期刊文献+

室外自然场景下的雾天模拟生成算法 被引量:2

Simulation of the Foggy Scene under Outdoor Natural Scenes
下载PDF
导出
摘要 为了通过单幅真实拍摄的图像生成一系列具有雾天效果的虚拟场景,提出了一种完全基于图像的室外自然场景的雾天模拟算法.该算法首先对图像内容进行语义分割,将不同的场景内容标签为天空、地面和立于地面上的物体等;其次针对不同类型的场景分别进行深度信息的解析;最后利用大气散射模型进行雾天的模拟与仿真,从而得到室外自然场景的雾天虚拟图像.理论分析和实验结果表明,该算法的效率仅与图像的分辨率有关,且生成的雾天虚拟场景具有视觉真实感. In this paper The algorithm takes th which are labeled as th for different model. The only relates a new algorithm is proposed to simulate ree steps. Firstly e sky, the ground regions. Finally, it theory and experime synthes nt show the foggy scene based on a real image. , it segments the input image into several semanti and the targets on the ground. Secondly, it estima izes virtual fogs in the scene using an atmospheric that the computational complexity of the proposed c regions, tes depths scattering algorithm to the resolution of the image, and the synthetic foggy scenes are visually realistic.
出处 《计算机辅助设计与图形学学报》 EI CSCD 北大核心 2013年第3期397-401,409,共6页 Journal of Computer-Aided Design & Computer Graphics
基金 国家自然科学基金重点项目(60832011) 天津市自然基金项目(10JCYBJC00800)
关键词 深度估计 语义分割 雾天模拟 depth estimation semantic segmentation simulation of fog
  • 相关文献

参考文献12

  • 1Narsimhan S G, Nayar S K. Vision and the atmosphere [J]. International Journal of Computer Vision, 2002, 48(3) : 233- 254.
  • 2Quartulli M, Datcu M. Bayesian model based city reconstruction from high resolution ISAR data [C] // Proceedings of IEEE/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas, Los Alamitos: IEEE Computer Society Press, 2001 : 58-63.
  • 3Scharstein D, Szeliski R. A taxonomy and evaluation of dense two frame stereo correspondence algorilhms [J]. Inler- national Journal of Computer Vision, 2002, 47(1): 7-42.
  • 4Frueh C, Zakhor A. Constructing 3D city models by merging ground-based and airborne views [C] //Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2003, 2:562-569.
  • 5Michels J, Saxena A, Ng A Y. High speed obstacle avoidance using monoeular vision and reinforcement learning [C] // Proceedings of International Conference on Machine Learning. New York: ACM Press, 2005:593-600.
  • 6Saxena A, Chung S H, Ng A Y. 3-D Depth reconstruction {tom a single still image [J]. International Journal of Computer Vision, 2008, 76(1): 53-69.
  • 7Hoiem D, Efros A A, Hebert M. Geometric context from a single image [C] //Proceedings of the 10th IEEE International Conference on Computer Vision. Los Alamitos: IEEE Computer Society Press, 2005, 1: 654-661.
  • 8Felzenszwalb P F, Huttenlocher D P. Efficient graph-based image segmentation [J]. International Journal of Computer Vision, 2004, 59(2) : 167-181.
  • 9Leung T, Malik J. Representing and recognizing the visual appearance of materials using three-dimensional textons [J]. International Journal of Computer Vision, 2004, 43(1): 29- 44.
  • 10Koseeka J, Zhang W. Video compass [M] //Lecture Notes in Computer Science. Heidelberg: Springer, 2006, 2353:29-32.

二级参考文献10

  • 1陈付幸,王润生.基于预检验的快速随机抽样一致性算法[J].软件学报,2005,16(8):1431-1437. 被引量:106
  • 2Fischler M A,Bolles R C.Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM,1981,24(6):381-395
  • 3Torr P H S,Zisserman A.MLESAC:a new robust estimator with application to estimating image geometry[J].Computer Vision and Image Understand,2000,78(1):138-156
  • 4Stewart C V.MINPRAN:a new robust operator for computer vision[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(10):925-938
  • 5Chum O,Matas J.Randomized RANSAC with Td,dtest[J].Image and Vision Computing,2002,22(10):837-842
  • 6Matas J,Chum O.Randomized RANSAC with sequential probability ratio test[C]//Proceedings of the 10th IEEE International Conference on Computer Vision,Beijing,2005:1727-1732
  • 7Matas J,Chum O.Matching with PROSAC-progressive sample consensus[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,San Diego,2005:220-226
  • 8Hartley R,Zisserman A.计算机视图中的多视图几何[M].韦穗,杨尚骏,章权兵,译.合肥:安徽大学出版社,2002.
  • 9Lowe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110
  • 10http://www.robots.ox.ac.uk/-vgg/data/data-aff.html.

共引文献12

同被引文献24

引证文献2

二级引证文献8

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部