全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

针对重复纹理场景的跟踪定位算法

Keywords: 特征识别,增强现实,跟踪注册,重复纹理

Full-Text   Cite this paper   Add to My Lib

Abstract:

提出一种针对复杂标识的分类学习算法,并将其应用于移动增强现实系统中,实现了基于自然特征的跟踪定位系统.在场景特征点识别分类基础上,采用关键帧匹配算法实现无标识跟踪定位.针对含有对称结构的场景提出一种误匹配特征的回收机制.实验结果表明,该算法可解决由于场景对称结构导致的错误特征匹配,从而大幅提高特征的正确匹配率.

References

[1]  David G L. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004,60(2):91-110.
[2]  Ess A, Bay H, Tuytelaars T. SURF: speeded up robust features[J]. Computer Vision and Image Understanding, 2008,110(3):346-359.
[3]  Yan K, Rahul S. PCA-SIFT: a more distinctive representation for local image descriptors[J]. Journal of Computer Vision and Pattern Recognition, 2004(2):506-513.
[4]  Lepetit V, Julien P, Fua P. Point matching as a classification problem for fast and robust object pose estimation //Proceedings of Conference on Computer Vision and Pattern Recognition. Washington D.C.: IEEE, 2004:244-250.
[5]  Amit Y, Geman D. Shape quantization and recognition with randomized trees[J]. Neural Computation, 1997,9(7):1545-1588.
[6]  Lepetit V, Lagger P, Fua P. Randomized trees for real-time keypoint recognition //Proceedings of Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2005:775-781.
[7]  Lepetit V, Fua P. Keypoint recognition using randomized trees[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006,28(9):1465-1479.
[8]  陈靖,王涌天,林精敦,等.基于增强现实技术的圆明园景观数字重现[J].系统仿真学报,2010,22(2):424-428. Chen Jing, Wang Yongtian, Lin Jingdun, et al. Digital reconstruction of Yuanmingyuan based on augmented reality technology[J]. Journal of System Simulation, 2010,22(2):424-428. (in Chinese)

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133