Journal of Applied Sciences ›› 2018, Vol. 36 ›› Issue (5): 826-836.doi: 10.3969/j.issn.0255-8297.2018.05.010

• Signal and Information Processing • Previous Articles     Next Articles

Least Square Image Matching Algorithm Considering Elevation Plane and Parallax Constraints

ZHANG Chun-sen1, MU Yan1, ZHU Shi-huan1, GUO Bing-xuan2, QIU Zhen-guo1   

  1. 1. College of Geomatics, Xi'an University of Science and Technology, Xi'an 710054, China;
    2. State Key Laboratory of Information Engineering in Surveying, Mapping & Remote Sensing, Wuhan University, Wuhan 430079, China
  • Received:2017-09-18 Revised:2017-11-21 Online:2018-09-30 Published:2018-09-30

Abstract: Aiming at the problem that the traditional least square image matching algorithm is limited by the image quality and the initial condition, this paper proposes a least square image matching algorithm considering elevation plane and parallax constraints by means of combining the characteristics of the vertical line locus and the multi-slice least square matching algorithm based on collinear constraints. The algorithm is based on elevation plane constraint matching where the parallax constraint is used in searching and matching process. The parallax offset can provide reliable and stable initial condition for the least square matching, realizing precisely matching of images. There experiments are conducted with the vertical line locus method, the multi-slice least square matching algorithm with collinear conditional constraints and with the proposed algorithm, respectively.Experimental results proof that the proposed algorithm has obvious advantages in matching accuracy and subsequent calculation of aerial triangulation, compard with the other two algorithms.

Key words: elevation plane, parallax constraint, least square match, high precision match

CLC Number: