Multi-Camera Positioning for Automated Tracking Systems in Dynamic Environments

Most existing camera placement algorithms focus on coverage and/or visibility analysis, which ensures that the object of interest is visible in the camera's field of view (FOV). According to recent literature, handoff safety margin is introduced to sensor planning so that sufficient overlapped FOVs among adjacent cameras are reserved for successful and smooth target transition. In this paper, we investigate the sensor planning problem when considering the dynamic interactions between moving targets and observing cameras. The probability of camera overload is explored to model the aforementioned interactions. The introduction of the probability of camera overload also considers the limitation that a given camera can simultaneously monitor or track a fixed number of targets and incorporates the target's dynamics into sensor planning. The resulting camera placement not only achieves the optimal balance between coverage and handoff success rate but also maintains the optimal balance in environments with various target densities. The proposed camera placement method is compared with a reference algorithm by Erdem and Sclaroff. Consistently improved handoff success rate is illustrated via experiments using typical office floor plans with various target densities.

[1]  Michel Bierlaire,et al.  Behavioral Priors for Detection and Tracking of Pedestrians in Video Sequences , 2006, International Journal of Computer Vision.

[2]  Shengyong Chen,et al.  Active Sensor Planning for Multiview Vision Tasks , 2008 .

[3]  M. Saadatseresht,et al.  Automatic Camera Placement in Vision Metrology Based On A Fuzzy Inference System , 2005 .

[4]  Nikolaos Papanikolopoulos,et al.  Optimal Camera Placement for Automated Surveillance Tasks , 2007, J. Intell. Robotic Syst..

[5]  Mongi A. Abidi,et al.  Camera handoff with adaptive resource management for multi-camera multi-object tracking , 2010, Image Vis. Comput..

[6]  Subhashis Banerjee,et al.  Recognizing large isolated 3-D objects through next view planning using inner camera invariants , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[7]  Nikolaos Papanikolopoulos,et al.  Multi-camera positioning to optimize task observability , 2005, IEEE Conference on Advanced Video and Signal Based Surveillance, 2005..

[8]  MengChu Zhou,et al.  Adaptive Sensor Placement and Boundary Estimation for Monitoring Mass Objects , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[9]  Larry S. Davis,et al.  COST: An Approach for Camera Selection and Multi-Object Inference Ordering in Dynamic Scenes , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[10]  Kishor S. Trivedi.  Probability and Statistics with Reliability, Queuing, and Computer Science Applications , 1984 .

[11]  Larry S. Davis,et al.  Task Scheduling in Large Camera Networks , 2007, ACCV.

[12]  Jake K. Aggarwal,et al.  Tracking Human Motion in Structured Environments Using a Distributed-Camera System , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Livier Reithler,et al.  Optimal deployment of cameras for video surveillance systems , 2007, 2007 IEEE Conference on Advanced Video and Signal Based Surveillance.

[14]  Stan Sclaroff,et al.  Automated camera layout to satisfy task-specific and floor plan-specific coverage requirements , 2006, Comput. Vis. Image Underst..

[15]  Enrique Dunn,et al.  Parisian camera placement for vision metrology , 2006, Pattern Recognit. Lett..

[16]  Y.F. Li,et al.  Automatic sensor placement for model-based robot vision , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[17]  Mongi A. Abidi,et al.  Can You See Me Now? Sensor Positioning for Automated and Persistent Surveillance , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[18]  Christophe Dumont,et al.  Next best view system in a 3D object modeling task , 1999, Proceedings 1999 IEEE International Symposium on Computational Intelligence in Robotics and Automation. CIRA'99 (Cat. No.99EX375).

[19]  John J. Fruin,et al.  Pedestrian planning and design , 1971 .

[20]  Nikolaos Papanikolopoulos,et al.  Multi-Camera Human Activity Monitoring , 2008, J. Intell. Robotic Syst..

[21]  V. K. Singh,et al.  A design methodology for selection and placement of sensors in multimedia surveillance systems , 2006, VSSN '06.

[22]  Pascal Frossard,et al.  Omnidirectional Views Selection for Scene Representation , 2006, 2006 International Conference on Image Processing.

[23]  Masatsugu Kidode,et al.  Multiple Active Camera Assignment for High Fidelity 3D Video , 2006, Fourth IEEE International Conference on Computer Vision Systems (ICVS'06).

[24]  Mongi A. Abidi,et al.  Sensor planning for automated and persistent object tracking with multiple cameras , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Thierry Siméon,et al.  Planning human walk in virtual environments , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[26]  D. Terzopoulos,et al.  Towards intelligent camera networks: a virtual vision approach , 2005, 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance.

[27]  Mongi A. Abidi,et al.  Camera Handoff with Adaptive Resource Management for Multi-camera Multi-target Surveillance , 2008, 2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance.

[28]  Xing Chen,et al.  An occlusion metric for selecting robust camera configurations , 2008, Machine Vision and Applications.

[29]  Mongi A. Abidi,et al.  Sensor planning for PTZ cameras using the probability of camera overload , 2008, 2008 19th International Conference on Pattern Recognition.

[30]  Subhashis Banerjee,et al.  Active recognition through next view planning: a survey , 2004, Pattern Recognit..

[31]  Sanjeev Khanna,et al.  Target tracking with distributed sensors: The focus of attention problem , 2005, Comput. Vis. Image Underst..

[32]  Pierre David,et al.  A Sensor Placement Approach for the Monitoring of Indoor Scenes , 2007, EuroSSC.

[33]  R. Lienhart,et al.  On the optimal placement of multiple visual sensors , 2006, VSSN '06.

[34]  Ioannis Pavlidis,et al.  Urban surveillance systems: from the laboratory to the commercial world , 2001, Proc. IEEE.

[35]  Larry S. Davis,et al.  Visibility Analysis and Sensor Planning in Dynamic Environments , 2004, ECCV.

[36]  Steve Benford,et al.  Can you see me now? , 2006, TCHI.

[37]  Ser-Nam Lim,et al.  Constructing task visibility intervals for a surveillance system , 2005, VSSN@MM.