• Journal of Platform Technology
• /
• v.6 no.4
• /
• pp.18-25
• /
• 2018

This paper describes a real-time human and robot tracking method in Intelligent Space with multi-camera networks. The proposed method detects candidates for humans and robots by using the histogram of oriented gradients (HOG) feature in an image. To classify humans and robots from the candidates in real time, we apply cascaded structure to constructing a strong classifier which consists of many weak classifiers as follows: a linear support vector machine (SVM) and a radial-basis function (RBF) SVM. By using the multiple view geometry, the method estimates the 3D position of humans and robots from their 2D coordinates on image coordinate system, and tracks their positions by using stochastic approach. To test the performance of the method, humans and robots are asked to move according to given rectangular and circular paths. Experimental results show that the proposed method is able to reduce the localization error and be good for a practical application of human-centered services in the Intelligent Space.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.715-718
• /
• 2021

정보통신 기술이 발전함에 따라 악의적인 공격을 통해 보안문제를 발생시키고 있다. 또한 새로운 악성코드가 유포되어 기존의 시그니처 비교방식은 새롭게 발생하는 악성코드를 빠르게 분석 할 수 없다. 새로운 악성코드를 빠르게 분석하고 방어기법을 제안하기 위해 악성코드의 패밀리를 분류할 필요가 있다. 본 논문에서는 악성코드의 바이너리 파일을 이용해 시각화하고 CNN모델을 통해 분류한다. 또한 정확도를 높이기 위해 LBP, HOG를 통해 악성코드 이미지에서 중요한 특성을 찾고 데이터 클래스 불균형에서 오는 문제를 앙상블 모델을 통해 해결하는 시스템을 제안한다.

• Journal of Animal Science and Technology
• /
• v.48 no.6
• /
• pp.933-942
• /
• 2006

This experiment was carried out to investigate effects of honeybee venom treatment on the humoral immune response in pigs. Corresponding author : S. K. Cho, Dept. of Animal Sci. Chung-Buk National University, Kaesin-dong, Cheongju, 361-763, Korea. phone : 043-261-2551. E-mail : deercho@chungbuk.ac.kr To investigate effects of natural honeybee venom on the concentration of immunoglobulin G, A, and M, 20 piglets(LY×D) from 3 sows were allocated into two groups bee venom-treated group(10 piglets) and non-treated control(10 piglets). Natural honeybee venom was treated at 0, 3, 6 days after birth and the acupoints were Hai-men(ST-25), Du-kou(CV-8) and Jiao-chao(GV-1) points at 0, 3 days after birth and the regions of castration and tail amputation point at 6 days. Control group was injected 1㎖ of saline to the same site. Concentrations of IgG, A, and M were measured with immunoturbidimetric method at 0, 3, 7, 14, and 21 days after treatment. To investigate the effect of bee venom on the production of antibodies against hog cholera and atrophic rhinitis vaccines that were used as indicator antigens, 40 piglets(LYxD) from 5 sows were grouped as bee venom-treated group (20 piglets) and control group(20 piglets). Natural honeybee venom was treated at 0, 3days(castration, tail amputation) and 21days after birth. The acupoints were Hai-men(ST-25), Du-kou(CV-8) and Jiao-chao (GV-1) points at 0 day, the regions of castration and tail ampution at 3 days and Jiao-chao(GV-1) and Bai-hui(GV-20) points at 21days after birth(weaning). Control group was injected 1ml of saline to the same site. Atrophic rhinitis vaccine was injected twice at 24 and 44 days after birth and hog cholera vaccine was also injected twice at 44 and 64 days after birth. Antibody titers against Bordetella bronchiseptica and hog cholera virus were measured by using tube agglutination and ELISA tests at 24, 34, 44, 54 and 74 days after birth. Concentrations of IgG of treated group were 339.52, 366.48, 296.52, 242.06 and 219.06mg/dl at 0, 3, 7, 14 and 21 days after birth, respectively. In contrast, concentrations of IgG in control group were respectively 347.10, 334.14, 243.28, 205.18 and 191.58mg/dl during same periods with treated group. Concentrations of IgG at 0 day was not significantly different between the treated group and control group but treated group were significantly increased by 10.28% at 3 days after birth (P<0.02), 21.88% at 7 days after birth(P<0.01), 18.0% at 14 days after birth(P<0.07) and 14.3% at 21 days after birth(P<0.01). Concentrations of IgA and Ig M were not significantly different. Antibody titers against hog cholera virus were significantly increased by 57.0% at 24 days after birth(P<0.03), 74.6% at 34 days after birth (P<0.006), 48.6% at 44 days after birth(P<0.017), 45.0% at 54 days after birth(P<0.16) and 44.4% at 74 days after birth (P<0.006) in bee venom treated group in comparison with control group. Antibody titers against the Bordetella bronchiseptica was significantly increased in Beevenom treated group as 9.1% (P<0.32) at 24days, 39.7% (P<0.002) at 34days, 31.9% (P<0.02) at 44days, 33.4% (P<0.01) at 54days and 57.3% (P<0.007) at 74 days after birth when compared with those of control group pigs. Collecting together, the results in this study showed that immune responses were increased by treatment of natural honeybee venom to pigs. These results suggested that the treatment of bee venom could be used effectively for the increase of productivity in livestock industry.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.1
• /
• pp.96-110
• /
• 2017

