• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.1
• /
• pp.16-25
• /
• 2020

Vegetation segmentation in a field color image is a process of distinguishing vegetation objects of interests like crops and weeds from a background of soil and/or other residues. The performance of the process is crucial in automatic precision agriculture which includes weed control and crop status monitoring. To facilitate the segmentation, color indices have predominantly been used to transform the color image into its gray-scale image. A thresholding technique like the Otsu method is then applied to distinguish vegetation parts from the background. An obvious demerit of the thresholding based segmentation will be that classification of each pixel into vegetation or background is carried out solely by using the color feature of the pixel itself without taking into account color features of its neighboring pixels. This paper presents a new pixel-based segmentation method which employs a multi-layer perceptron neural network to classify the gray-scale image into vegetation and nonvegetation pixels. The input data of the neural network for each pixel are 2-dimensional gray-level values surrounding the pixel. To generate a gray-scale image from a raw RGB color image, a well-known color index called Excess Green minus Excess Red Index was used. Experimental results using 80 field images of 4 vegetation species demonstrate the superiority of the neural network to existing threshold-based segmentation methods in terms of accuracy, precision, recall, and harmonic mean.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.32 no.3
• /
• pp.1-17
• /
• 2004

The focus of this study is the promotion of green area volumes and their naturalness, water circulation system, decline of entropy, creation of biological habitats and linkage of separated urban green space. Re-presentative urban biotope survey sites were categorized as urban biotope, semi-natural biotope, and natural forest. In the urban biotope, a residential biotope was constructed near the Han river and in mountain areas. The green-area ratio at the housing complex was about 25%. GVZ(Grunvolumenzahl) was 0.35m$^3$/m$^2$ at the 5∼10-story housing complex, and 1.53m$^3$/m$^2$ over the 11-story. As for the green-area structure of the housing complex, canopy layer, understory layer, and shrub layer were not differentiated and the green-area volume was not high enough. The green-area ratio of school areas as a public area biotope was 5∼20%. GVZ was 1.12m$^3$/m$^2$ at Myungduk High School, and 1.78m$^3$/m$^2$ at Jeonggok Elementary School. In order to convert the urban biotope into an ecological area, green areas around the buildings should be connected to urban buffer green areas, and multi-layer structures should be established with natural plant species. In the semi-natural biotope, neighbor parks were created park in the vicinity of the natural forests. GVZ was 0.28m$^3$/m$^2$, and plantation was established with single layer structure and was definitely insufficient for the area. The urban buffer green areas have been established in strip corridors with the width of 20∼123m. In those areas, GVZ was 0.16∼0.27m$^3$/m$^2$ and had a deficient canopy layer, understory layer, and shrub layer. Soil conditions were not favorable for tree growth. In the natural biotope, GVZ of the plantation was 1.03∼1.5m$^3$/m$^2$ but the high crown closure of this area reduces the chance of species change and succession. GVZ of natural forest was 2.53∼2.57m$^3$/m$^2$. It is desirable to plant diverse plants and the natural forest should be succeeded by broad-leaf deciduous tree species. To improve the value of biotope at Kangseo-Gu, building height needs to be limited to reduce the environmental deterioration in the city. In order to maintain the water circulation system, water-permeable material is recommened when the urban surface areas are paved. The establishment of a water circulation system will improve ground water levels, soil moisture, water quality, and habitats. In order to improve biological diversity, it is desirable to have multi-layer structures in urban green areas with native species.

• Ocean Systems Engineering
• /
• v.7 no.2
• /
• pp.107-120
• /
• 2017

Spud-can is used for fixing jack-up rig on seabed. It needs to be inserted up to the required depth during the installation process to secure enough soil reaction and prevent overturning accidents. On the other hand, it should be extracted from seabed soils as fast as possible during the extraction process to minimize the corresponding operational cost. To achieve such goals, spud-can may be equipped with water-jetting system including monitoring and control. To develop such a smart spud-can, a reliable numerical simulation tool is essential and it has also to be validated against physical model tests. In this regard, authors developed a numerical simulation tool by using a commercial program ANSYS with extended Drucker-Prager (EDP) formula. Authors also conducted small-scale (1/100) physical model tests for verification and calibration purpose. By using the numerical model, a systematic parametric study is conducted both for sand and K(kaolin)-clay with varying important soil parameters and the best estimated soil properties of the physical test are deduced. Then, by using the selected soil properties, the numerical and experimental results for a sand/K-clay multi-layer case are cross-checked to show reasonably good agreement. The validated numerical model will be useful in the next-stage study which includes controllable water-jetting.

• Proceedings of the KIEE Conference
• /
• 2006.07e
• /
• pp.89-90
• /
• 2006

Recent earth systems not only make earth resistance decreased by installing earth electrode but also are demanded by earth construction for the protection of human life and equipments through total investigation about circumstances. Layer constructions in Jeju island consist of multi-layer of scoria, rocks and shale except clay layers on the surface, which needs the construction of the coring earth electrode suitable in the condition of the area. For this reason, we've used the coring earth electrode. But the coring earth electrode is expected to slow down the performance of this equipment according to the progress of time changing the effects. It is also applied for the stability of earth system construction and management after the construction work analyzing the condition of the earth system. Therefore, this is actually focused on the analysis on measuring the earth resistance and the soil resistivity that cover the range where the remarkable contrast can be expected to be seen in the layer structures.

• Asian Journal of Turfgrass Science
• /
• v.19 no.2
• /
• pp.151-160
• /
• 2005

Research was initiated to investigate seasonal turf quality under a sand-based USGA soil system. USGA system 45 centimeters deep was built with rootzone layer, intermediate layer, and drainage layer. Six turfgrass entries were comprised of 3 blends and 3 mixtures from cool-season grasses (CSG). Turfgrass quality ratings were best in spring and fall, especially early May to early July and late August to early November. Kentucky bluegrass(KB) consistently produced the greatest quality, while perennial ryegrass (PR) the poorest. Intermediate turf quality between KB and PR was observed with tall fescue (TF). Among CSG mixtures it increased with KB but decreased with PR. There were considerable variations in summer turf performance. No summer drought injury was found in KB and TF. However, PR showed poor performance through summer as compared with other CSG. Results demonstrate that KB was the best and PR the worst among CSG grown in a sand-based USCA soil system.

• The Journal of Engineering Geology
• /
• v.14 no.3 s.40
• /
• pp.301-311
• /
• 2004

This study is suggested a new dielectric tracer test method to understand geological structure of porous media and groundwater flow to use the dielectric constant which is one of electrical special quality of various geological materials. To measure their parameters, tracer material is made an ethanol mixing liquid(EML) having a same specific gravity of water. Also, soil materials are prepared a dielectric tracer test using the FDR system that could measure dielectric constant for saturated standard sand and river sand layers which have different initial porosity. To compare with their results, we discussed with the concentration variation of saline water having a saline concentration $3\%$ which is general tracer material by using the electro multi-meter system in the laboratory or field test. In two tracer experiment results, EML tracer test could confirm definitely EML concentration variation from each saturated soil layer as standard and river sands. However, tracer test of saline water $3\%$ concentration could not confirm permeating movement of water by degree of salinity change because these are settled at lower part column in a whole column area continuously. These causes are that specific gravity of saline water is heavier than water. That is, it could know that deposition of saline water is composed of lower part of soil column continuously independently of the direction of water into saturated soil material.

• The KIPS Transactions:PartD
• /
• v.9D no.5
• /
• pp.939-944
• /
• 2002

In this paper, we propose and apply new classification method to the remotely sensed image acquired from airborne multi-spectral scanner. This is a neuro-fuzzy image classifier derived from the generic model of a 3-layer fuzzy perceptron. We implement a classification software system with the proposed method for land cover image classification. Comparisons with the proposed and maximum-likelihood classifiers are also presented. The results show that the neuro-fuzzy classification method classifies more accurately than the maximum likelihood method. In comparing the maximum-likelihood classification map with the neuro-fuzzy classification map, it is apparent that there is more different as amount as 7.96% in the overall accuracy. Most of the differences are in the "Building" and "Pine tree", for which the neuro-fuzzy classifier was considerably more accurate. However, the "Bare soil" is classified more correctly with the maximum-likelihood classifier rather than the neuro-fuzzy classifier.

