期刊文献+

宽带图像信号的直线提取 被引量:3

Line Extraction for Broadband Image Signals
下载PDF
导出
摘要 该文用 FPGA+DSP实现了宽带图像信号的实时直线提取 ,适用于通常的视频图像信号和线阵 CCD成像的连续图像信号 .实现的直线提取模块已经用于高传输率的快速遥感图像处理系统 .算法将直线提取中的参数计算分解为一个可以累加的过程 ,从而简化了计算 ,同时保证了直线参数的准确性 ,在理论上证明了算法的完备性 .文章的最后给出了实验结果及比较 . A hardware solution for real-time line extraction from broadband image signals is presented. The realization is based upon FPGA+DSP architecture. The line extraction module can process both the common frame-based video signals and the continuous image signals generalized by a line array CCD. The module has been used in a high-speed remote sensing system. The algorithm of the module is based on the gradient phase of the gray level image. In the former line extraction algorithms, three separated steps are included which are the edge detection, the GP (gradient phrase) grouping, and the line fitting. In the proposed algorithm all the three steps are performed simultaneously during a scan of the image. The basic procedural unit is to scan line by line. The LSE method is used to fit the line parameter; the calculation is transformed into a distinct cumulative procedure, which reduces the calculation without degrading the extracted lines. The pixels are input into the FPGA in the scan order. In each scan line, the connected pixels, which have the same gradient phase, are grouped as 'run code'.The DSP collects the line parameters from the run codes by a cumulative procedure. The final parameters of the line are fitted when the line is no longer expanded. The universality of the algorithm is proved. The total delay of the line extraction is less than 5 line-scan periods, and only a little memory is used to store the information about the current scanning line.
出处 《计算机学报》 EI CSCD 北大核心 2002年第7期753-758,共6页 Chinese Journal of Computers
关键词 宽带图像信号 直线提取 实时处理 可靠性 计算机视觉 图像处理 Algorithms Digital signal processing Feature extraction Online systems
  • 相关文献

参考文献1

  • 1王润生.图像理解[M].长沙:国防科技大学出版社,1994..

共引文献25

同被引文献31

  • 1Vailaya A, Figueiredo M, Jain A, et al. Content-based hierarchical classification of vacation images [C]//Proceedings of IEEE International Conference on Multimedia Computing and Systems, Florence, 1999, 1:9518-9523.
  • 2Szummer M, Picard R W. Indoor-outdoor image classification [C] //Proceedings of IEEE International Workshop on Content-Based Access of Image and Video Databases, Bombay, 1998:42-52.
  • 3Oliva A, Torralba A. Modeling the shape of the scene: a holistic representation of the spatial envelope [J]. International Journal of Computer Vision, 2001, 42(3) : 145- 175.
  • 4Carson C, Thomas M, Belongie S, et al. Blobworld: a system for region-based image indexing and retrieval [C] // Proceedings of International Conference on Visual Information Systems, Amsterdam, 1999:660-672.
  • 5Sivic J, Zisserman A. Video Google: a text retrieval approach to object matching in videos [C]//Proceedings of the 9th IEEE International Conference on Computer Vision, Nice, 2003, 2: 1470-1478.
  • 6Lazebnik S, Schmid C, Ponce J. Beyond bags of features: spatial pyramid matching for recognizing natural categories [C]//Proceedings of IEEE Computer Sociely Conference on Computer Vision and Pattern Recognition, New York, 2006:2169-2178.
  • 7Quelhas P, Monay F, Odobez J M, et al. A thousand words in a scene [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(9): 1575-1589.
  • 8Bosch A, Zisserman A, Mufioz X. Scene classification using a hybrid generative/discriminative approach [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(4): 712-727.
  • 9Hofmann T. Unsupervised learning by probabilistic latent semantic analysis [J]. Machine Learning, 2001, 42 (1/2) : 177-196.
  • 10BleiDM, Ng A Y, Jordan M I. Latent Dirichlet allocation [J]. Journal of Machine Learning Research, 2003, 3:993- 1022.

引证文献3

二级引证文献44

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