caa a22 4500 605540543 CHVBK 20210128100912.0 cr unu---uuuuu 210128e20151001xx s 000 0 eng 10.1007/s00371-014-1022-6 doi (NATIONALLICENCE)springer-10.1007/s00371-014-1022-6 Unique people count from monocular videos [Elektronische Daten] [Satarupa Mukherjee, Stephani Gil, Nilanjan Ray] Counting unique number of people in a video (i.e., counting a person only once while the person passes through the field of view) is required in many video analytic applications, such as transit passenger and pedestrian volume count in railway stations, malls, and road intersections. The principal roadblock here is occlusion. To avoid this bottleneck, we adopt a combination of (a) a radical new approach of unique influx and outflux count (UIOC) of people within a region of interest (ROI), which is adopted from computational fluidics, (b) a nonlinear regressor to estimate the number of people within a ROI, and (c) ROI boundary tracking (as opposed to object or feature tracking) for a short period. In UIOC, we compute influx/outflux rate, i.e., number of people entering or exiting the ROI per unit time. Then, we sum the influx/outflux rate between any two time points to estimate the number of people that entered and/or left the ROI within that time interval. Our framework is validated on 19 publicly available datasets, with abundant occlusion, obtaining more than 95% accuracy for each video. Our framework is online and real time. Our framework is comparatively inexpensive to install and operate as only one camera is used. These features make the proposed framework suitable for low-cost, small-business/residential and/or commercial applications. We also extend our framework beyond monocular videos and apply it on multiple views of a publicly available dataset with about 99% accuracy. Springer-Verlag Berlin Heidelberg, 2014 Unique people count nationallicence Influx nationallicence Outflux nationallicence Occlusion nationallicence Boundary tracking nationallicence Mukherjee Satarupa Department of Computing Sciences, University of Alberta, Edmonton, Canada aut Gil Stephani Department of Computing Sciences, University of Alberta, Edmonton, Canada aut Ray Nilanjan Department of Computing Sciences, University of Alberta, Edmonton, Canada aut The Visual Computer Springer Berlin Heidelberg 31/10(2015-10-01), 1405-1417 0178-2789 31:10<1405 2015 31 371 https://doi.org/10.1007/s00371-014-1022-6 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00371-014-1022-6 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Mukherjee Satarupa Department of Computing Sciences, University of Alberta, Edmonton, Canada aut NATIONALLICENCE 700 1- Gil Stephani Department of Computing Sciences, University of Alberta, Edmonton, Canada aut NATIONALLICENCE 700 1- Ray Nilanjan Department of Computing Sciences, University of Alberta, Edmonton, Canada aut NATIONALLICENCE 773 0- The Visual Computer Springer Berlin Heidelberg 31/10(2015-10-01), 1405-1417 0178-2789 31:10<1405 2015 31 371