• Geomechanics and Engineering
• /
• v.12 no.3
• /
• pp.441-464
• /
• 2017

The determination of the mixture parameters of stabilization has become a great concern in geotechnical applications. This paper presents an effort about the application of artificial intelligence (AI) techniques including radial basis neural network (RBNN), multi-layer perceptrons (MLP), generalized regression neural network (GRNN) and adaptive neuro-fuzzy inference system (ANFIS) in order to predict the unconfined compressive strength (UCS) of silty soil stabilized with bottom ash (BA), jute fiber (JF) and steel fiber (SF) under different freeze-thaw cycles (FTC). The dosages of the stabilizers and number of freeze-thaw cycles were employed as input (predictor) variables and the UCS values as output variable. For understanding the dominant parameter of the predictor variables on the UCS of stabilized soil, a sensitivity analysis has also been performed. The performance measures of root mean square error (RMSE), mean absolute error (MAE) and determination coefficient ($R^2$) were used for the evaluations of the prediction accuracy and applicability of the employed models. The results indicate that the predictions due to all AI techniques employed are significantly correlated with the measured UCS ($p{\leq}0.05$). They also perform better predictions than nonlinear regression (NLR) in terms of the performance measures. It is found from the model performances that RBNN approach within AI techniques yields the highest satisfactory results (RMSE = 55.4 kPa, MAE = 45.1 kPa, and $R^2=0.988$). The sensitivity analysis demonstrates that the JF inclusion within the input predictors is the most effective parameter on the UCS responses, followed by FTC.

• Korean Journal of Soil Science and Fertilizer
• /
• v.44 no.5
• /
• pp.688-695
• /
• 2011

This study was carried out for some survey about soil compaction in the multi-cropping system of paddy field. Investigated sites were 90 farmer's fields in south-eastern part of Korea. The tillage practices season was different according to cropping system of paddy; in spring for mono rice cultivation and in autumn for the multi-cropping field. The average tillage depth in investigated sites was about 25 cm, however, it is different between the farmer's tillage practices and soil characteristics. It is high correlation to tillage deep and minimum resistance of penetration. The reaching soil deep to maximum resistance of penetration was about 27 cm, and average penetration resistance of the deep is 1.8~2.0 MPa for moderately fine-textured soils and more than 3.0 MPa for moderately coarse-textured soils. The difference of penetration resistance between cultivating and compacted layer was in order to sandy loam > clayey loam > clayey, and the difference was lesser in poorly drained soils than somewhat poorly ones. In the rice mono cropping field, the maximum resistance in no-tillage for 15 years was 1.18~1.25 Mpa at 20~25 cm in soil deep, however, the resistance of field with every year tillage practices was 2.03~2.21 Mpa. In the extremely compacted sandy loam textured soils, the penetration resistance at 30 cm in soil depth was drastically reduced by the subsoil from 5.2 Mpa to 3.2 Mpa, and the watermelon root in plastic film house was deep elongated.

• Journal of Korean Society of Environmental Engineers
• /
• v.34 no.2
• /
• pp.91-96
• /
• 2012

In this study we investigated the effects of operational parameters of a multi-layered soil filtration (filter depth, filtration velocity, and continuous/intermittent operation) on removal of pollutants in river water. As filter depth increased removal of all the pollutants (COD, TP, TN, and $NH_4$-N) was increased because the increase in filter depth increased in contact time between media and pollutants. The removal of TP and $NH_4$-N more increased with the increase in filter depth, comparing to the biological COD removal which was performed only in the top layer, since the removal mechanism of TP and $NH_4$-N was physicochemical process occurring throughout the whole layers. However, the reduction in filtration velocity resulted in decrease of removal all the pollutants removal due to shorter retention time. Biological COD removal was more influenced with the reduction in filtration velocity (longer retention time), than the removal of TP and $NH_4$-N. Because biological process was occurred only in the top layer which has relatively shorter retention time, comparing with physicochemical process occurred throughout whole media. Therefore, it is desirable that the operation parameters be controlled toward increasing retention time, in order to achieve efficient pollutants removal. The change in operation mode (continuos vs. intermittent operations) did not provide significant effects on the pollutant treatment efficiency by the multi-layered soil filtration system. Our findings suggest that for stable long-term operation it should be considered keeping conditions for biological activity and accelerating clogging.