基于插值超分辨的双目三维重建方法OA北大核心CSTPCD
Binocular 3D reconstruction method based on interpolation super-resolution
基于双目立体匹配重建物体表面三维形貌时,其匹配精度往往受限于传感器尺寸、镜头焦距和光源环境等物理条件.针对此问题,本文提出了一种基于插值超分辨的双目表面三维重建方法.首先,在图像预处理阶段,建立基于小波变换与双直方图均衡融合的图像增强方法,克服传统双目视觉受限于复杂环境光干扰等问题;其次,构建基于拉格朗日与三次多项式插值的超分辨算法,提升图像像素密度,为双目匹配代价计算阶段增加图像细节,从而提高匹配精度;最后,基于SLIC算法对目标图像进行分割,…查看全部>>
The reconstruction of the three-dimensional surface morphology of objects based on binocular ste-reo matching is constrained by physical conditions such as sensor size,lens focal length,and environmental light.A binocular surface three-dimensional reconstruction method based on interpolation super-resolution is proposed in response to this issue.First,at the image preprocessing stage,an image enhancement method based on wavelet transform and dual histogram e…查看全部>>
刘宇豪;吴福培;吴树壮;王瑞
汕头大学工学院机械工程系,广东汕头 515063汕头大学工学院机械工程系,广东汕头 515063汕头大学工学院机械工程系,广东汕头 515063汕头大学工学院机械工程系,广东汕头 515063
计算机与自动化
双目视觉三维测量插值超分辨超像素分割
binocular vision3D measurementinterpolation super-resolutionsuperpixel segmentation
《中国光学（中英文）》 2024 (4)
862-874,13
国家自然科学基金(No.61573233)广东省自然科学基金(No.2021A1515010661)广东省普通高校创新团队资助项目(No.2020KCXTD012)Supported by National Natural Science Foundation of China(No.61573233)National Natural Science Found-ation of Guangdong,China(No.2021A1515010661)the Guangdong Provincial University Innovation Team Project(No.2020KCXTD012)
评论