental result, the trained model showed 99% precision and 92% recall, which shows the excellent field applicability of the proposed framework.

• Journal of Korea Water Resources Association
• /
• v.55 no.spc1
• /
• pp.1177-1185
• /
• 2022

The water and sewage system is an infrastructure that provides safe and clean water to people. In particular, since the water and sewage pipelines are buried underground, it is very difficult to detect system defects. For this reason, the diagnosis of pipelines is limited to post-defect detection, such as system diagnosis based on the images taken after taking pictures and videos with cameras and drones inside the pipelines. Therefore, real-time detection technology of pipelines is required. Recently, pipeline diagnosis technology using advanced equipment and artificial intelligence techniques is being developed, but AI-based defect detection technology requires a variety of learning data because the types and numbers of defect data affect the detection performance. Therefore, in this study, various defect scenarios are implemented using 3D printing model to improve the detection performance when detecting defects in pipelines. Afterwards, the collected images are performed to pre-processing such as classification according to the degree of risk and labeling of objects, and real-time defect detection is performed. The proposed technique can provide real-time feedback in the pipeline defect detection process, and it would be minimizing the possibility of missing diagnoses and improve the existing water and sewerage pipe diagnosis processing capability.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.1
• /
• pp.31-37
• /
• 2024

In this study, we propose a machine vision-based pedestrian signal detection algorithm that operates efficiently even in computing resource-constrained environments. This algorithm demonstrates high efficiency within limited resources and is designed to minimize the impact of ambient lighting by sequentially applying HSV color space-based image processing, binarization, morphological operations, labeling, and other steps to address issues such as light glare. Particularly, this algorithm is structured in a relatively simple form to ensure smooth operation within embedded system environments, considering the limitations of computing resources. Consequently, it possesses a structure that operates reliably even in environments with low computing resources. Moreover, the proposed pedestrian signal system not only includes pedestrian signal detection capabilities but also incorporates IoT functionality, allowing wireless integration with a web server. This integration enables users to conveniently monitor and control the status of the signal system through the web server. Additionally, successful implementation has been achieved for effectively controlling 50W LED pedestrian signals. This proposed system aims to provide a rapid and efficient pedestrian signal detection and control system within resource-constrained environments, contemplating its potential applicability in real-world road scenarios. Anticipated contributions include fostering the establishment of safer and more intelligent traffic systems.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.205-212
• /
• 2024

This study developed a deep learning model that distinguishes the front (with garnish) and the back (without garnish) surface of the dried semi-finished product (dried bukak) for screening operation before transfter the dried bukak to oil heater using robot's vacuum gripper. For deep learning model training and verification, RGB images for the front and back surfaces of 400 dry bukak that treated by data preproccessing were obtained. YOLO-v5 was used as a base structure of deep learning model. The area, surface information labeling, and data augmentation techniques were applied from the acquired image. Parameters including mAP, mIoU, accumulation, recall, decision, and F1-score were selected to evaluate the performance of the developed YOLO-v5 deep learning model-based surface detection model. The mAP and mIoU on the front surface were 0.98 and 0.96, respectively, and on the back surface, they were 1.00 and 0.95, respectively. The results of binary classification for the two front and back classes were average 98.5%, recall 98.3%, decision 98.6%, and F1-score 98.4%. As a result, the developed model can classify the surface information of the dried bukak using RGB images, and it can be used to develop a robot-automated system for the surface detection process of the dried bukak before deep frying.

• The Korean Journal of Nuclear Medicine
• /
• v.34 no.5
• /
• pp.393-402
• /
• 2000

