TY - JOUR
T1 - Inlier clustering based on the residuals of random hypotheses
AU - Kutbi, Mohammed
AU - Chang, Yizhe
AU - Mordohai, Philippos
N1 - Publisher Copyright:
© 2021
PY - 2021/10
Y1 - 2021/10
N2 - We present an approach for motion clustering based on a novel observation that a signature for putative pixel correspondences can be generated by collecting their residuals with respect to model hypotheses drawn randomly from the data. Inliers of the same motion cluster should have strongly correlated residuals, which are low when a hypothesis is consistent with the data in the cluster and high otherwise. After evaluating a number of hypotheses, members of the same cluster can be identified based on these correlations. Due to this property, we named our approach Inlier Clustering based on the Residuals of Random Hypotheses (ICR). An important advantage of ICR is that it does not require an inlier-outlier threshold or parameter tuning. In addition, we propose a supervised recursive formulation of ICR (r-ICR) that, unlike many motion clustering methods, does not require the number of clusters to be known a priori, as long as annotated data are available for training. We validate ICR and r-ICR on several publicly available datasets for robust geometric model fitting.
AB - We present an approach for motion clustering based on a novel observation that a signature for putative pixel correspondences can be generated by collecting their residuals with respect to model hypotheses drawn randomly from the data. Inliers of the same motion cluster should have strongly correlated residuals, which are low when a hypothesis is consistent with the data in the cluster and high otherwise. After evaluating a number of hypotheses, members of the same cluster can be identified based on these correlations. Due to this property, we named our approach Inlier Clustering based on the Residuals of Random Hypotheses (ICR). An important advantage of ICR is that it does not require an inlier-outlier threshold or parameter tuning. In addition, we propose a supervised recursive formulation of ICR (r-ICR) that, unlike many motion clustering methods, does not require the number of clusters to be known a priori, as long as annotated data are available for training. We validate ICR and r-ICR on several publicly available datasets for robust geometric model fitting.
KW - Clustering
KW - Model estimation
KW - Motion segmentation
UR - http://www.scopus.com/inward/record.url?scp=85111322015&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85111322015&partnerID=8YFLogxK
U2 - 10.1016/j.patrec.2021.07.007
DO - 10.1016/j.patrec.2021.07.007
M3 - Article
AN - SCOPUS:85111322015
SN - 0167-8655
VL - 150
SP - 101
EP - 107
JO - Pattern Recognition Letters
JF - Pattern Recognition Letters
ER -