The diameters of trunk and branch of the standing tree are important working parameters of the intelligent pruning robots. This paper presented a method based on computer vision to measure the diameters of trunk and branch of the standing tree. The method includes following six steps: (1) the image, which includes the calibration stick and the standing tree, is acquired by the CCD earner a. ( 2 ) the calibration stick is detected by using the twice template matching, the number of the pixels in the horizontal direction of calibration stick in the image is counted. (3) By dividing the size of the calibration stick by the number of the pixels in the area of the calibration stick , the actual size of a pixel in the image is got. (4) detecting the intersections of trunks and branches by using template matching. (5) the trunks and branches of the standing tree are detected by detecting the joint of the trunk and branch, and then the number of the pixels of trunk and that of branch are counted. (6) the actual diameters of the trunk and the branch of the standing tree are got by multiplying the numbers of the pixel of trunk and branch by the actual size of a pixel. The diameters of 12 trunks and branches were got in the experiments, the mean absolute error is 0.67cm, and the mean relative error is 1.9%. The results of experiments show that the method presented in the paper can exactly get the diameters of trunks and branches of the standing trees. When the diameters of trunks and branches of the standing trees in a complex background are measured by the method presented in the paper, the precision of it is relatively low.
[1]
Dong-Gyu Sim,et al.
Robust Hausdorff distance matching algorithms using pyramidal structures
,
2001,
Pattern Recognit..
[2]
Zhang Junmei.
Development on Wireless Remote Control System of Pruning Robot of Commercial Plantation
,
2003
.
[3]
Jean Serra,et al.
Image Analysis and Mathematical Morphology
,
1983
.
[4]
Pierre Soille,et al.
Morphological Image Analysis: Principles and Applications
,
2003
.
[5]
Roger M. Dufour,et al.
Template matching based object recognition with unknown geometric parameters
,
2002,
IEEE Trans. Image Process..
[6]
James A. McHugh,et al.
Automated fingerprint recognition using structural matching
,
1990,
Pattern Recognit..
[7]
A. Ardeshir Goshtasby,et al.
A Two-Stage Cross Correlation Approach to Template Matching
,
1984,
IEEE Transactions on Pattern Analysis and Machine Intelligence.
[8]
Sun Ren.
Automatic identification for standing tree limb pruning
,
2005
.