Purpose: Tc-99m-MIBI (MIBI) and Tc-99m-Tetrofosmin (TF) are commonly used for scintimammog (SMM). We compared the diagnostic ability of SMM using Tc-99m-MIBI and Tc-99m-TF for the diagnosis of breast mass. Materials and Methods: The study subjects were comprised of 123 breast lesior 86 normal breasts of 114 patients who underwent SMM. Bilateral prone images and anterior supine images obtained at 5 minutes and 1 or 3 hours after intravenous injection of 740 MBq of either MIBI or TF. of tumors were not significantly different between the MIBI and TF groups. First, two observers read the SMM without clinical information (1st interpretation), then read again with information about location (2nd interpretation). Sensitivity and specificity of each radiopharmaceutical for the diagnosis of cancer were evaluated in terms of image acquisition time, tumor size, and location. Results: The SMM a good agreement between two observers for 1st and 2nd interpretation, except for TF SMM at 3 hr. first interpretation, the sensitivities at 5 min, 1 hr, and 3 hr were not significantly different between MIBI TF SMM (81.6%, 80.0%, 60.9% in MIBI vs. 88.9%, 80.6%, 42.9% in TF), although the sensitivities of images were significantly lower than 5 min images in both MIBI and TF SMM. The specificity of TF at was superior to that of MIBI (81.5%, 90.0%, 82.9% in MIBI vs. 96.7%, 100%, 90.0% in TF, p<0.01 MIBI TF at 5 min). For the second interpretation with information of mass location, the sensitivities at 3 hr were significantly lower than 5 min images (86.8%, 86.7%, 78.3% in MIBI vs. 88.9%, 93.5%, 57.1% between MIBI and TF SMM. However, there was no significant difference in the specificity (60.0%, 75.0% for MIBI vs. 86.7%, 100%, 100% for TF). MIBI and TF SMM showed lower sensitivities for the with less than 1 cm than tumors with more than 1 cm. However, the location of tumors did not sensitivity and specificity between MIBI and TF SMM. Conclusion: The ability for the differential of breast tumor is similar between MIBI and TF SMM, and delayed image is not necessary. TF may be than MIBI considering the specificity of SMM without clinical information and labeling convenience.

• Nuclear Medicine and Molecular Imaging
• /
• v.40 no.4
• /
• pp.218-227
• /
• 2006

Purpose: The HSV1-tk reporter gene system is the most widely used system because of its advantage that direct monitoring is possible without the introduction of a separate reporter gene in case of HSV1-tk suicide gene therapy. In this study, we investigate the usefulness of the reporter probe (substrate), $9-(4-[^{18}F]Fluoro-3-hydroxymethylbutyl)$guanine ($[^{18}F]FHBG$) for non-invasive reporter gene imaging using PET in HSV1-tk expressing hepatoma model. Materials and Methods: Radiolabeled FHBG was prepared in 8 steps from a commercially available triester. The labeling reaction was carried out by NCA nucleophilic substitution with $K[^{18}F]/K2.2.2.$ in acetonitrile using N2-monomethoxytrityl-9-14-(tosyl)-3-monomethoxytritylmethylbutyl]guanine as a precursor, followed by deprotection with 1 N HCl. Preliminary biological properties of the probe were evaluated with MCA cells and MCA-tk cells transduced with HSV1-tk reporter gene. In vitro uptake and release-out studies of $[^{18}F]FHBG$ were performed, and was analyzed correlation between $[^{18}F]FHBG$ uptake ratio according to increasing numeric count of MCA-tk cells and degree of gene expression. MicroPET scan image was obtained with MCA and MCA-tk tumor bearing Balb/c-nude mouse model. Results: $[^{18}F]FHBG$ was purified by reverse phase semi-HPLC system and collected at around 16-18 min. Radiothemical yield was about 20-25%) (corrected for decay), radiochemical purity was >95% and specific activity was around >55.5 $GBq/{\mu}\;mol$. Specific accumulation of $[^{18}F]FHBG$ was observed in HSV1-tk gene transduced MCA-tk cells but not in MCA cells, and consecutive 1 hour release-out results showed more than 86% of uptaked $[^{18}F]FHBG$ was retained inside of cells. The uptake of $[^{18}F]FHBG$ was showed a highly significant linear correlation ($R^2=0.995$) with increasing percentage of MCA-tk numeric cell count. In microPET scan images, remarkable difference of accumulation was observed for the two type of tumors. Conclusion: $[^{18}F]FHBG$ appears to be a useful as non-invasive PET imaging substrate in HSV1-tk expressing hepatoma model.