• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.6 s.312
• /
• pp.28-35
• /
• 2006

Statistical models of shape variability based on active shape models (ASMs) have been successfully utilized to perform segmentation and recognition tasks in two-dimensional (2D) images. Three-dimensional (3D) model-based approaches are more promising than 2D approaches since they can bring in more realistic shape constraints for recognizing and delineating the object boundary. For 3D model-based approaches, however, building the 3D shape model from a training set of segmented instances of an object is a major challenge and currently it remains an open problem in building the 3D shape model, one essential step is to generate a point distribution model (PDM). Corresponding landmarks must be selected in all1 training shapes for generating PDM, and manual determination of landmark correspondences is very time-consuming, tedious, and error-prone. In this paper, we propose a novel automatic method for generating 3D statistical shape models. Given a set of training 3D shapes, we generate a 3D model by 1) building the mean shape fro]n the distance transform of the training shapes, 2) utilizing a tetrahedron method for automatically selecting landmarks on the mean shape, and 3) subsequently propagating these landmarks to each training shape via a distance labeling method. In this paper, we investigate the accuracy and compactness of the 3D model for the human liver built from 50 segmented individual CT data sets. The proposed method is very general without such assumptions and can be applied to other data sets.

• Korean Journal of Soil Science and Fertilizer
• /
• v.45 no.5
• /
• pp.848-852
• /
• 2012

Vegetation can make not only to lower the urban ambient air temperature (UAAT) by crop evapotranspiration (ET) and increasing solar radiation albedo, but also to reduce the urban air pollution by $CO_2$ uptake and $O_2$ emission in addition to the reducing ozone concentrations by aid of lower the UAAT. To evaluate the effect of vegetation on urban heat island mitigation (UHIM), the climate change of 6 cities during 30 years are analysed, and the amount of ET, $CO_2$ uptake, $O_2$ emission and ozone concentrations are estimated in Korea. The most hot season is the last part of July and the first part of August, and the highest average UAAT of a period of ten days was $35.03^{\circ}C$ during 30 years (1979 - 2008). The mean values of maximum ET of rice and soybean in urban area during urban heat island phenomena were 6.86 and $6.00mm\;day^{-1}$, respectively. The effect of rice and soybean cultivation on lowering the UAAT was assessed to be 10.5 and $3.0^{\circ}C$ in Suwon, respectively, whereas the differences between the UAAT and canopy temperature at urban paddy and upland in Ansung were 2.6 and $2.2^{\circ}C$. On the other hand, the urban-garden in Suwon city had resulted in lowering the UAAT and the surface temperature of buildings to 2.0 and $14.5^{\circ}C$, respectively. Furthermore, the amounts of $CO_2$ uptake by rice and soybean were estimated to be 20.27 and $15.54kg\;CO_2\;10a^{-1}day^{-1}$, respectively. The amounts of $O_2$ emission by rice and soybean were also assessed to be 14.74 and $11.30kg\;O_2\;10a^{-1}day^{-1}$, respectively. As other cleaning effect of air pollution, the ozone concentrations could be also estimated to reduce 21.0, 8.8, and 4.0 ppb through rice-, soybean cultivation, and urban gardening during most highest temperature period in summer, respectively.