TY - JOUR
T1 - Adaptive Termination of Voting in the Probabilistic Circular Hough Transform
AU - YlaJaaski, Antti
AU - Kiryati, Nahum
N1 - Funding Information:
Manuscript received August I, 1992; revised January 4, 1994. This work whs supported the ETH through the project “Cooperating Robot with Visual and Tactile Skills,” by the Technion VPK Funds: E. and I. Bishop Fund and I. Goldberg Fund, and by the Fund for the Promotion of Research at the Technion. Recommended for acceptance by Associate Editor B. Bhdnu. 4. Yla-Jaaski was with the Image Science Group, Communication Technology Laboratory, ETH-Zurich, Switzerland. He is now with Nokia Research Center, P.O. Box 45, FIN-0021 1 Helsinki, Finland. V. Kiryati was with the Image Science Group, Communication Technology Laboratory, ETH-Zurich, Switzerland. He is now with the Department of Elctrical Engineering, Technion-Israel Institute of Technology, Haifa 32000, Israel; e-mail: [email protected]. IEEE Log Number 9403776.
PY - 1994/9
Y1 - 1994/9
N2 - 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. 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 in 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. We 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.
AB - 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. 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 in 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. We 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.
KW - Adaptive algorithms
KW - probabilistic hough transform
KW - stopping rules
UR - https://www.scopus.com/pages/publications/0028499282
U2 - 10.1109/34.310688
DO - 10.1109/34.310688
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:0028499282
SN - 0162-8828
VL - 16
SP - 911
EP - 915
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
IS - 9
ER -