Most of vehicle detection studies using the existing general lens or wide-angle lens have a blind spot in the rear detection situation, the image is vulnerable to noise and a variety of external environments. In this paper, we propose a method that is detection in harsh external environment with noise, blind spots, etc. First, using a fish-eye lens will help minimize blind spots compared to the wide-angle lens. When angle of the lens is growing because nonlinear radial distortion also increase, calibration was used after initializing and optimizing the distortion constant in order to ensure accuracy. In addition, the original image was analyzed along with calibration to remove fog and calibrate brightness and thereby enable detection even when visibility is obstructed due to light and dark adaptations from foggy situations or sudden changes in illumination. Fog removal generally takes a considerably significant amount of time to calculate. Thus in order to reduce the calculation time, remove the fog used the major fog removal algorithm Dark Channel Prior. While Gamma Correction was used to calibrate brightness, a brightness and contrast evaluation was conducted on the image in order to determine the Gamma Value needed for correction. The evaluation used only a part instead of the entirety of the image in order to reduce the time allotted to calculation. When the brightness and contrast values were calculated, those values were used to decided Gamma value and to correct the entire image. The brightness correction and fog removal were processed in parallel, and the images were registered as a single image to minimize the calculation time needed for all the processes. Then the feature extraction method HOG was used to detect the vehicle in the corrected image. As a result, it took 0.064 seconds per frame to detect the vehicle using image correction as proposed herein, which showed a 7.5% improvement in detection rate compared to the existing vehicle detection method.

• Journal of Animal Environmental Science
• /
• v.16 no.3
• /
• pp.193-204
• /
• 2010

The goal of this study was to develop a high-rise hog building(HRHB) for growing-fattening stages. HRHB was two story building and was suitable for specific environment in Korea. Manure was treated in a first floor and pigs were raised on the slatted second floor. Three ventilation systems - 1) duct inlet to wall exhaust system(V1), 2) eave inlet to wall exhaust system(V2), and 3) ceiling inlet to wall exhaust system(V3) - were used. This experiment was conducted during winter and from summer to fall. Air temperature, air speed, ammonia, hydrogen sulfide in HRHB, and swine growth rate were measured. During winter, air temperature in V1 system tended to be slightly high without any effect of outside air temperature. Maximum temperature from summer to fall was between 33.4 and $33.8^{\circ}C$ and there was no significant difference among systems. Continuously measured daily temperature was lower in V2 system than other systems and the fluctuation of air temperature was high. Air speed in V1 and V2 systems were similar (0.02~0.21 m/s), and was 0.04~0.15 m/s in V3 during winter. From summer to fall, air speed in V1, V2, and V3 systems were 0.10~0.41 m/s, 0.10~0.83 m/s, and 0.11~0.26 m/s, respectively. V2 system showed bigger fluctuation of air speed than other systems. During winter, the highest concentrations of ammonia in V1, V2, and V3 systems were 7.0, 3.5, and 8.7 ppm, respectively. Hydrogen sulfide was not detected. The highest concentrations of ammonia from summer to winter in V1, V2, and V3 systems were 6.1, 2.8, and 5.6 ppm, respectively. Swine growth showed no statistical significance among systems. However, daily weight gain was approximately 4% higher in V1 and V3 than in V2. Feed intake/daily weight gain was approximately 4% higher in V1 than other systems. From summer to fall, daily weight gain in V1 and V3 tended to approximately 3% higher than other systems, and feed intake/daily weight gain was approximately 2% higher in V1 than other systems. Hence, V2 system for the ventilation system of HRHB should not be utilized.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.11
• /
• pp.305-313
• /
• 2019

Recently, spatial information is being constructed actively based on the images obtained by drones. Because occlusion areas occur due to buildings as well as many obstacles, such as trees, pedestrians, and banners in the urban areas, an efficient way to resolve the problem is necessary. Instead of the traditional way, which replaces the occlusion area with other images obtained at different positions, various models based on deep learning were examined and compared. A comparison of a type of feature descriptor, HOG, to the machine learning-based SVM, deep learning-based DNN, CNN, and RNN showed that the CNN is used broadly to detect and classify objects. Until now, many studies have focused on the development and application of models so that it is impossible to select an optimal model. On the other hand, the upgrade of a deep learning-based detection and classification technique is expected because many researchers have attempted to upgrade the accuracy of the model as well as reduce the computation time. In that case, the procedures for generating spatial information will be changed to detect the occlusion area and replace it with simulated images automatically, and the efficiency of time, cost, and workforce will also be improved.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.3 no.2
• /
• pp.103-114
• /
• 1995

