TY - GEN
T1 - Robust autocalibration for a surveillance camera network
AU - Liu, Jingchen
AU - Collins, Robert T.
AU - Liu, Yanxi
PY - 2013
Y1 - 2013
N2 - We propose a novel approach for multi-camera autocalibration by observing multiview surveillance video of pedestrians walking through the scene. Unlike existing methods, we do NOT require tracking or explicit correspondences of the same person across time/views. Instead, we take noisy foreground blobs as the only input and rely on a joint optimization framework with robust statistics to achieve accurate calibration under challenging scenarios. First, each individual camera is roughly calibrated into its local World Coordinate System (lWCS) based on analysis of relative 3D pedestrian height distribution. Then, all lWCSs are iteratively registered with respect to a shared global World Coordinate System (gWCS) by incorporating robust matching with a partial Direct Linear Transform (pDLT). As demonstrated by extensive evaluation, our algorithm achieves satisfactory results in various camera settings with up to moderate crowd densities with a large proportion of foreground outliers.
AB - We propose a novel approach for multi-camera autocalibration by observing multiview surveillance video of pedestrians walking through the scene. Unlike existing methods, we do NOT require tracking or explicit correspondences of the same person across time/views. Instead, we take noisy foreground blobs as the only input and rely on a joint optimization framework with robust statistics to achieve accurate calibration under challenging scenarios. First, each individual camera is roughly calibrated into its local World Coordinate System (lWCS) based on analysis of relative 3D pedestrian height distribution. Then, all lWCSs are iteratively registered with respect to a shared global World Coordinate System (gWCS) by incorporating robust matching with a partial Direct Linear Transform (pDLT). As demonstrated by extensive evaluation, our algorithm achieves satisfactory results in various camera settings with up to moderate crowd densities with a large proportion of foreground outliers.
UR - http://www.scopus.com/inward/record.url?scp=84875618353&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84875618353&partnerID=8YFLogxK
U2 - 10.1109/WACV.2013.6475051
DO - 10.1109/WACV.2013.6475051
M3 - Conference contribution
AN - SCOPUS:84875618353
SN - 9781467350532
T3 - Proceedings of IEEE Workshop on Applications of Computer Vision
SP - 433
EP - 440
BT - 2013 IEEE Workshop on Applications of Computer Vision, WACV 2013
T2 - 2013 IEEE Workshop on Applications of Computer Vision, WACV 2013
Y2 - 15 January 2013 through 17 January 2013
ER -