Improved Method for
Positioning Crane Grab Boom Corner Points using Hough Transform and
K-means Clustering
Min Wang 1, Longkun Wan 2 , Chengli
Zhao 2,Zhangyan Zhao2*
1 CCCC Second Harbor Engineering Company LTD,Wuhan 430040,China
2 School of Transportation and Logistics Engineering, Wuhan University
of Technology, Wuhan 430063,China
Correspondence:zzy63277@163.com
Abstract: In the process
of automatic grabbing of bridge segment beams, in order to ensure that
the crane can smoothly calibrate and align the lifting rod with the beam
body lifting hole, it is necessary to use image processing technology to
locate and detect the corner coordinates of the crane’s grabbing lifting
rod. When applying traditional corner detection methods to this scene,
there are challenges such as low detection accuracy and unsuitability.
This article proposes a new idea for corner positioning, which locates
corner coordinates through the intersection of straight lines. This
method is divided into three steps: first, use the R and G channels of
the RGB color space to construct a grayscale difference map, so that the
grayscale histogram of the foreground and background presents a bimodal
feature, which is conducive to Otsu’s threshold segmentation. And use
the open close operation to denoise the small impurities in the Canny
edge detection results; Secondly, this article proposes the optimal
adaptive threshold determination method to filter the number of votes in
the clustering results, eliminate interfering straight lines, and then
improve the clustering centroid calculation method by using weight
calculation formulas based on different proportion of votes, replacing
the original clustering centroid as the basis for line fitting; Finally,
calculate the corner coordinates of the crane’s grab boom based on the
straight line fitting results, and compare the recognition accuracy
under different lighting conditions. The experimental results show that
when there are many interfering edge points in the edge detection result
graph, compared to other line detection algorithms, the detection error
of our algorithm is smaller and has strong robustness. The calculated
corner coordinate accuracy is pixel level. The algorithm in this article
has the best detection performance under strong complementary light
conditions. The average detection error within 0-2 pixels accounts for
97.1% and a recognition accuracy of 98.6%. The recognition success
rate under different lighting conditions is higher than 92.9%. This
method is significantly superior to traditional linear detection methods
and meets the needs of automatic gripping of the boom. It has certain
engineering application value and provides a method basis for solving
the algorithm accuracy and robustness problems of port cranes under
multiple environmental variables.
Keywords: Crane grabbing boom、Hough transform、K-means
clustering、Line fitting、Corner detection