Straight line extraction via multi-scale Hough transform based on pre-storage weight matrix

被引:0
|
作者
Xu, Sheng-Hua [1 ]
Zhu, Qing [2 ]
Liu, Ji-Ping [1 ]
Han, Li-Tao [3 ]
Zhao, Xue-Lian [4 ]
Zhang, Li-Hua [5 ]
机构
[1] Research Center of Government Geographic Information System, Chinese Academy of Surveying and Mapping, Beijing 100039, China
[2] Wuhan University, Wuhan 430079, China
[3] Shandong University of Science and Technology, Qingdao 266510, China
[4] China University of Geosciences, Wuhan 430079, China
[5] Dalian Naval Academy, Dalian 116018, China
关键词
Algorithms - Computer simulation - Computer vision - Hough transforms;
D O I
暂无
中图分类号
学科分类号
摘要
Aiming at the critical time-consuming and accuracy issues of straight line extraction from large-size remote sensed imagery, after briefly reviewing the existing straight line extraction methods, a multi-scale Hough transform method based on the pre-storage weight matrix is proposed, which saves a lot of storage space, takes care of discretization errors, and avoids the abruption and conglutination of characters that are the drawbacks of the existing straight line extraction algorithms. The improvement of classical Hough transform method in detail is introduced. To optimize speed and precision, the best choice of accumulator based on image size is suggested too. The experimental results show that this algorithm is more efficient in computation and robust to noise, and is rich in feature content and accurate, especially for large-size images.
引用
收藏
页码:83 / 88
相关论文
共 25 条
  • [1] Straight line extraction via multi-scale Hough transform based on pre-storage weight matrix
    Xu, Shenghua
    Liu, Jiping
    Wang, Yong
    Han, Litao
    Zhang, Yunsheng
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 2011, 32 (23) : 8315 - 8330
  • [2] A new straight line segment extraction method based on Hough transform
    Lin, Yu-Chi
    Xie, Yu-Chan
    Liu, Qi-Hai
    Nami Jishu yu Jingmi Gongcheng/Nanotechnology and Precision Engineering, 2009, 7 (05): : 433 - 438
  • [3] Fast straight-line extraction algorithm based on improved Hough transform
    Kang, Wen-Jing
    Ding, Xue-Mei
    Cui, Ji-Wen
    Ao, Lei
    Guangdian Gongcheng/Opto-Electronic Engineering, 2007, 34 (03): : 105 - 108
  • [4] Building extraction from high resolution imagery based on multi-scale object oriented classification and probabilistic Hough transform
    Liu, ZJ
    Wang, J
    Liu, WP
    IGARSS 2005: IEEE International Geoscience and Remote Sensing Symposium, Vols 1-8, Proceedings, 2005, : 2250 - 2253
  • [5] A multi-scale plane-detection method based on the Hough transform and region growing
    Leng, Xiaoxu
    Xiao, Jun
    Wang, Ying
    PHOTOGRAMMETRIC RECORD, 2016, 31 (154): : 166 - 192
  • [6] Algorithm based on wavelet lifting transform for extraction of multi-scale edge
    School of Information Science and Engineering, Northeastern University, Shenyang 110004, China
    Dongbei Daxue Xuebao/Journal of Northeastern University, 2007, 28 (04): : 473 - 476
  • [7] MULTI-SCALE CREST LINE EXTRACTION BASED ON HALF GAUSSIAN KERNELS
    Magnier, Baptiste
    Aberkane, Arezki
    Borianne, Philippe
    Montesinos, Philippe
    Jourdan, Christophe
    2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
  • [8] Multi-exposure fusion for welding region based on multi-scale transform and hybrid weight
    Chen, Haiyong
    Ren, Yafei
    Cao, Junqi
    Liu, Weipeng
    Liu, Kun
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2019, 101 (1-4): : 105 - 117
  • [9] Multi-exposure fusion for welding region based on multi-scale transform and hybrid weight
    Haiyong Chen
    Yafei Ren
    Junqi Cao
    Weipeng Liu
    Kun Liu
    The International Journal of Advanced Manufacturing Technology, 2019, 101 : 105 - 117
  • [10] A multi-scale line filter with automatic scale selection based on the Hessian matrix for medical image segmentation
    Lorenz, C
    Carlsen, IC
    Buzug, TM
    Fassnacht, C
    Weese, J
    SCALE-SPACE THEORY IN COMPUTER VISION, 1997, 1252 : 152 - 163