Image tracking technology for dynamic angle measurement of machine vision

In order to realize high-precision measurement of spatial dynamic angle, a spatial dynamic angle measurement method based on machine vision is proposed. A high-precision two-axis servo system is installed onto the measured target. When the spatial angle of the measured target is changed, the servo system outputs the pitch angle and the azimuth angle by identifying and tracking the cooperative target。According to the spatial coordinate system transformation,the angle change value of the measured target can be obtained. The measurement accuracy of the spatial angle will be influenced by the accuracy of the tracking cooperative target with the servo system. A cross-patterned target board is designed based on the measured distance and the imaging system. Several major algorithms of detection are summarized. Their merits and demerits are analyzed by identifying and locating the center of captured image. The captured images are compared by the servo system controlled with these algorithms. The measurement results are solved by spatial coordinate transformation. According to the experimental results, a fast detection algorithm of target center in the real-time image processing is selected. High accuracy and good real-time performance of this method in processing the target image is demonstrated by calculating and comparing the results of each image processing algorithm, which satisfies the measured requirement of space dynamic angle.

[1]  Zhuo Yang Fast Template Matching Based on Normalized Cross Correlation with Centroid Bounding , 2010, 2010 International Conference on Measuring Technology and Mechatronics Automation.

[2]  孙泽林 Sun Ze-lin,et al.  Analysis and control of error on two theodolite intersection measurement for gun rotated accuracy of artillery , 2011 .

[3]  Gao Zhao Research of an Image Matching Method Based on Principal Component Analysis , 2002 .

[4]  Shang-Hong Lai,et al.  Fast Template Matching Based on Normalized Cross Correlation With Adaptive Multilevel Winner Update , 2008, IEEE Transactions on Image Processing.

[5]  Sun Wen-bang An Improved Fast Normalized Cross Correlation Algorithm for Image Matching , 2013 .

[6]  Chen Peng Object tracking algorithm based on improved template matching , 2011 .

[7]  Han Rui,et al.  A measuring method for large antenna assembly using laser and vision guiding technology , 2016 .

[8]  刘晓利,et al.  A Correlation Tracking Algorithm Based on Template Partition Motion Estimation , 2009 .

[9]  Guo Bo,et al.  Research on Optimizing Disposition Method of Double Theodolites in Gun Rotated Precision Detection , 2011 .

[10]  Zou Xue-xiang Research on Target Tracking Method Based on an Improved Normalized Product Correlation Algorithm , 2013 .

[11]  Xiao Cheng,et al.  Technical progress and analysis on large-scale spatial angle measurement , 2016 .

[12]  Rachid Deriche,et al.  Region tracking through image sequences , 1995, Proceedings of IEEE International Conference on Computer Vision.

[13]  Yu Bing Dong,et al.  An Improved Fast Normalized Cross Correlation Algorithm , 2013 .

[14]  Li Ji Tracking algorithm by template matchingbased on particle swarm optimization , 2015 .

[15]  Sun Jing-le Improved mean shift target tracking algorithm , 2013 .

[16]  Patrick Bouthemy,et al.  Region-Based Tracking Using Affine Motion Models in Long Image Sequences , 1994 .