Professional Documents
Culture Documents
'Robotic Laboratory, Shenyang Institute ofAutomation, Chinese Academy of Science 110016, China
1806
Authorized licensed use limited to: INDIAN INSTITUTE OF TECHNOLOGY MADRAS. Downloaded on March 20,2010 at 06:18:51 EDT from IEEE Xplore. Restrictions apply.
2
robustly, Gabor filter is applied to eliminate the influence of and the current offset position of the UGV on the stairways,
the illuminate. Furthermore, a fast method is proposed to filter which make it possible to control the UGV to creep the stairs
out small and vertical lines after the edges are detected. This automatically. Fig.2 illustrates the whole flow of our
step improves the efficiency and the accuracy of the algorithm algorithm.
in the stair edge detecting and linking processing. Then, a Our algorithm includes the following steps:
robust edge linking algorithm is used to extract the set of Firstly, the Gabor function is used to filter the image in
parallel lines. Finally, we estimate the two offset parameters order to eliminate the influence of the illuminate and keep the
based on the theory of RANSAC algorithm [10][11][12]. The stair edges.
experimental results validate our algorithm. Secondly, the generic edge detector is applied to the filtered
The paper is organized as followed: in section 2, we image. With our proposed fast algorithm the most of the small,
describe the whole flow of our algorithm. In section 3, we vertical edges are removed. It can improve the efficiency and
estimate the two parameters by the RANSAC and describe the accuracy of the linking algorithm in the next step.
strategy of steering the UGV. In section 4, the results of our Thirdly, the remainder adjacent edges are linked into a long,
experiments are shown. We end this paper with conclusions horizontal edge (which should be the stair edges) according to
and discussions in section 5. some basic constraints.
Finally, the two offset parameters are estimated by the
II. THE WHOLE FLOW OF OUR ALGORITHM RANSAC method. And the UGV can be steered by the two
Stairways are of different styles, different materials, and parameters to climb the stairs. When the vehicle arrives at the
under different lighting conditions. The only feature of linking between two staircases, it restarts the Stair Detection
stairways is that their profile includes a set of parallel lines in Program to detect the stairs automatically. If the vehicle
3D space. When the UGV is creeping on the stairways, the detects the stair, it will go on climb the stair based on vision.
projection of stair edges on the 2D image plane are nearly a A. The Gaborfilter
group of parallel lines. The Gabor filter can eliminate the influence of the
The intention of our vision algorithm is to detect long, illumination to an image efficiently and reserve the multi-scale
horizontal lines in an image, and to extract the most similar and multi-direction information. The Gabor filter has also
ones among these lines which should be the stair edges. These been shown to be benefit to the receptive fields of simple cells
extracted lines can be used to estimate the current offset angle in the striate cortex and hence their relationship to models for
the early vision of manuals [7,8,9]. The Gabor filter is applied
to eliminate the influence of variety illumination and shadows
effects on an image. The appropriate selection of the scale and
the frequency of the Gabor filter to maintain the level of the
staircase edges will be a precondition for the following
.L
processing.
Equation 1 shows the Gabor function:
1 I1X2 2
ga ,, (x, Y) exp[- (- + y 2 )] exp[jo (x + y)] (1)
where (x, y) is the point position in the horizontal and vertical
N
y
v
Authorized licensed use limited to: INDIAN INSTITUTE OF TECHNOLOGY MADRAS. Downloaded on March 20,2010 at 06:18:51 EDT from IEEE Xplore. Restrictions apply.
3
direction, ax, a is the standard deviation of the x direction The main idea of our template operation is that if a line gets
through or partial get through the template boundaries, it may
and y direction respectively, and o0 is the space frequency of be a line preserved. If a line does not get through, it would be
the complex plane-wave. eliminated. We define the radius of the template as r, the width
By selecting the appropriate parameters of ax, (y, and o of the template as W=2*r+1 and the image point as img (i, j),
to maintain the level of the stair edges, it will be conducive to the boundary point of the template as Edge{i, j}
further processing. For our current work, we use the where i = 1 or i = W or j = 1 or j = W . The set of
multi-channel filtering approach with a set of predetermined neighbor points of the Edge{ i, j} are denoted as
filter parameters. In our experiments, we assume that all the
stair edges are horizontal or nearly horizontal (the slope is less adj{fi, j} . The method to compute the sum of the neighbor
than 0.5). So in order to get the appropriate parameters of points of the edge points in the template is as follows:
Gabor filters, we experimentally apply a series of Gabor filters
to stair images in order to choose the filter which has the sum = E adj(i, j)xEdge(k,l)
edge point adj i_j
largest response in vertical direction and the lowest response
in horizontal direction as the most suitable one. Through If sum > 1,
experiments, the parameters are determined, which direction is There would be a line pass through the template;
vertical and the band width equal to 1. And these parameters Else if sum < 1,
are used in all of our experiments. Fig.3 shows the original
image, and Fig.4 shows the result of the image convolved by There would be no line, and so we elim inate all
the Gabor filter. of the edge pixels in the template.
This method can remove all of the isolate points and most of
the short discontinuous lines, and save much time in edge
linking. The result of the method on synthesize image is
illustrated in Fig.6. And Fig.7 shows the results of this method
on the stair binary image.
