• The Journal of the Korea Contents Association
• /
• v.21 no.1
• /
• pp.552-560
• /
• 2021

Currently, the domestic aquaculture industry is pursuing smartization, but it is still proceeding with human subjective judgment in many processes in the aquaculture stage. The prerequisite for the smart aquaculture industry is to effectively grasp the condition of fish in the farm. If real-time monitoring is possible by identifying the number of fish populations, size, pathways, and speed of movement, various forms of automation such as automatic feed supply and disease determination can be carried out. In this study, we proposed an algorithm to identify the state of fish in real time using underwater video data. The fish detection performance was compared and evaluated by applying the latest deep learning-based object detection models, and an algorithm was proposed to measure fish object identification, path tracking, and moving speed in continuous image frames in the video using the fish detection results. The proposed algorithm showed 92% object detection performance (based on F1-score), and it was confirmed that it effectively tracks a large number of fish objects in real time on the actual test video. It is expected that the algorithm proposed in this paper can be effectively used in various smart farming technologies such as automatic feed feeding and fish disease prediction in the future.

• Journal of Biomedical Engineering Research
• /
• v.43 no.5
• /
• pp.341-352
• /
• 2022

Medical image segmentation is the most important task in radiation therapy. Especially, when segmenting medical images, the liver is one of the most difficult organs to segment because it has various shapes and is close to other organs. Therefore, automatic segmentation of the liver in computed tomography (CT) images is a difficult task. Since tumors also have low contrast in surrounding tissues, and the shape, location, size, and number of tumors vary from patient to patient, accurate tumor segmentation takes a long time. In this study, we propose a method algorithm for automatically segmenting the liver and tumor for this purpose. As an advantage of setting the boundaries of the tumor, the liver and tumor were automatically segmented from the CT image using the 2D CoordConv DeepLab V3+ model using the CoordConv layer. For tumors, only cropped liver images were used to improve accuracy. Additionally, to increase the segmentation accuracy, augmentation, preprocess, loss function, and hyperparameter were used to find optimal values. We compared the CoordConv DeepLab v3+ model using the CoordConv layer and the DeepLab V3+ model without the CoordConv layer to determine whether they affected the segmentation accuracy. The data sets used included 131 hepatic tumor segmentation (LiTS) challenge data sets (100 train sets, 16 validation sets, and 15 test sets). Additional learned data were tested using 15 clinical data from Seoul St. Mary's Hospital. The evaluation was compared with the study results learned with a two-dimensional deep learning-based model. Dice values without the CoordConv layer achieved 0.965 ± 0.01 for liver segmentation and 0.925 ± 0.04 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.927 ± 0.02 for liver division and 0.903 ± 0.05 for tumor division. The dice values using the CoordConv layer achieved 0.989 ± 0.02 for liver segmentation and 0.937 ± 0.07 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.944 ± 0.02 for liver division and 0.916 ± 0.18 for tumor division. The use of CoordConv layers improves the segmentation accuracy. The highest of the most recently published values were 0.960 and 0.749 for liver and tumor division, respectively. However, better performance was achieved with 0.989 and 0.937 results for liver and tumor, which would have been used with the algorithm proposed in this study. The algorithm proposed in this study can play a useful role in treatment planning by improving contouring accuracy and reducing time when segmentation evaluation of liver and tumor is performed. And accurate identification of liver anatomy in medical imaging applications, such as surgical planning, as well as radiotherapy, which can leverage the findings of this study, can help clinical evaluation of the risks and benefits of liver intervention.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2003.09a
• /
• pp.44-44
• /
• 2003

As a basic measurement tool in the areas of animal models of human disease, gene expression and therapy, and drug discovery and development, small animal PET imaging is being used increasingly. An ideal small animal PET should have high sensitivity and high and uniform resolution across the field of view to achieve high image quality. However, the combination of long narrow pixellated crystal array and small ring diameter of small animal PET leads to the degradation of spatial resolution for the source located at off center. This degradation of resolution can be improved by determining the depth of interaction (DOI) in the crystal and by taking into account the information in sorting the coincident events. Among a number of 001 identification schemes, dual layer phsowich detector has been widely investigated by many research groups due to its practicability and effectiveness on extracting DOI information. However, the effects of each crystal length composing dual layer phoswich detector on DOI measurements and image qualities were not fully characterized. In order to minimize the DOI effect, the length of each layer of phoswich detector should be optimized. The aim of this study was to perform simulations using a simulation tool, GATE to design the optimum lengths of crystals composing a dual layer phoswich detector. The simulated small PET system employed LSO front layer LuYAP back layer phoswich detector modules and the module consisted of 8${\times}$8 arrays of dual layer crystals with 2 mm ${\times}$ 2 mm sensitive area coupled to a Hamamatsu R7600 00 M64 PSPMT. Sensitivities and variation of radial resolutions were simulated by varying the length of LSO front layer from 0 to 10 mm while the total length (LSO + LuYAP) was fixed to 20 mm for 10 cm diameter ring scanner. The radial resolution uniformity was markedly improved by using DOI information. There existed the optimal lengths of crystal layers to minimize the variation of radial resolutions. In 10 cm ring scanner configuration, the radial resolution was kept below 3.4 mm over 8 cm FOV while the sensitivity was higher than 7.4% for LSO 5 mm : LuYAP 15 mm phoswich detector. In this study, the optimal length of dual layer phoswich detector was derived to achieve high and uniform radial resolution.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.125-137
• /
• 2021

