The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B3b. Beijing 2008 
Figure 7. Results of the second experiment, (a) Input Image, (b) Result of Edison 
algorithm with tight thresholds, (c) Result of Edison algorithm with 
loose thresholds, (d) Result of the proposed algorithm. 
5. CONCLUSION 
An edge detection algorithm based on linear perception is 
proposed, the algorithm use the human visual mode of linear 
perception as reference to enhance the performance of detecting 
weak edges and inhibit false edges. The proposed algorithm and 
Edison algorithm are compared using different aerial images. 
The experiments show that the proposed algorithm can enhance 
the ability of detecting the edge in different images. Therefore, 
the edge detection method based on linear perception is 
effective and applicable. The method can be improved in the 
further study: regular curve can be easily detected by human 
vision, it makes that it’s possible to enhance the detection on 
weak edges forming into regular curve; furthermore, the more 
continuous and completed edges can be detected if taking the 
integrality of the object’s edge structure into consideration. 
ACKNOWLEDGEMENTS 
Thanks for the support from Chinese National Project (863) 
(SQ2006AA12Z108506), Natural Science Fund of P. R. China 
(40701154) and Open Fund of State Key Laboratory of 
Information Engineering in Surveying, Mapping and Remote 
Sensing (05-0401). 
REFERENCES 
C.Gonzalez, R. and R. E.Woods, 2002. Digital Image 
Processing. Beijing, Publishing House of Electronics Industry. 
Furukawa, Y. and Y. Shinagawa, 2003. Accurate and robust line 
segment extraction by analyzing distribution around peaks in 
Hough space. Computer Vision and Image Understanding, 
92(1), pp. 1-25. 
He, S. and Y. Tang, 2005. A Perceptual Image Processing 
Method for Edge Linking. Infrared Technology, 27(4), pp. 338- 
342. 
Huang, X., 2006. Research on 3D Building Model Extraction 
from Airborne LIDAR Data. Photogrammetry and Remote 
Sensing. Wuhan, Wuhan University. Doctor Degree Thesis. 
Jiang, W., 2004. Multiple Aerial Image Matching and 
Automatic Building Detection. Photogrammetry and Remote 
Sensing. Wuhan, Wuhan University. Doctor Degree These. 
Meer, P. and B. Georgescu, 2001. Edge Detection with 
Embedded Confidence. IEEE Transactions on Pattern Analysis 
and Machine Intelligence, 23(12), pp. 1351-1365. 
Ralescu, A. L. and J. G. Shanahan, 1995. Learning Perceptual 
Organization for Straight Line Segments. Systems, Man and 
Cybernetics, 1995. 'Intelligent Systems for the 21st Century'., 
IEEE International Conference on. 
Wang, X. and Z. Wang, 2006. Visual perceptual edge linking 
based on two-level threshold. Computer Applications, 26(8), pp. 
1845-1847. 
Canny, J., 1986. A computational app roach to edge detection. 
IEEE Transactions on Pattern Analysis and Machine 
Intelligence, 8(6), pp. 679-698. 
501