Trajectory association across multiple airborne cameras

被引:21
|
作者
Sheikh, Yaser Ajmal [1 ]
Shah, Mubarak [2 ]
机构
[1] Carnegie Mellon Univ, Inst Robot, Pittsburgh, PA 15213 USA
[2] Univ Cent Florida, Sch Elect Engn & Comp Sci, Orlando, FL 32816 USA
关键词
applications; scene analysis; motion; sensor fusion; registration;
D O I
10.1109/TPAMI.2007.70750
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A camera mounted on an aerial vehicle provides an excellent means to monitor large areas of a scene. Utilizing several such cameras on different aerial vehicles allows further flexibility in terms of increased visual scope and in the pursuit of multiple targets. In this paper, we address the problem of associating trajectories across multiple moving airborne cameras. We exploit geometric constraints on the relationship between the motion of each object across cameras without assuming any prior calibration information. Since multiple cameras exist, ensuring coherency in association is an essential requirement, e. g., that transitive closure is maintained between more than two cameras. To ensure such coherency, we pose the problem of maximizing the likelihood function as a k-dimensional matching and use an approximation to find the optimal assignment of association. Using the proposed error function, canonical trajectories of each object and optimal estimates of intercamera transformations ( in a maximum likelihood sense) are computed. Finally, we show that, as a result of associating trajectories across the cameras, under special conditions, trajectories interrupted due to occlusion or missing detections can be repaired. Results are shown on a number of real and controlled scenarios with multiple objects observed by multiple cameras, validating our qualitative models, and, through simulation, quantitative performance is also reported.
引用
收藏
页码:361 / 367
页数:7
相关论文
共 50 条
  • [1] Trajectory association and fusion across partially overlapping cameras
    Anjum, Nadeem
    Cavallaro, Andrea
    [J]. AVSS: 2009 6TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE, 2009, : 201 - 206
  • [2] Object tracking across multiple independently moving airborne cameras
    Sheikh, Y
    Shah, M
    [J]. TENTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS 1 AND 2, PROCEEDINGS, 2005, : 1555 - 1560
  • [3] Trajectory association across non-overlapping moving cameras in planar scenes
    Sheikh, Yaser
    Li, Xin
    Shah, Mubarak
    [J]. 2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8, 2007, : 1620 - +
  • [4] Multi-pose Volume Reconstruction Across Arbitrary Trajectory from Multiple Fisheye Cameras
    Kottari, Konstantina
    Delibasis, Konstantinos
    [J]. ARTIFICIAL INTELLIGENCE APPLICATIONS AND INNOVATIONS, 2015, 458 : 29 - 44
  • [5] Tracking across multiple cameras with disjoint views
    Javed, O
    Rasheed, Z
    Shafique, K
    Shah, M
    [J]. NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS I AND II, PROCEEDINGS, 2003, : 952 - 957
  • [6] An Efficient Method of Tracking across Multiple Cameras
    Hassan, Muhammad
    Mehmood, Ahsen
    Khan, Muhammad Faisal
    [J]. TRUSTCOM 2011: 2011 INTERNATIONAL JOINT CONFERENCE OF IEEE TRUSTCOM-11/IEEE ICESS-11/FCST-11, 2011, : 1477 - 1481
  • [7] Trajectory Ensemble: Multiple Persons Consensus Tracking across Non-overlapping Multiple Cameras over Randomly Dropped Camera Networks
    Kawanishi, Yasutomo
    Deguchi, Daisuke
    Ide, Ichiro
    Murase, Hiroshi
    [J]. 2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2017, : 1471 - 1477
  • [8] People Reacquisition across Multiple Cameras with Disjoint Views
    Cong, D. -N. Truong
    Khoudour, L.
    Achard, C.
    [J]. IMAGE AND SIGNAL PROCESSING, PROCEEDINGS, 2010, 6134 : 488 - +
  • [9] Video Sequences Association for People Re-identification across Multiple Non-overlapping Cameras
    Gong, Dung Nghi Truong
    Achard, Catherine
    Khoudour, Louahdi
    Douadi, Lounis
    [J]. IMAGE ANALYSIS AND PROCESSING - ICIAP 2009, PROCEEDINGS, 2009, 5716 : 179 - +
  • [10] Parametric Tracking Across Multiple Cameras with Spatial Estimation
    Sebastian, Patrick
    Vooi Voon, Yap
    Comley, Richard
    [J]. IETE JOURNAL OF RESEARCH, 2023, 69 (02) : 839 - 853