The number of CCTV installed in Korea is over 1.3 million, increasing by more than 15% annually. However, due to the limited budget compared to the installation demand, the infrastructure is composed of 500,000 pixel low-quality CCTV, and there is a limits on identification of objects in the video. Public CCTV has high utility in various fields such as crime prevention, traffic information collection (control), facility management, and fire prevention. Especially, since installed in high height, it works as its role in solving diverse crime and is in increasing trend. However, the current public CCTV field is operated with potential problems such as inability to identify due to environmental factors such as fog, snow, and rain, and the low-quality of collected images due to the installation of low-quality CCTV. Therefore, in this study, in order to remove the typical low-quality elements of public CCTV, the method of attenuating scattered light in the image caused by dust, water droplets, fog, etc and algorithm application method which uses deep-learning algorithm to improve input video into videos over quality over 4K are suggested.

• Tunnel and Underground Space
• /
• v.33 no.6
• /
• pp.508-518
• /
• 2023

This paper presents a new approach for the automatic mapping of discontinuities in a tunnel face based on its 3D digital model reconstructed by LiDAR scan or photogrammetry techniques. The main idea revolves around the identification of discontinuity areas in the 3D digital model of a tunnel face by segmenting its 2D projected images using a deep-learning semantic segmentation model called U-Net. The proposed deep learning model integrates various features including the projected RGB image, depth map image, and local surface properties-based images i.e., normal vector and curvature images to effectively segment areas of discontinuity in the images. Subsequently, the segmentation results are projected back onto the 3D model using depth maps and projection matrices to obtain an accurate representation of the location and extent of discontinuities within the 3D space. The performance of the segmentation model is evaluated by comparing the segmented results with their corresponding ground truths, which demonstrates the high accuracy of segmentation results with the intersection-over-union metric of approximately 0.8. Despite still being limited in training data, this method exhibits promising potential to address the limitations of conventional approaches, which only rely on normal vectors and unsupervised machine learning algorithms for grouping points in the 3D model into distinct sets of discontinuities.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.3
• /
• pp.44-51
• /
• 2009

This paper addresses a face verification method using the nonlinear composite filter. This face verification process can be simple and speedy because it does not require any reprocessing such as face detection, alignment or cropping. The optimum nonlinear composite filter is derived by minimizing the output energy due to additive noise and an input scene while maintaining the outputs of training images constant. The filter is equipped with the discrimination capability and the robustness to additive noise by minimizing the outputs of the input scene and the noise, respectively. We build the nonlinear composite filter with two training images and compare the filter with the conventional synthetic discriminant function (SDF) filter. The receiver operating characteristics (ROC) curves are presented as a metric for the performance evaluation. According to the experimental results the optimum nonlinear composite filter is shown to be a robust scheme for face verification in low resolution and noise environments.

• The Journal of Engineering Geology
• /
• v.10 no.3
• /
• pp.237-245
• /
• 2000

This study was for characterizing the engineering geological properties of Moryang Fault, and providing the basic data for tunnel design. Land-sat image analysis, geologic surveys, resistivity prospecting and 3-dimensional analysis for results of resistivity prospecting, core boring, mineralogical identification and chemical analysis for the bedrock, and K-Ar age dating for fault clay were carried out for the study of Moryang Fault which is located at Duckhyunri Sangbukmyun Uljinkun Ulsan metropolis. As a result of the study, it was shown that strike/dip was N20-3$0^{\circ}C$E/70-9$0^{\circ}C$NW, width of fault ranged from 20 to 60m(maximum 80m), and depth was more than 50m. K-Ar age dating results of fault clay were 5,700$\pm$1.129Ma and 1,900$\pm$0.380Ma. Hydraulic fracturing test results showed the principal stress direction similar to the strike of Moryang Fault.

• The KIPS Transactions:PartD
• /
• v.19D no.3
• /
• pp.221-228
• /
• 2012

This paper proposes a new forging work-in-process control system that guarantees independency of a specific device and provides cost-effectiveness. Until now, much research has been studied on improving the process productivity through efficient work-in-process or inventory controls. Especially, incorporating various IT technologies such as barcode, RFID, and image recognition has been done. However, those approaches cause many problems due to the characteristics of the forging work-in-process control environment. To overcome the limitations of the existing approaches, this paper proposes a novel forging work-in-process control system. The proposed system in this paper identifies and precisely manages positions of objects by using GPS information of smart mobile devices. Therefore, identification tags as well as specific devices for reading the tags do not been required. It resolves the problems of the previous approaches and enhances the productivity of the overall forging work-in-process control process.

• Journal of Advanced Navigation Technology
• /
• v.24 no.3
• /
• pp.224-231
• /
• 2020

An optical tracking plays an important role for measurement operation, as it is responsible for low altitude measurements that are difficult to obtain with radar systems. Since the existing optical tracking systems have not been developed in the proving ground itself so far, it is difficult to modify them to fit the environment of the proving ground. Also, they are designed as a vehicle-mounted type, so there is a limitation in selecting an optimal site. The in-house developed small optical tracking system is designed with a simple configuration to overcome these shortcomings and makes it possible for operators to operate the system at any place in the proving ground. In addition, there has been a need of developing small optical trackers by ourselves to be prepared for future research so that artificial intelligence (AI) can be applied to the optical tracking systems. In this paper, we described the design concept of the small optical tracker, the configuration of the components to implement the basic tracking function, and showed the results of the simulation to set the configuration of the equipment according to the characteristics of the flight targets.

• 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.