• Journal of Korea Multimedia Society
• /
• v.22 no.2
• /
• pp.136-145
• /
• 2019

The crowded environment of a domestic pig farm is highly vulnerable to the spread of infectious diseases such as foot-and-mouth disease, and studies have been conducted to automatically analyze behavior of pigs in a crowded pig farm through a video surveillance system using a camera. Although it is required to correctly separate occluding pigs for tracking each individual pigs, extracting the boundaries of the occluding pigs fast and accurately is a challenging issue due to the complicated occlusion patterns such as X shape and T shape. In this study, we propose a fast and accurate method to separate occluding pigs not only by exploiting the characteristics (i.e., one of the fast deep learning-based object detectors) of You Only Look Once, YOLO, but also by overcoming the limitation (i.e., the bounding box-based object detector) of YOLO with the test-time data augmentation of rotation. Experimental results with two-pigs occlusion patterns show that the proposed method can provide better accuracy and processing speed than one of the state-of-the-art widely used deep learning-based segmentation techniques such as Mask R-CNN (i.e., the performance improvement over Mask R-CNN was about 11 times, in terms of the accuracy/processing speed performance metrics).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.3055-3062
• /
• 2014

3D integral imaging technique with an active mask is capable of displaying real 3D images with high resolution in space. In this paper, we present a novel 3D/2D convertible integral imaging display system using an active mask. For the proposed method, the principles of 3D, 2D, and 3D/2D composed operations are explained according to the displayed images through two LCD panels. In 3D mode, the elemental images and the mask images are displayed in two display panels. On the other hand, the light source image and 2D image are displayed in 2D mode. In addition, 3D/2D mode is obtained using the spatial separation for 3D and 2D modes. To show the feasibility of the proposed method, we carry out the preliminary experiments and present the optical results.

• Resources Recycling
• /
• v.17 no.6
• /
• pp.43-49
• /
• 2008

In this study, a scrap sorting system using a color recognition method has been developed to automatically sort out specified materials from a mixture, and its application as been examined in the separation of Cu and other non-ferrous metal parts from a mixture of iron scraps. The system is composed of three parts; measuring, conveying and ejecting parts. The color of scrap surface is recognized by the measuring part consisting of a line-scan camera, light sources and a frame grabber. The recognition is program-controlled by a image processing algorithms, and thus only the scrap part of designated color is separated by the use of air nozzles. In addition, the light system is designed to meet a high speed of sorting process with a frequency-variable inverter and the air nozzled ejectors are to be operated by an I/O interface communication with a hardware controller. In the functional tests of the system, its efficiency in the recognition of Cu scraps from its mixture with Fe ones reaches to more than 90%, and that in the separation more than 80% at a conveying speed of 25 m/min. Therefore, it is expected that the system can be commercialized in the industry of shredder makers if a high efficiency ejecting system is realized.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2010.04a
• /
• pp.383-384
• /
• 2010

The control surface on a ship is to control the motion of it in forward and backward states. In this paper, the measured results has been compared with each other to predict the backward flow characteristics of the single rudder's 2-dimensional section at $Re=2.0\times10^4$ using 2-frame grey level cross correlation PIV method especially, The separation region appears at 10 to 20 degrees angle of attack in a forward state. The separation point and boundary layer demonstrate in the same angle of attack compared it with the forward states.

• Membrane Journal
• /
• v.26 no.6
• /
• pp.449-457
• /
• 2016

In this study, polyvinylidene fluoride (PVDF) membrane with excellent mechanical properties and chemical resistance was prepared and characterized for the application of water treatment. Dibutyl-phthalate (DBP) was used as a diluent for making a membranes through temperature induced phase separation (TIPS) method, and the crystallization temperature, melting point, cloud point and SEM image were observed with different ratio of diluent in polymer/diluent mixture. The crystallization temperature and melting point increased proportionally with the content of polymer, while the cloud point temperature decreased. Finally, it was confirmed that stable membrane could be manufactured at a polymer content of 62 wt% and a temperature $125^{\circ}C$ using the phase diagram of PVDF/DBP mixtures with temperatures.

• Proceedings of KOSOMES biannual meeting
• /
• 2006.11a
• /
• pp.53-58
• /
• 2006

Along with the development of costal engineering, various type of breakwaters have been built. The main purpose of breakwaters are to provide harbour protection against waves, to stabilize beaches against erosion due to large wave action, and to provide for temporary wave protection for installation on or under water surface. This paper an application example of PIV system for analyzing the flow of Floating Breakwater with double barriers. We introduce an analysis method to predict the characteristics of flow around the neighboring fields of Floating Breakwater with double barriers in order to develop a high performance model. Flow visualization has conducted in circulating water channel by a high speed camera and etc. Flowing phenomenon according to velocity distribution and flow separation around the breakwater with double barriers were obtained by 2-D PIV system.

