• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.45-54
• /
• 2022

Image depth estimation is a technology that is the basis of various image analysis. As analysis methods using deep learning models emerge, studies using deep learning in image depth estimation are being actively conducted. Currently, most deep learning-based depth estimation models are being trained with clean and ideal images. However, due to the lack of data on adverse conditions such as haze or fog, the depth estimation may not work well in such an environment. It is hard to sufficiently secure an image in these environments, and in particular, obtaining non-homogeneous haze data is a very difficult problem. In order to solve this problem, in this study, we propose a method of synthesizing non-homogeneous haze images and a learning method for a monocular depth estimation deep learning model using this method. Considering that haze mainly occurs outdoors, datasets mainly containing outdoor images are constructed. Experiment results show that the model with the proposed method is good at estimating depth in both synthesized and real haze data.

• Proceedings of the Korea Air Pollution Research Association Conference
• /
• 2001.11a
• /
• pp.197-198
• /
• 2001

대기 중 인위적 자연적 발생원에 기인하는 SO$_2$, NOx 및 HCs는 균일반응(homogeneous reaction)과 불균일반응(heterogenous reaction)을 통해서 산화되어 산성가스와 에어로졸을 형성한다. 대부분의 산성물질은 대기 중 구름, 안개, 에어로졸 액적중에서 균일반응을 통해 생성되며, 입자표면에서 가스상 물질의 불균일반응은 에어로졸농도가 높은 배출원 근처에서 국한된다. 이와 같은 반응을 통해 생성된 산성오염물질 및 전구물질은 건성 및 습성침적(dry and wet deposition)을 통해 지표면에 침강되어 생태계에 직ㆍ간접적인 영향을 줄 뿐만 아니라 산성우 및 동식물의 호흡기질환에 중요한 영향을 미친다.(Petros et al., 1989) (중략)

• Proceedings of the Korea Air Pollution Research Association Conference
• /
• 2002.11a
• /
• pp.253-254
• /
• 2002

대기중 인위적 및 자연적 발생원에 기인하는 SO$_2$, NOx 및 HCs는 균일반응과 불균일반응을 통해서 산화되어 산성가스와 에어로졸을 형성한다 대부분의 산성물질은 대기중 구름, 안개, 에어로졸 액적중에서 균일반응을 통해 생성되며, 입자표면에서 가스상 물질의 불균일반응은 에어로졸 농도가 높은 배출원근처에서 국한된다. 이와 같은 반응을 통해 생성된 산성오염물질 및 전구물질은 건성 및 습성침적 (dry and wet deposition)을 통해 지표면에 침강되어 생태계에 직ㆍ간접적인 영향을 줄뿐만 아니라 산성우 및 동식물의 호흡기 질환에 중요한 영향을 미친다. (중략)

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.5 no.1
• /
• pp.11-17
• /
• 2003

pH value of sampled fogwater at source regions (above highway and road) in Yongin sites showed the lowest value and was increased after passing the forest stands. Changes of ion concentrations through the forest stands showed a lowering tendency at sampling sites. The fogwater passing the forest stands (Quercus mangolica and Pinus rigida) surrendered acid pollutants to crown and stem from the atmosphere. It was concluded that environmental moisture in the atmosphere is acidified in fogwater. The influence was extended to the pure zone, and the frequency of acid rain has increased. The forests are assumed to remove air pollutants because ion concentrations in fogwater decreased after passing the forests. The fogwater which functions as a local sink for pollutants (H$_2$SO$_4$, HNO$_3$, etc.) falling on plant surfaces is considered to effectively remove acid pollutants. But if the deposition of pollutants exceeds the capacity of purification, it would damage the forest ecosystem. Further investigation is necessary to identify tree species tolerant to acid pollutants.