2019年 4 月7日
ICROS-SICE International Joint Conference 2009
August 18-21, 2009, Fukuoka International Congress Center, Japan
Vision-Based Estimation of Bolt-Hole Location using Circular Hough Transform
Yungeun Choe1, Hoo-Cheol Lee1, Young-Joong Kim1, Dae-Hie Hong2, Sin-Suk Park2, Myo-Taeg Lim1
1Department of Electrical Engineering, Korea University
(Tel : 82-2-3290-3698; E-mail: email@example.com)
2Department of Mechanical Engineering, Korea University
Abstract: In order to use a robot in the construction automation filed, we proposed the concept of Bolting Robot and a visual servo control scheme to track a bolting tool to a bolt hole in the structural steel frame. For estimating a location of a bolt hole, Circular Hough Transform (CHT) was used to extract circles. Generally, CHT is computationally complex due to a power of the dimensionality of a circle. A distance from a camera to a steel frame can be measured by using laser range -finder installed. The radius of a bolt hole can be calculated with the distance to a steel frame. Since the radius is known, the processing of CHT can be reduced to 2D. In addition, it contains image pre-processing to make an image of bolt holes to be clear. Pre-processing has 4 steps which consist of compensating lens distortion, noise filtering, histogram equalization, and edge detection.
Keywords: Construction Automation, Robot, Bolt Hole Detection, Image Processing, Circular Hough Transform
In the construction automation filed, the usage of robot is increasing. In this paper, we propose the concept of Bolting Robot and visual servo control scheme to track a bolting tool to a bolt hole in a structural steel frame. In vision based bolt hole tracking, circle detection is the key technique to extract bolt holes. Circular Hough Transform (CHT) was used to extract circles.
A general method for shape recognition is the Hough Transform (HT) in digital images [1, 2]. Firstly, it was applied to the recognition of straight lines [3, 4] and then extended to circles , ellipses  and arbitrarily shaped objects . CHT has been widely used to extract circles  and ellipses . Its main disadvantage is the fact that computational and storage requirements of the algorithm increase as a power of the dimensionality of the curve does. For circles, the computational complexity and storage requirements are O(n3 ). If the
radius of the circle is known, a power of the dimensionality of the circle can be reduced from O(n3 )
to O(n 2 ).
This paper is organized as follows. We will mention basic theory of CHT. Then the concept of bolting robot and visual servo control scheme will be provided. And we will propose image pre-processing sequence to enhance an bolt hole image. The pre-processing in applying CHT has 4 steps which consist of compensating lens distortion, noise filtering, histogram equalization, and edge detection to get a clear bolt hole image. The results of proposed method show more accuracy and faster processing time.
2. CIRCULAR HOUGH TRANSFORM (CHT)
CHT can be used to determine the parameters of a circle. A circle with radius r and center (a , b) can be described with the following parametric Eq. (1) and Eq.
x = a r cos(theta; ),
y = b r sin(theta; ).
When the angle ș sweeps through the full 360 degree range, the points (x , y) trace the perimeter of a circle. If an image contains many points, then the job of the search program is to find parameter triplets (a, b, r) to describe each circle. The fact that the parameter space is 3D makes a direct implementation of the Hough technique more expensive in computer memory and time. If the radius r of the circles in an image is known, then the search can be reduced to 2D. The objective is to find the (a, b) coordinates of the centers.
Fig. 1 Circular Hough Transform from the x , y-space (left) to the parameter space (right) and this example is for a constant radius.
At each edge point, we draw a circle of the desired radius with center in the point. This circle is drawn in the parameter space, such that our x axis is the a value and the y axis is the b value while the z axis is the radii.
At the coordinates which belong to the perimeter of the drawn circle, we increase the value in our accumulator matrix which has the same size as the parameter space. In this way, we sweep over every edge point in the input image drawing circles with the desired radii and increasing the values in our accumulator. The accumulator will contain numbers corresponding to the number of circles passing through the individual coordinates. Thus the highest numbers correspond to the center of the circles in the image.
- 4821 - PR0002/09/0000-4821 yen;400 copy; 2009 SICE
3. CONCEPT OF BOLTING ROBOT
3.1 Organization of Bolting Robot
We aim to develop a n