Automatic inference of geometric camera parameters and inter-camera topology in uncalibrated disjoint surveillance cameras

Person tracking across non-overlapping cameras and other types of video analytics benefit from spatial calibration information that allows an estimation of the distance between cameras and a relation between pixel coordinates and world coordinates within a camera. In a large environment with many cameras, or for frequent ad-hoc deployments of cameras, the cost of this calibration is high. This creates a barrier for the use of video analytics. Automating the calibration allows for a short configuration time, and the use of video analytics in a wider range of scenarios, including ad-hoc crisis situations and large scale surveillance systems. We show an autocalibration method entirely based on pedestrian detections in surveillance video in multiple non-overlapping cameras. In this paper, we show the two main components of automatic calibration. The first shows the intra-camera geometry estimation that leads to an estimate of the tilt angle, focal length and camera height, which is important for the conversion from pixels to meters and vice versa. The second component shows the inter-camera topology inference that leads to an estimate of the distance between cameras, which is important for spatio-temporal analysis of multi-camera tracking. This paper describes each of these methods and provides results on realistic video data.

[1]  Anton van den Hengel,et al.  Large-Scale Camera Topology Mapping: Application to Re-identification , 2014, Person Re-Identification.

[2]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[3]  Xiaoyan Sun,et al.  Particle Filter-Based Object Tracking and Handover in Disjoint View Multi-Cameras , 2014 .

[4]  Horst Bischof,et al.  People tracking across two distant self-calibrated cameras , 2007, 2007 IEEE Conference on Advanced Video and Signal Based Surveillance.

[5]  Peng Wang,et al.  Activity-Based Scene Decomposition for Topology Inference of Video Surveillance Network , 2014, J. Electr. Comput. Eng..

[6]  Shishir K. Shah,et al.  A survey of approaches and trends in person re-identification , 2014, Image Vis. Comput..

[7]  Tim J. Ellis,et al.  Learning multi-planar scene models in multi-camera videos , 2015, IET Comput. Vis..

[8]  Yanxi Liu,et al.  Automatic Surveillance Camera Calibration without Pedestrian Tracking , 2011, BMVC.

[9]  Dimitrios Makris,et al.  Bridging the gaps between cameras , 2004, CVPR 2004.

[10]  Amit K. Roy-Chowdhury,et al.  Determining Topology in a Distributed Camera Network , 2007, 2007 IEEE International Conference on Image Processing.

[11]  Jasper R. van Huis,et al.  Automatic detection of suspicious behavior of pickpockets with track-based features in a shopping mall , 2014, Security and Defence.

[12]  W. Eric L. Grimson,et al.  Inference of non-overlapping camera network topology by measuring statistical dependence , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[13]  Xiaogang Wang,et al.  Intelligent multi-camera video surveillance: A review , 2013, Pattern Recognit. Lett..

[14]  Pietro Perona,et al.  The Fastest Pedestrian Detector in the West , 2010, BMVC.

[15]  Dacheng Tao,et al.  Sparse Camera Network for Visual Surveillance -- A Comprehensive Survey , 2013, ArXiv.

[16]  Jenq-Neng Hwang,et al.  Consistent Human Tracking Over Self-organized and Scalable Multiple-camera Networks , 2014 .

[17]  Hassan Foroosh,et al.  Robust Auto-Calibration from Pedestrians , 2006, 2006 IEEE International Conference on Video and Signal Based Surveillance.

[18]  Michael Werman,et al.  Scene geometry from moving objects , 2014, 2014 11th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[19]  Ramakant Nevatia,et al.  Inter-camera Association of Multi-target Tracks by On-Line Learned Appearance Affinity Models , 2010, ECCV.

[20]  W. Eric L. Grimson,et al.  Correspondence-Free Activity Analysis and Scene Modeling in Multiple Camera Views , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  J. Kruskal.  Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis , 1964 .

[22]  Paulo R. S. Mendonça,et al.  Bayesian autocalibration for surveillance , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[23]  Shaogang Gong,et al.  Multi-camera activity correlation analysis , 2009, CVPR.

[24]  Jong Hyuk Park,et al.  Inference topology of distributed camera networks with multiple cameras , 2012, Multimedia Tools and Applications.

[25]  Raúl Mohedano del Pozo,et al.  Capabilities and limitations of mono-camera pedestrian-based autocalibration , 2010, ICIP 2010.

[26]  Klamer Schutte,et al.  Instantaneous threat detection based on a semantic representation of activities, zones and trajectories , 2014, Signal, Image and Video Processing.

[27]  Paulo R. S. Mendonça,et al.  Autocalibration from Tracks of Walking People , 2006, BMVC.

[28]  Henri Bouma,et al.  Real-time tracking and fast retrieval of persons in multiple surveillance cameras of a shopping mall , 2013, Defense, Security, and Sensing.

[29]  Tieniu Tan,et al.  Object tracking across non-overlapping views by learning inter-camera transfer models , 2014, Pattern Recognit..

[30]  Ramakant Nevatia,et al.  Camera calibration from video of a walking human , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Andrew Gilbert,et al.  Incremental, scalable tracking of objects inter camera , 2008, Comput. Vis. Image Underst..