000 04385nas|a2200517 a 4500
005 20260818090355.0
008 170313s2013 th uu|m rtt 0| a1eng d
035 _a.b12180440
099 9 _aAIT Diss. no.CS-13-02
100 1 _aAli, Irshad
245 1 0 _aDetection and tracking of multiple humans in high-density crowds
260 _aPathum Thani, Thailand :
_bAsian Institute of Technology,
_c2013
300 _a68 p. :
_bill.
490 1 _aDissertation ;
_vno. CS-13-02
500 _aA dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Computer Science, School of Engineering and Technology
502 _aThesis (Ph.D.) - Asian Institute of Technology, 2013
520 _aAs public concern about crime and terrorist activity increases, the importance of public security is growing, and video surveillance systems are increasingly widespread tools for monitoring, management, and law enforcement in public areas. At the same time, video surveillance systems have become a popular research area in computer vision. Many algorithms exist to detect and track people in video streams. However, human detection and tracking in high density crowds, where object occlusion is very high, is still an unsolved problem. Pre-processing techniques such as background subtraction fail in such situations. The emphasis in this work is on the development of a fully automatic algorithm to detect and track multiple humans in high-density crowds in the presence of extreme occlusion. Typical approaches such as background modeling and body part-based pedestrian detection fail when most of the scene is in motion and most body parts of most of the pedestrians are occluded. Under these conditions, we believe that the head is the only body part that can be robustly detected and tracked. In this dissertation, we therefore present a method for tracking pedestrians that detects and tracks heads rather than full bodies. First, we use a Viola and Jones AdaBoost detection cascade to detect human heads in images. However, we do not rely particularly on the Viola and Jones method. Our method will improve upon the raw results of any head detector using a blend of detection, appearance-based tracking, and incremental head plane estimation. Any effective head detector could be plugged into our algorithm if it is capable of detecting heads in crowds.
650 0 _aElectronic surveillance
650 0 _aComputer vision
650 0 _aSignal detection
700 1 _aDailey, Mathew N.,
_eChairperson
700 1 _aAfzulpurkar, Nitin V.,
_eExamination Committee
700 1 _aDuboz, Raphael,
_eExamination Committee
700 1 _aOrwell, James,
_eExamination committee
710 2 _aHigher Education Commission (HEC), Pakistan,
_eScholarship donor
710 2 _aAsian Institute of Technology Fellowship,
_eScholarship donor
810 2 _aAsian Institute of Technology.
_tDissertation ;
_vno. CS-13-02
856 _3Full-Text
_uhttp://203.159.5.9/ait-thesis/detail.php?q=B00295
907 _a.b12180440
_bmnait
_cm
902 _a240411
998 _b0
_c170313
_dm
_ea
_fm
_g0
962 _a000:001:PDF:b1218044:003023:0:0:0:0:0:0
_tAbstract--AIT Diss. no.CS-13-02
_vn
945 _lmnait
945 _lmnait
945 _lmnarc
945 _lmnarc
945 _lmnarc
942 _c20
942 _c40
909 _aBarcode : 30050120407712
_bCREATED : 2017-03-13
_cRECORD # : i13069627
_dLPATRON : 0
_eLCHKIN : -
_f# RENEWALS : 0
_g# OVERDUE : 0
_hIUSE3 : 0
_iTOT CHKOUT : 0
_jTOT RENEW : 0
909 _aBarcode : 30050120407688
_bCREATED : 2017-03-13
_cRECORD # : i13069639
_dLPATRON : 1015151
_eLCHKIN : 2019-02-04
_f# RENEWALS : 0
_g# OVERDUE : 0
_hIUSE3 : 0
_iTOT CHKOUT : 1
_jTOT RENEW : 4
909 _aBarcode : 30050120405914
_bCREATED : 2017-05-04
_cRECORD # : i13073734
_dLPATRON : 0
_eLCHKIN : -
_f# RENEWALS : 0
_g# OVERDUE : 0
_hIUSE3 : 0
_iTOT CHKOUT : 0
_jTOT RENEW : 0
909 _aBarcode : 30050120978134
_bCREATED : 2020-09-18
_cRECORD # : i13297302
_dLPATRON : 0
_eLCHKIN : -
_f# RENEWALS : 0
_g# OVERDUE : 0
_hIUSE3 : 0
_iTOT CHKOUT : 0
_jTOT RENEW : 0
909 _aBarcode : 30050120978126
_bCREATED : 2020-09-18
_cRECORD # : i13297314
_dLPATRON : 0
_eLCHKIN : -
_f# RENEWALS : 0
_g# OVERDUE : 0
_hIUSE3 : 0
_iTOT CHKOUT : 0
_jTOT RENEW : 0
999 _c27879
_d27879