Since autoheated thermophilic aerobic digestion (ATAD) process has various advantages for the treatment of high-strength organic wastewater, active research and field application has been applied in U.S.A. and Canada, recently and the interest in ATAD process has been elevated for treating high-strength organic wastewater efficiently in Korea. Therefore, various experiments were carried out to evaluate the feasibility of ATAD process for the treatment of pig manure wastewater. The results of this study showed possibility to reuse pig manure wastewater as wet fodder or liquid compost, since ATAD process led excellent stabilization on the basis of odor and putrefaction. However. digested sludge can not be provided as wet fodder to most of hog farms without changing dry feeder system into wet system and as liquid compost to hog farms not having their own grass land. Since the results showed that the increase of temperature in reactor was resulted not from energy by biological activity. but from mechanical mixing energy. the reactor investigated in this study was against the principle of ATAD process. Therefore. if pig manure wastewater treated by ATAD can not be utilized as wet fodder. it is not economical to adopt ATAD process only for the treatment of wastewater.

• Korean Journal of Soil Science and Fertilizer
• /
• v.15 no.2
• /
• pp.141-146
• /
• 1982

Laboratory and greenhouse experments were conducted to find out the optimum dilution time of methane fermented effluent of hog waste which was high pH (7.85), $NH_4$-N (683ppm), electric conductivity (8.3mmhos/cm) and BOD (about 1,000ppm) and the interval of effluent change which will provide maximun yield of green algae (Scenedesmus accuminatus), duck weed (Lemner minor L.) and Azolla anabaena (Azolla pinnata). The results of this experiment are summerized as follows. 1. The maximum yield were obtained at 5 times diluted effluent ($NH_4$-N : 137ppm) and exchange of 4 day intertval, from 25 times to 50 times dilution ($NH_4$-N : 7-14ppm) and 4 day interval, and 50 times dilution ($NH_4$-N : 14 ppm) and exchange the effluent at 4-8 day interval for green algae, duck weed and azolla growth, respectively. 2. Purification of the effluent was enhenced by growth of the green algae, duck weed and azolla due to decrease of pH, $MH_4$-N and electric conductivity of effluent. The degree of purification was higher in case of azolla growth than duck week growth.

• Food Science of Animal Resources
• /
• v.28 no.1
• /
• pp.32-38
• /
• 2008

In order to expand the use of hog liver by the food industry, spreadable liver product was manufactured and quality changes were investigated depending on storage temperature at $-2^{\circ}C,\;5^{\circ}C\;and\;20^{\circ}C$ for 30 days. pH, thiobarbituric acid (TBA), volatile basic nitrogen (VBN), color, microbiological and sensory evaluation were carried out. Changes in pH values were not significantly different at different storage temperatures. TBA values were 0.6 mg MA/kg at $-2^{\circ}C$ after 30 days, 0.80 mg MA/kg at $5^{\circ}C$ after 21 days and showed 0.91 mg MA/kg at $20^{\circ}C$ after 14 days. The change in VBN content tended to increase during prolonged storage periods regardless of storage temperature. The product color tended to lighten over time, although there was no difference in a value of color during storage periods. Also, sensory evaluation results showed that the optimal storage temperature for the liver product was $5^{\circ}C$. The numbers of general bacteria increased to a level of 7.38 log CFU/g on storage 7 days in $20^{\circ}C$. This study showed that a viable spreadable liver product could be manufactured using hog liver and remains edible for at least 14 days when stored at temperatures below $5^{\circ}C$.

• Korean Journal of Veterinary Service
• /
• v.26 no.1
• /
• pp.1-9
• /
• 2003

The aim of this survey was to investigate the characteristics of outbreak farm determined as the classical swine fever(CSF) at Gangwha-gun and Seo-gu, Incheon metropolitan area from October 7 to November 25 in 2002. Sixty pigs in six different farms were confirmed to the CSF and a total of 9,106 pigs containing 3,194 related epidemiologically was slaughtered to stop spreading of the disease. Clinical signs of pigs diagnosed with the CSF were high fever, anorexia, depression, paralysis of hindlimbs, cyanosis, etc and gross lesions were typically represented with hemorrhage of submandibular and superficial lymph node, infarction of spleen, and petechial (ecchymotic) hemorrhage of kidney and skin. But some outbreak farms had not shown remarkable symptoms, so they were confused with other bacterial diseases. White blood cell (WBC) counts, the classical swine fever virus(CSFV) antigen and antibody enzyme linked immunosorbent assay(ELISA) and reverse transcriptase polymerase chain reaction (RT-PCR) results about six farms indicated that total 60 pigs were infected with the CSFV. Although the origin and infection route of the CSFV were not clear, but the transmissions between farms were mainly through indirect contact such as the movement of farm personal and vehicles from outbreak farm.