US 11,704,936 B2
Object tracking and best shot detection system
Paul C Brewer, Arlington, VA (US); Dana Eubanks, Herndon, VA (US); Himaanshu Gupta, Herndon, VA (US); W. Andrew Scanlon, Falls Church, VA (US); Peter L Venetianer, McLean, VA (US); Weihong Yin, Great Falls, VA (US); Li Yu, Sterling, VA (US); and Zhong Zhang, Great Falls, VA (US)
Assigned to MOTOROLA SOLUTIONS, INC., Chicago, IL (US)
Filed by AVIGILON FORTRESS CORPORATION, Vancouver (CA)
Filed on Feb. 23, 2022, as Appl. No. 17/678,202.
Application 17/678,202 is a division of application No. 16/749,334, filed on Jan. 22, 2020, granted, now 11,288,495.
Application 16/749,334 is a division of application No. 15/842,925, filed on Dec. 15, 2017, granted, now 10,546,186, issued on Jan. 8, 2020.
Application 14/884,778 is a division of application No. 13/804,280, filed on Mar. 14, 2013, granted, now 9,195,883, issued on Nov. 4, 2015.
Application 15/842,925 is a continuation of application No. 14/884,778, filed on Oct. 16, 2015, granted, now 9,858,474, issued on Dec. 13, 2017.
Claims priority of provisional application 61/621,703, filed on Apr. 9, 2012.
Prior Publication US 2022/0375262 A1, Nov. 24, 2022
Int. Cl. G06V 20/52 (2022.01); G06V 40/16 (2022.01)
CPC G06V 40/174 (2022.01) [G06V 20/52 (2022.01); G06V 40/173 (2022.01)] 10 Claims
OG exemplary drawing
 
1. A video surveillance system for automatically tracking a target, the system comprising:
one or more image capture devices; and
a computer system including one or more computer readable storage media configured to:
receive a plurality of face images of a particular face that were captured by the one or more image capture devices during a time period;
for each respective face image in the plurality of face images, determine a respective rating based on a plurality of features;
compare the respective ratings for the respective face images to each other to identify a highest rating from among the respective ratings for the respective face images;
identify a best face image to which the highest rating corresponds;
associate the best face image with tracked object in a log based on body association information, wherein the tracked object corresponds to the target; and
use the best face image as an index to supplement tracking of the target.