- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Chongqing (2018.6.27-2018.6.29)] 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Lunar Geomorphology Three-Dimensional Visualization within WorldWide Telescope Based on GPU
摘要： The three-dimensional visualization of lunar geomorphology was a significant research topic. There exist some problems during the three-dimensional visualization of lunar geomorphology image such as massive dataset rendering, parallelized visualization algorithms on GPU, and lunar geomorphology image projection transformation. So this paper utilized the WorldWide Telescope platform as the image rendering architecture and adopted the OSWorkflow engine and OpenPBS scheduler to enhance parallel efficiency. Beyond above, one map transformation called tessellated octahedral adaptive subdivision transform was also designed and applied into the three-dimensional rendering of lunar geomorphology image.
关键词： lunar geomorphology image,three-dimensional visualization,map projection transformation
更新于2025-09-23 15:22:29
-
Determination and Visualization of Different Levels of Deoxynivalenol in Bulk Wheat Kernels by Hyperspectral Imaging
摘要： A hyperspectral imaging system is proposed as a method to rapidly and nondestructively predict mycotoxin deoxynivalenol (DON) levels in FHB-infected wheat kernels. Standard normal variate transformation and multiplicative scatter correction (MSC) were used in spectral preprocessing. The successive projections algorithm (SPA) and random frog algorithm were used to select the optical wavelengths. Finally, the support vector machine (SVM) technique and partial least squares discriminant analysis were applied to establish different models for determining DON levels. Based on a comparison of the results, the MSC–SPA–SVM model, with the highest classi?cation accuracy (100.00% for the training test and 97.92% for the testing set), gave the best performance, and a visualization map of the DON content level based on this model was created.
关键词： optical wavelength selection,hyperspectral imaging,classi?cation model,deoxynivalenol content,bulk wheat kernels,visualization map
更新于2025-09-10 09:29:36