This Article 
 Bibliographic References 
 Add to: 
Adaptive Termination of Voting in the Probabilistic Circular Hough Transform
September 1994 (vol. 16 no. 9)
pp. 911-915

Reliable detection of objects using the Hough transform is often possible even if just a small random poll of edge points is used for voting. This can lead to significant computational savings. To reduce the risk of errors, it is customary to preset the poll size to a value that is much larger than necessary in average conditions. An adaptive setting of the poll size in the probabilistic Hough transform is suggested. It is experimentally demonstrated that by monitoring changes in the ranks of peaks in the parameter space, sensible decisions on voting termination can be made. Adaptive stopping leads to polls that are on average smaller than the fixed poll that leads to the same error rate. In many applications the number of objects to be detected is unknown. Finding the number of appearances of an object in a noisy image is difficult, especially with partial data. The authors present an adaptive stopping rule that terminates voting as soon as any number of objects seem to be reliably detected, even though the existence of others may not be ruled out yet.

[1] F. Ade, M. Peter, M. Rutishauser, M. Trobina, and A. Ylä-Jääski, "A 3-D vision system for deriving gripping information for a robot," inProc. 8th SCIA, Tromsø, Norway, May 1993.
[2] G. Gerig, "Linking image-space and accumulator-space: A new approach for object recognition," inProc. 1st ICCV, London, 1987, pp. 112-117.
[3] W. E. L. Grimson and D. P. Huttenlocher, "On the verification of hypothesized matches in model-based recognition,"IEEE Trans. Pattern Anal. Machine Intell., vol. 13, pp. 1201-1213, 1991.
[4] N. Kiryati, Y. Eldar, and A. Bruckstein, "A probabilistic Hough transform,"Patt. Recog., vol. 24, pp. 303-316, 1991.
[5] V. F. Leavers, "Which Hough transform,"CVGIP: Image Understanding, vol. 158, pp. 250-264, 1993.
[6] J. Sheinvald, B. Dom, W. Niblack, and S. Banerjee, "Detecting parametrized curve segments using MDL and the Hough transform," inProc. CVPR'92, Champaign, Illinois, June 1992, pp. 547-552.
[7] J. Sklansky, "On the Hough technique for curve detection,"IEEE Trans. Comput., vol. C-27, pp. 923-926, 1978.
[8] L. Xu, E. Oja, and P. Kultanen, "A new curve detection method: Randomized Hough transform (RHT),"Patt. Recognition Lett., vol. 11, pp. 331-338, 1990.
[9] A. Ylä-Jääski, "Contributions to a 3-D robot vision system: Grouping from sparse and incomplete data,"Acta Polytechnica Scandinavica, Elect. Eng. Ser. No. 73, Helsinki, 1993.

Index Terms:
Hough transforms; probability; edge detection; adaptive termination; probabilistic circular Hough transform; objects detection; small random poll; edge points; computational savings; risk of errors; peaks; parameter space; decisions; voting termination; adaptive stopping; noisy image
A. Ylä-Jääski, N. Kiryati, "Adaptive Termination of Voting in the Probabilistic Circular Hough Transform," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 9, pp. 911-915, Sept. 1994, doi:10.1109/34.310688
Usage of this product signifies your acceptance of the Terms of Use.