摘要
传统虚拟地形建模通常采用基于人工设计的过程化生成方法,无法满足军事仿真等需要对真实环境进行还原的仿真建模任务.针对此类任务,提出了一种基于遥感图像的虚拟地形仿真建模方法,其核心是地形混合纹理生成网络(landscape blended texture generation network, LBTG-Net).该方法利用地形混合纹理生成器(blended texture generator, BTG),在风格鉴别器(style discriminator, SD)以及多级分类损失的约束下生成地形混合纹理贴图,基于该混合纹理贴图生成结果对地形环境进行程序化构建.该方法包含2个核心特点:(1)对输入遥感图像进行准确的地表覆盖类型分类,以保证对输入遥感图像环境的还原;(2)生成高质量地形混合纹理贴图,以提高虚拟地形建模质量. LBTG-Net使用Sentinel-2多光谱遥感图像数据集进行训练和验证.实验结果表明,该方法在各地表覆盖类型分类评价指标下均有良好表现,能够在准确还原输入遥感图像的环境分布的同时完成高质量虚拟地形仿真建模.
Traditional virtual terrain modeling commonly uses a procedural generation method based on manual design, which cannot be used for competent simulation modeling tasks that need to restore real environments, such as in military applications. In this paper, we proposed a landscape simulation modeling method based on remote sensing images. The core of our proposed method is a landscape blended texture generation network(LBTG-Net);this method uses a blended texture generator(BTG) to generate landscape blended textures with the supervision of a style discriminator(SD) and multi-stage classification loss. Then, we procedurally build the complete virtual environment based on the blended texture generated by LBTG-Net. Our method has two main features:(1) accurate land-cover classification ability of remote sensing image inputs;and(2) high quality landscape blended texture outputs to guarantee virtual landscape modeling quality. We used multispectral image data from the Sentinel-2 satellite as the experimental dataset. The experimental results showed that our method offered high performance under mainstream land-cover classification evaluating indicators and can accurately reproduce the environmental distribution of input remote sensing images while completing high-quality virtual terrain simulation modeling.
作者
王泽华
高岩
陈敏刚
WANG Zehua;GAO Yan;CHEN Mingang(School of Computer Science and Technology,East China Normal University,Shanghai 200062,China;Shanghai Key Laboratory of Computer Software Testing and Evaluating,Shanghai 201112,China)
出处
《华东师范大学学报（自然科学版）》
CAS
CSCD
北大核心
2023年第2期82-94,共13页
Journal of East China Normal University(Natural Science)
基金
国家自然科学基金(62072183)。
关键词
虚拟地形仿真建模
生成对抗网络
地形混合纹理贴图
landscape simulation modeling
generative adversarial networks
landscape blended texture
