Acta Geodaetica et Cartographica Sinica ›› 2015, Vol. 44 ›› Issue (10): 1108-1116.doi: 10.11947/j.AGCS.2015.20150088

Previous Articles     Next Articles

A Seamline Optimization Approach Based on Watershed Segmentation for Aerial Image Mosaicking

YUAN Shenggu1, WANG Mi1,2, PAN Jun1,2, HU Fen3, LI Dongyang4   

  1. 1. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
    2. Collaborative Innovation Center for Geospatial Technology, Wuhan University, Wuhan 430079, China;
    3. Satellite Surveying and Mapping Application Center, National Administration of Surveying, Mapping and Geoinformation, Beijing 100830, China;
    4. Geomatics Center of Zhejiang Province, Hangzhou 310012, China
  • Received:2015-02-10 Revised:2015-06-07 Online:2015-10-20 Published:2015-10-23
  • Supported by:
    The National Basic Research Program of China (973 Program) (Nos.2014CB744201,2012CB719901),The Key Program of National Natural Science Foundation of China (No. 91438203),The National Natural Science Foundation of China (Nos. 41371430,91438112),Foundation for the Author of National Excellent Doctoral Dissertation of China (No. 201249)

Abstract: Seamline optimization is a key step in the process of aerial image seamless mosaicking.This paper presents a novel algorithm of seamline optimization for aerial image mosaicking by adaptive marker-based watershed segmentation.The preferred region is determined by the difference of the region achieved by adaptive marker-based watershed segmentation. Then, the minimum binary heap Dijkstra's algorithm is adopted to determine the final seamlines in the preferred region. The experimental results show that the seamline determined by our method can avoid crossing obvious stand-alone objects. Compared with other algorithms,our method has higher feasibility and higher speed.

Key words: orthoimage mosaicking, seamline optimization, marker-based watershed segmentation

CLC Number: