• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.81-86
• /
• 2024

The Image Signal Processor (ISP) converts RAW images captured by the camera sensor into user-preferred sRGB images. While RAW images contain more meaningful information for image processing than sRGB images, RAW images are rarely shared due to their large sizes. Moreover, the actual ISP process of a camera is not disclosed, making it difficult to model the inverse process. Consequently, research on learning the conversion between sRGB and RAW has been conducted. Recently, the ParamISP[1] model, which directly incorporates camera parameters (exposure time, sensitivity, aperture size, and focal length) to mimic the operations of a real camera ISP, has been proposed by advancing the simple network structures. However, existing studies, including ParamISP[1], have limitations in modeling the camera ISP as they do not consider the degradation caused by lens shading, optical aberration, and lens distortion, which limits the restoration performance. This study introduces Positional Encoding to enable the camera ISP neural network to better handle degradations caused by lens. The proposed positional encoding method is suitable for camera ISP neural networks that learn by dividing the image into patches. By reflecting the spatial context of the image, it allows for more precise image restoration compared to existing models.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.27 no.1
• /
• pp.94-98
• /
• 1982

To understand the growth pattern of ginseng plant under shading, the vertical distribution of leaf area, leaf area index (LAI) and specific leaf weight (SLW) and changes in light intensity as affected by planting position were investigated in 3 to 5 years old ginseng plant populations. Light intensity was vertically lowest at about 10cm above the ground and became low at the rear planting position in 3-year-old population. When culturing bed (96cm in width) were divided into three parts at intervals of 32cm from front to rear, the leaf area in 3-year-old population was largest in middle 1/3 part of planting bed. Light intensity affected the SLW positively, but LAI showed no distinct difference among planting positions. The light environment of 4-year-old population was worse than that of 3-year-old population and leaf area and LAI differed greatly among planting positions. In 5-year-old population, leaf dry weight and leaf area of furrow part (that is, the amount of leaves protruded from the plants which were planted in 1st, 2nd or 3rd lines into the furrow) increased. The dry weights of leaves and stem increased considerably as plant became aged, and were distributed mainly in upper layer.

• Journal of Biomedical Engineering Research
• /
• v.19 no.2
• /
• pp.189-198
• /
• 1998

3D medical image reconstruction techniques are useful to figure out complex 3D structures from the set of 2D sections. In the paper, 3D medical image reconstruction system is constructed under PC environment and programmed based on modular programming by using Visual C++ 4.2. The whole procedures are composed of data preparation, gradient estimation, classification, shading, transformation and ray-casting & compositing. Three speed optimization techniques are used for accelerating 3D medical image reconstruction technique. One is to reduce the rays when cast rays to reconstruct 3D medical image, another is to reduce the voxels to be calculated and the other is to apply early ray termination. To implement 3D medical image reconstruction system based on PC, speed optimization techniques are experimented and applied.

• Journal of Korean Society of Transportation
• /
• v.36 no.3
• /
• pp.216-228
• /
• 2018

In this study analyzed the ponding changing of plastic deformation section follwed time development to apply weather, geometry and traffic data in additon to time development to improve road management service and safety of roads during or after rain. After We selected an 8.3km section of old national highway the Seongnam-Janghowon section and created a three-demensional surface of terrain through the numerical transformantion of design drawing data, with reflection the linear data of the same coordinate system in order to describe more realistic roads, we design additional structures with shading above roads. The altitude and azimuth of the sun were calculated and set based on the longitude and latitude data of the survey line for the analysis of the sun rate, and the daylight impact zone was visualized by setting the shaded time to an interval of 1 hour and the shade rate of the corresponding section. In addition, the evaporation volume calculated from weather data such as temperature, humidity, radiant energy, and road temperature analyzes together, it will use the way of a safer and more efficient road management as grasping the ponding changing more efficent in time development.