(5) 
nple, and 
algorithm, 
1, and the 
l curve is 
S that the 
Dp Which 
ints to be 
3, and the 
(C at 
^ LA-L2 
se of the 
ocal grey 
hm. In the 
grid cells 
image LI 
g through 
he ANCC 
s obtained. 
matching 
algorithm 
raditional 
ace under 
ne, which 
orrelation 
ability of 
'arries on 
ording to 
ffects of 
matching. 
  
  
7 s 910 
nstraint 
  
'onstraint 
  
4. CONCLUSION 
Focusing on the buildings occlusion problem in matching with 
city image, as well as the multiple solutions in matching due to 
repetitive texture, this paper summarizes the existing multi- 
view image matching algorithms, and proposes a multi-view 
image matching algorithm for feature point supported by the 
moving Z-Plane constraint. This paper selects three UCX digital 
aerial images of a typical building area in the same strip for 
matching experiments, and verifies the validity of the proposed 
algorithm. The conclusions are as follows. 
(1) The matching algorithm proposed in this paper can 
simultaneously match with any number of multi-view image, 
and obtains the matching results in any overlapping areas in 
multi-view image ; 
(2) Based on the selective matching, the MZPC algorithm 
effectively avoids the effects by occlusion image, and improves 
the reliability of the matched results; 
(3) The MZPC algorithm does not need the iterative calculation 
of height, and avoids the appearance of multiple peaks in the 
cross-correlation curve caused by similar texture, and reduces 
the probability of mismatches. 
(4) The MZPC algorithm is entirely based on the matching with 
feature points. The uniformity and the density of feature points 
distribution directly determine the density of matching results. 
It needs to further research the dense matching with other 
matching primitives. 
(5) The experimental results also have a few mismatched 
homologous points. It needs to research a high reliable method 
to reject the mistakes. 
ACKNOWLEDGEMENTS 
Our research project is supported by the "National Scientific 
Fund Program (No. 41101452, No. 40901222)", the “Open 
Research Fund Program of the State Key Laboratory of 
Information Engineering in Surveying, Mapping and Remote 
Sensing of Wuhan University (No. 11102)", and the "Research 
Fund for the Doctoral Program of Higher Education of China 
(No. 20112121120003)". 
REFERENCES 
Collins, R.T. , 1995. A space-sweep approach to true multi- 
image matching. Conference on Computer Vision and Pattern 
Recognition, San Francisco, pp. 358-363. 
Ji S., 2008. Multi-view matching theories and methods for 
automatic DSM extraction from linear array images. PLA 
Information Engineering University for the Degree of Master of 
Engineering, Zhengzhou, pp. 24-25. 
Pateraki M., 2005. Adaptive Multi-image matching for DSM 
generation from airborne linear array CCD Data. Institute of 
Technology Zurich, ETH Zurich, Zurich, pp. 58-61. 
Yuan X. X., Ming Y., 2009. A novel method of multi-image 
matching using image and space synthesis information. Acta 
Geodaetica et Cartographica Sinica, 38(3), pp. 216-222. 
Zhang L., 2005. Automatic digital surface model (DSM) 
generation from linear array images. Institute of Geodesy and 
Photogrammetry, ETH Zurich, Zurich, pp. 81-99. 
  
  
  
   
  
   
   
   
   
    
    
    
   
  
  
   
   
   
   
    
  
  
   
   
  
   
   
  
   
  
  
    
  
  
  
  
  
  
  
   
  
  
  
  
  
  
    
  
    
  
    
     
Zhang L, Zhang J. X., Wang S. C., 2008. Multi-image matching 
for DTM generation from SPOT-5 HRS/HRG and IRS-P5 
imagery for the project of West China topographic mapping at 
1:50,000 scale. The International Archives of the 
Photogrammetry, Remote Sensing and Spatial Information 
Sciences, Beijing, chian, XXXVII, Part B1, pp. 1109-1116. 
Zhang Y. S., Fan D. Z., Ji S., 2007. Multi-view matching 
algorithm model for ADS40 sensor. Journal of Zhengzhou 
Institute of Surveying and Mapping, 24(2), pp. 83-86. 
Zhang Z. X., Zhang J. Q. 2002. Principles of Digital 
Photogrammetry. Wuhan University Press, Wuhan, pp. 111-114.