• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1321-1330
• /
• 2023

This study attempts to address the problem of 3D pose estimation for multiple human objects through a single image generated during the character development process that can be used in augmented reality. In the existing top-down method, all objects in the image are first detected, and then each is reconstructed independently. The problem is that inconsistent results may occur due to overlap or depth order mismatch between the reconstructed objects. The goal of this study is to solve these problems and develop a single network that provides consistent 3D reconstruction of all humans in a scene. Integrating a human body model based on the SMPL parametric system into a top-down framework became an important choice. Through this, two types of collision loss based on distance field and loss that considers depth order were introduced. The first loss prevents overlap between reconstructed people, and the second loss adjusts the depth ordering of people to render occlusion inference and annotated instance segmentation consistently. This method allows depth information to be provided to the network without explicit 3D annotation of the image. Experimental results show that this study's methodology performs better than existing methods on standard 3D pose benchmarks, and the proposed losses enable more consistent reconstruction from natural images.

• Journal of Animal Science and Technology
• /
• v.49 no.5
• /
• pp.677-688
• /
• 2007

돼지를 포함한 대부분의 동물은 일정한 발정주기를 가지고 일정한 시기에 배란을 하는 자연배란동물이지만, 토끼, 고양이, 밍크 등의 암놈은 교미자극에 의해 배란이 일어나는 유기배란동물이다. 또한 1년에 한 번만 발정하는 단발정동물과 1년에 수차례 발정하는 다발정동물이 있다. 이 중에서 모돈은 1년에 수차례 발정하는 다발정 동물로서 발정기에 들면 비발정기와는 다른 행동을 나타낸다(Diehl 등, 2001). 양돈가의 수익을 최대화하기 위해서는 비생산일수를 최소로 줄여야 한다. 모돈의 비생산일수를 줄일 수 있는 한 가지 방법은 성공적으로 교배를 시키는 것이다. 이처럼 성공적으로 교배를 시키기 위해서는 수정적기를 정확히 예측해야 한다. 만약 수정적기를 정확히 판단하지 못하여 수태가 되지 않으면, 비생산일수가 늘어나 손실을 입게 된다. 따라서 수정적기를 정확히 판단하는 것은 모돈의 성공적인 인공수정에 있어서 중요한 요소이다. 수정적기는 배란이 일어나기 전 10시간에서 12시간 사이이며, 발정이 시작되는 시점을 기준으로 하였을 때 경산돈의 경우 26시간에서 34시간 사이이고 미경산돈의 경우는 18시간에서 26시간 사이이다(Evans 등, 2001). 현재 하루에 두 번 모돈의 발정을 확인하는 것이 일반화되어 있으며, 이 때 웅돈을 접촉시키거나 육안관찰을 통하여 발정 유무를 판단한다. 이러한 방법에는 숙련된 기술과 풍부한 경험이 요구될 뿐만 아니라 총 소요노동력의 30% 정도가 요구된다(Perez 등, 1986). 하루에 두 번밖에 발정을 감지하지 않기 때문에 발정이 언제 시작되었는지를 정확히 알 수 없으며, 또한 발정의 대부분이 새벽에 시작되므로 수정적기를 정확히 판단하기란 매우 어렵다. 만약 발정을 감지했더라도 적기에 인공수정을 하지 못한다면, 수태율이 낮아지므로 경제적 손실이 초래된다. 현재 이러한 문제점 때문에 2회에서 3회에 걸쳐 인공수정을 하고 있으나 이에 따른 소요비용과 소요노동력 등은 양돈가의 부담을 가중시키는 요인이 되고 있다. 돼지는 발정기가 되면 비발정기에 나타내지 않던 외음부의 냄새를 맡는 행동, 귀를 세우는 행동 및 승가허용 행동 등을 나타낸다(Diehl 등, 2001). 또한 돼지는 비발정기에 비하여 발정기에 더 많은 활동량을 나타낸다(Altman, 1941; Erez and Hartsock, 1990). Freson 등(1998)은 스톨에서 개별적으로 사육되고 있는 모돈의 활동량을 적외선센서를 이용하여 측정함으로써 발정을 86%까지 감지하였다고 보고하였다. 그러나 이 연구는 단지 모돈의 발정을 감지하였을 뿐 번식관리에 있어서 가장 중요한 수정적기의 판단 기준을 제시하지 못하였다. 따라서, 본 연구는 스톨에서 사육되는 모돈의 활동량을 측정함으로써 발정시작시각을 감지하고 이를 기준으로 인공수정적기를 예측할 수 있는 인공수정적기 예측 장치를 개발한 후 이의 성능을 농장실증실험을 통하여 시험하고자 수행되었다.

• Journal of Bio-Environment Control
• /
• v.27 no.1
• /
• pp.27-33
• /
• 2018

This study was performed to review the domestic and international smart farm service model based on the convergence of agriculture and information & communication technology and derived various factors needed to improve the Korean smart greenhouse. Studies on modelling of crop growth environment in domestic smart farms were limited. And it took a lot of time to build research infrastructure. The cloud-based research platform as an alternative is needed. This platform can provide an infrastructure for comprehensive data storage and analysis as it manages the growth model of cloud-based integrated data, growth environment model, actuators control model, and farm management as well as knowledge-based expert systems and farm dashboard. Therefore, the cloud-based research platform can be applied as to quantify the relationships among various factors, such as the growth environment of crops, productivity, and actuators control. In addition, it will enable researchers to analyze quantitatively the growth environment model of crops, plants, and growth by utilizing big data, machine learning, and artificial intelligences.

• Applied Biological Chemistry
• /
• v.44 no.2
• /
• pp.92-96
• /
• 2001

Soil physical-chemical properties and phosphorous adsorption characteristics were investigated to obtain the informations of the appropriate fertilization and soil management in Baicheng region, China, where agricultural circumstances at present forces to consider the use of land for crop production. Soils were collected from one uncultivated and three cultivated lands on August 1993. Soil $_PH$ was very higher in uncultivated land than in cultivated land, their values were 10.2 and 7.4, respectively. Regardless of cultivation, soil organic matter contents were below 2%, and concentrations of available soil phosphorus expressed as Bray 1 P and Olson P were less than 10 mg P $kg^{-1}$, however, cation exchange capacity was higher than 20 cmol(+) $kg^{-1}$. For uncultivated soil, the values of exchangeable sodium percent and calcium saturation percent were higher than 100%. The major cation of soil saturation paste extracts was Na regardless of land use type. Based on electrical conductivity and sodium adsorption ratio of saturation paste extracts, uncultivated soil was classified as saline-sodic soil and cultivated soil was classified as sodic or normal soil. The maximum adsorption capacity of phosphorus calculated by Langmuir isotherm ranged from 406 to 521 mg P ,$kg^{-1}$. The constraints of soils in Baicheng regions for agricultural cops werw high salt concentration, unfavorable soil chemical composition such as low concentration of available phosphorous, and poor drainage due to soil dispersion by high Na concentration. Therefore, the soil in Baicheng region, need the application of phosphorus fertilizer to increase the soil fertility and the proper soil management to improve the soil physical property especially permeability and soil structure.

• Research in Plant Disease
• /
• v.11 no.2
• /
• pp.140-145
• /
• 2005

A collection of 12 Erwinia carotovora strains from blackleg diseased potato in Jeju island was characterized genetic diversity by 5. cayotovora subsp. atposeptica (Eca)-specific PCR, PCR-RFLP of the two genes (16S rRNA and pel) and repetitive sequence PCR (ERIC-PCR). The results were compared with those of the other E. carotovora representative strains. None of the blackleg strains produced PCR amplicons with Eca-specific primers in contrast to the single 690 bp amplicon obtained with Eca strains. In addition, on the basis of pel gene RFLP with Sau3AI, the blackleg strains belonged to the pattern 2 whereas Eca strains belonged to the other one (pattern 3). By analysis of 16S rDNA RELP generated with HinfI, the most strains including the E. carotovera subsp. carotovora (Ecc) representative strains used in this study belonged to the pattern 1 whereas the blackleg strains belonged to the pattern 2 except for one strain. Moreover, ERIC-PCR analysis showed that the blackleg strains were closely related to each other and had an unique DNA band. Based on these molecular approaches, we have confirmed that the blackleg disease of potato is caused by a different E. carotovora from Eca and Ecc in Jeju island.

• Journal of Korean Society of Forest Science
• /
• v.25 no.1
• /
• pp.49-71
• /
• 1975

The importance of bamboo as raw material for bamboo wares and several kinds of industrial products is highly appreciated at home and abroad. But different kinds of bamboo-bundle systems have been traditionally used in the local areas. There being no reasonable bamboo-bundle system, we have a lot of difficulty in trading bamboo products and executing adrinistmative works. Therefore, a reasonable bamboo-bundle system based on scientific proofs needs to be tested and established for fair trade and administration. This study is carried out to solve the above difficulty with statistical investigation and analysis. The results obtained are as follows. 1. The larger the circles at eye-height become, the more the possibility of the largest internode covering the span between eye-height and 1/4 height increases. 2. The longest internodes are distributed according to a rule without relation to circles at eye-height. 3. The tapering grade of bamboo culms is very high and its form is almost the same without relation to its size. (Form exponent; 0.71-1.05, eye-height form factor; 0.60-0.66, 1/4 becomes, seeing that the circle grade and the percentage of actual volume height form factor; 0.61-0.69). 4. The larger the circles at eye-height are, the lower the percentage of actual volume have negative curve relation to each other. 5. It is considered that the numbers of bamboos bundled in a "Sok" is not decided according to the usefulness of bamboos, judging from the fact that the outputs of bamboo wares per "Sok" in every circle grade are not the same. 6. As the results of the regression analysis, the empirical formulae of several amounts to circles at eye-height and culm length are as follows; Volume, $${\hat{y}}_i=\bar{3}.821874+2.013181log\;C_i+0.839128log\;H_i$$ $$V=0.0066355\;C^{2.013181}\;H^{0.839128}$$ Actual volume, $${\hat{y}}_{ai}=3.915338+0.776549log\;C_i+1.857000log\;H_i$$ $$V_a=0.0082288\;C^{0.776549}\;H^{1.857000}$$ Weight, $$w_i=3.869148+1.936410log\;C_i+0.566904log\;H_i$$ $$W=0.0073986\;G^{1.936410}\;H^{0.565904}$$ 7. Korean Phyllostachys bambusoides Sieb. et Zucc. is almost the same as that of Japan in several amounts, just the same especially in the weight. 8. It is found that the bamboo-bundle systems of Korea and Japan have much closer relation to the weight than other amounts. So It is, therefore, considered that the weight is important factor in deciding bamboo-bundle system. 9. According to the item 8, I should like to propose the appropriate numbers per "Sok" adjusted on the basis of the weight in the Table 18.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.11
• /
• pp.89-96
• /
• 2024

In this paper, we design an improved weed detection model using YOLOv10, a deep learning-based object detection algorithm. YOLOv10 improves its performance compared to previous versions by adding an attention module, the PSA module. PSA is strong at recognising complex patterns in large areas because it uses some features of its own attention to reduce computation and learn global information. However, it may be inefficient for certain problems, such as weeds, which are generally small objects. Therefore, in this paper, we propose an improved YOLOv10 by applying another attention module, SENet, instead of the PSA module. Since, SENet learns the importance between channels, it can learn the features of weeds in more detail than the PSA module. In addition, SENet is lighter, less computationally intensive, and faster than the PSA module, so we conducted experiments by replacing the PSA module with SENet, which is suitable for weed detection. The experiment consisted of 200 training runs with a total of 14 classes, and we compared the performance through various performance evaluations. The experimental results showed that the FPS increased from 476.19 to 526.32, which is about 9.52% processing speed improvement. The mAP50-95 value increased from 88.7% to 88.3%, which shows that the proposed model is lighter than the existing model and performs similarly to the existing model.