Network exploitation using WAMI tracks

Creating and exploiting network models from wide area motion imagery (WAMI) is an important task for intelligence analysis. Tracks of entities observed moving in the WAMI sensor data are extracted, then large numbers of tracks are studied over long time intervals to determine specific locations that are visited (e.g., buildings in an urban environment), what locations are related to other locations, and the function of each location. This paper describes several parts of the network detection/exploitation problem, and summarizes a solution technique for each: (a) Detecting nodes; (b) Detecting links between known nodes; (c) Node attributes to characterize a node; (d) Link attributes to characterize each link; (e) Link structure inferred from node attributes and vice versa; and (f) Decomposing a detected network into smaller networks. Experimental results are presented for each solution technique, and those are used to discuss issues for each problem part and its solution technique.

[1]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[2]  Michael A. West,et al.  Hierarchical priors and mixture models, with applications in regression and density estimation , 2006 .

[3]  M. R. Brito,et al.  Connectivity of the mutual k-nearest-neighbor graph in clustering and outlier detection , 1997 .

[4]  Jae Young Lee,et al.  Recognizing wide-area and process-type activities , 2007, 2007 10th International Conference on Information Fusion.

[5]  Carl E. Rasmussen,et al.  The Infinite Gaussian Mixture Model , 1999, NIPS.

[6]  John A. Antoniades,et al.  Autonomous real-time ground ubiquitous surveillance-imaging system (ARGUS-IS) , 2008, SPIE Defense + Commercial Sensing.

[7]  Don R. Hush,et al.  Wide-Area Motion Imagery , 2010, IEEE Signal Processing Magazine.

[8]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[9]  David M. Blei,et al.  Hierarchical relational models for document networks , 2009, 0909.4331.

[10]  Michael I. Jordan,et al.  Hierarchical Dirichlet Processes , 2006 .

[11]  Raymond D. Rimey,et al.  Temporal structure methods for image-based change analysis , 2008, 2008 37th IEEE Applied Imagery Pattern Recognition Workshop.

[12]  J. D. Morrison,et al.  A framework for activity detection in wide-area motion imagery , 2009, Defense + Commercial Sensing.

[13]  Shashi Shekhar,et al.  Mining Personally Important Places from GPS Tracks , 2007, 2007 IEEE 23rd International Conference on Data Engineering Workshop.

[14]  Eric Horvitz,et al.  Predestination: Inferring Destinations from Partial Trajectories , 2006, UbiComp.

[15]  Lawrence Carin,et al.  Nonparametric factor analysis with beta process priors , 2009, ICML '09.

[16]  Henry A. Kautz,et al.  Learning and inferring transportation routines , 2004, Artif. Intell..

[17]  Matthias Grossglauser,et al.  A parsimonious model of mobile partitioned networks with clustering , 2009, 2009 First International Communication Systems and Networks and Workshops.

[18]  Charu C. Aggarwal,et al.  Graph Data Management and Mining: A Survey of Algorithms and Applications , 2010, Managing and Mining Graph Data.

[19]  Raymond D. Rimey.  Recognizing Activity Structures in Massive Numbers of Simple Events Over Large Areas , 2011 .

[20]  Stefan Wrobel,et al.  Visual analytics tools for analysis of movement data , 2007, SKDD.

[21]  Xing Xie,et al.  GeoLife: A Collaborative Social Networking Service among User, Location and Trajectory , 2010, IEEE Data Eng. Bull..

[22]  Matthew Richardson,et al.  Markov logic networks , 2006, Machine Learning.

[23]  Georgiy Levchuk,et al.  Identification of Adversarial Activities: Profiling Latent Uses of Facilities from Structural Data and Real-time Intelligence , 2008 .