Fig. 4 The result of Gabor filter 'The synthesize image 'The result of the eliminate small lines
Fig.6 The result of the eliminate small lines on synthesize image
B. Eliminate small Lines
The Gabor filtered image is segmented by the generic edge
detector, and there are still a lot of small lines in the image.
Fig.5 shows their results respectively. It is inefficient if we
apply Hough transform, RANSAC or other edge link
algorithms directly on the output binary edge images for
detecting the stair lines. In order to remove most of small,
vertical lines which are not wanted, we propose a new fast
1808
Authorized licensed use limited to: INDIAN INSTITUTE OF TECHNOLOGY MADRAS. Downloaded on March 20,2010 at 06:18:51 EDT from IEEE Xplore. Restrictions apply.
4
S>S1y xI- s
area I l s I I Continue.
=area'S> - Si Si x
(3) Else
Insert line ijth into L,
S' yiscythe sum of all its x coordinates, S' is the N=N+ 1.
sum ofWhere
all its
sum of all its y coordinates, S'. is the sum of the square of For i=l: total number of the merged lines
If the length of the line i is less than width/4,
all its x coordinates, S'y is the sum of the square of all its y Delete.
coordinates, and Syis the sum of the product of all its x Else If x;> width/2 or xl <width/2
Delete.
1809
Authorized licensed use limited to: INDIAN INSTITUTE OF TECHNOLOGY MADRAS. Downloaded on March 20,2010 at 06:18:51 EDT from IEEE Xplore. Restrictions apply.
5
1810
Authorized licensed use limited to: INDIAN INSTITUTE OF TECHNOLOGY MADRAS. Downloaded on March 20,2010 at 06:18:51 EDT from IEEE Xplore. Restrictions apply.
6
to the stairway. The white lines indicate the estimated center Finally, implemented on a laptop computer (Pentuium4
of the stairwells. Fig. 11(a) shows the vehicle is mounted on 2.4GHZ) using C language, the over time of the systems is
the side of the stair. The offset parameters marked by the less than 60ms, including extracting the edges, estimating the
white line are estimated successfully. Figi 1(b) shows that our time, and steering the UGV.
vision system is guiding the vehicle to the center of the
stairways. Fig.11(c) shows the vehicle inclines on the V. CONCLUSION
stairwells and our algorithm can still detect the stair edges and We have demonstrated a vision system based on our own
estimate the parameters robustly. At last, Fig. 11(d) shows the algorithm which can guide the UGV to climb the stairs
vehicle is adjusted in the center of the stair by our algorithm. automatically under various conditions. The results proved the
validity of our algorithm.
REFERENCES
[1] S. Se and M. Brady, "Vision-based Detection of Kerbs and Steps",
Proc. BMVC97, 1997
[2] JS Gutmann, M Fukuchi, M Fujita "Stair climbing for humanoid
robots using stereo vision" Intelligent Robots and Systems,
2004.(IROS 2004)
[3] Xiaoye Lu, Manduchi, R. " Detection and Localization of Curbs and
Stairways Using Stereo Vision" Proc.ICRA 2005 4648- 4654
The indoor condition fqce to the, -un [4] R. Turchetto and R. Manduchi, "Visual Curb Localization for
Autonomous Navigation", Proc. IEEE/RSJ IROS'03, Las Vegas,
October2003.
[5] Y.Xiong and L.Matthies, "Vision-Guided Autonomous Stair
Climbing",Proc. ICRA, 2000.
[6] Anastasios I. Mourikis, Nikolas Trawny, Stergios I. Roumeliotis,etc
"Autonomous Stair Climbing for Tracked Vehicles" The International
Journal of Robotics Research, Vol. 26, No. 7, 737-758 (2007)
[7] G.Daugman. "Uncertainty relation for resolution in space,
spatial-frequency, and orientation optimized by two-dimensional visual
cortical filters". J.OPT.Soc.Am., 2(7):1160-1169,1985
[8] Tai Sing Lee. "Image Representation Using 2D Gabor Wavelet" IEEE
Trans. on Pattern Analysis and Machine Intelligence, 1996,
18(10):959-971
[9] J. K. Kamarainen, V. Kyrki and H. Kalviainen. "Invariance Properties of
Gabor Filter-Based Features" Overview and Applications. IEEE Trams.
On Image Processing, 2006, 15(5):1088 1099
[10] M.A.Fischler and R.C.Bolls. Random sample consensus: A paradigm for
model fitting with application to image analysis and automated
cartography. Communication of the ACM, 24(6):381-395,1981
[11] D.R.Myatt, P.H.S.Torr, S.J.Nasuto, J.M.Bishop, and
R.Craddock.Napsac :High noise, high dimensional robust estimation-
it's in the bag. British Machine Visioin Conference, Cardiff, UK, pages
The outdoor condition 458-467,2002.
Fig. 10 The results under various conditions [12] 0. Chum and J. Matas. Randomized ransac with t(d,d) test. British
Machine Vision Conference, Cardi*), UK, pages 448 {457, 2002.
Fig. 11 A steering processing when the UGV are mounted on the side of the
stair
1811
Authorized licensed use limited to: INDIAN INSTITUTE OF TECHNOLOGY MADRAS. Downloaded on March 20,2010 at 06:18:51 EDT from IEEE Xplore. Restrictions apply.