• Fashion & Textile Research Journal
• /
• v.17 no.1
• /
• pp.11-21
• /
• 2015

This study analyzed the expressive phenomenon of a blurred boundary in fashion jewelry focused on the relationship between fashion jewelry and costume or fashion jewelry and body. The method of this study was to analyze recent documentaries about jewelry theories in regards to 607 cases of fashion jewelry design in fashion books, fashion magazines, fashion internet sites from 2000 to 2014. The results were: First, phenomenon of blurred boundary between fashion jewelry and costume was expressed in a see-through wear form made of luxury material (gold and diamond) or paste material, a similar form (like fashion accessories made of crystal, bids, and gold chain), an integration of fashion accessories and jewelry, and an attached jewelry on fashion accessories. It reflected a rearrangement of conventional relationships, a blurred relation of function and meaning, dissolution of jewelry form stereotypes, jewelry styling, a harmony of function and decoration, and an alteration to the central role of a fashion image. Second, the phenomenon of a blurred boundary between fashion jewelry and body was expressed in a body organ wrapping, body surface adhesion and sculptural jewelry based on body pose. It reflected a separation from conventional space of jewelry expression, a realization of mystery and fantastic, an expression of new body surface and a blurred boundaries of fashion jewelry and body art. Aesthetic characteristics were analyzed into metaphor and integration by separation from the conventional relationship of fashion jewelry and costume or fashion jewelry and body.

• Journal of Climate Change Research
• /
• v.7 no.3
• /
• pp.249-256
• /
• 2016

Porous $Al_2O_3$ hollow fiber membranes were successfully prepared by dry-wet spinning/sintering method. The SEM image shows that the $Al_2O_3$ hollow fiber membrane consists mostly of sponge pore structure. The contact angle and the breakthrough pressure were $126^{\circ}$ and 1.91 bar, respectively. This results indicate that the $Al_2O_3$ hollow fiber membranes were successfully modified to hydrophobic surface. The hydrophobic modified $Al_2O_3$ hollow fiber membranes were assembled into a membrane contactor system to separate $CO_2$ from a model gas mixture of the flue gas at elevated gas velocity. The $CO_2$ absorption flux was enhanced when the gas velocity increased from $1{\times}10^{-3}$ to $6{\times}10^{-3}$ m/s. Whereas the $CO_2$ absorption flux was decreased with the number of hollow fiber membrane of a module because of the concentration polarization. Furthermore, we developed an lab-scale $Al_2O_3$ hollow fiber membrane contactor modules and their system (i.e., $CO_2$ absorption using the $Al_2O_3$ membrane and monoethanolamine (MEA)) that could dispose of over $0.02Nm^3/h$ mixture gas (15% $CO_2$) with the removal efficiency higher than 95%. The results can be useful in a field of the membrane contactor for $CO_2$ separation, helping to design and extend a equipment.

• Journal of Radiation Protection and Research
• /
• v.44 no.2
• /
• pp.53-63
• /
• 2019

Background: As neutron fields are always accompanied by gamma rays, it is essential to distinguish neutrons from gamma rays in the detection of neutrons. Neutrons and gamma rays can be separated by pulse shape discrimination (PSD) methods. Recently, we performed characterization of a stilbene scintillator detector and an EJ-301 liquid scintillator detector with a high-speed digitizer DT5730 and investigated optimized PSD variables for both detectors. This study is for providing a basis for developing fast neutron/gamma-ray dual-particle imager. Materials and Methods: We conducted PSD experiments using stilbene scintillator and EJ-301 liquid scintillator and evaluated neutron and gamma ray discriminability of each PSD method with a $^{137}Cs$ gamma source and a $^{252}Cf$ neutron source. We implemented digital signal processing techniques to apply two PSD methods - the charge comparison (CC) method and the constant time discrimination (CTD) method - to distinguish neutrons from gamma rays. We tried to find optimized PSD variables giving the best discriminability in a given experimental condition. Results and Discussion: For the stilbene scintillator detector, the charge comparison method and the constant time discrimination method both delivered the PSD FOM values of 1.7. For the EJ-301 liquid scintillator detector, both PSD methods delivered the PSD FOM values of 1.79. With the same PSD variables, PSD performance was excellent in $300{\pm}100keVee$, $500{\pm}100keVee$, and $700{\pm}100keVee$ energy regions. This result shows that we can achieve an effective discrimination of neutrons from gamma rays using these scintillator detector systems. Conclusion: We applied both PSD methods to a stilbene and a liquid scintillator and optimized the PSD performance represented by FOM values. We observed a good separation performance of both scintillators combined with a high-speed digitizer and digital PSD. These results will provide reference values for the dual-particle imager we are developing, which can image both fast neutrons and gamma rays simultaneously.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.3
• /
• pp.179-185
• /
• 2019

This paper proposes a block-type classification based image binarization for the implementation of the low-power feature extraction algorithm. The proposed method can be implemented with threshold value re-use technique approach when the image divided into $64{\times}64$ macro blocks size and calculating the threshold value for each block type only once. The algorithm is validated based on quantitative results that only a threshold value change rate of up to 9% occurs within the same image/block type. Existing algorithms should compute the threshold value for 64 blocks when the macro block is divided by $64{\times}64$ on the basis of $512{\times}512$ images, but all suggestions can be made only once for best cases where the same block type is printed, and for the remaining 63 blocks, the adaptive threshold calculation can be reduced by only performing a block type classification process. The threshold calculation operation is performed five times when all block types occur, and only the block type separation process can be performed for the remaining 59 blocks, so 93% adaptive threshold calculation operation can be reduced.