Target Tracking in Sensor Networks

1. Target Tracking in Sensor Networks Choong Seon Hong Kyung Hee University cshong@khu.ac.kr

2. Tracking • One of the most important applications of sensors is target tracking. • Each node can sense in multiple modalities such as acoustic, seismic and infrared. • The type of signals to be sensed are determined by the objects to be tracked • Given a sensor network, use the sensors to determine the motion of one or more targets • Canonical domain for DSNs - much of what we have seen so far is applicable • data routing, query propagation, wireless protocols • Typically requires more cooperation among entities than other examples we have seen • Compare: “is there an elephant out there?” vs. “where has that particular elephant been?”

3. Objectives to be satisfied • Collaborative Signal Processing (CSP) • Distributive processing • Goal oriented, on-demand processing • Information fusion • Multi-resolution processing

4. Collaborative Signal Processing (CSP) • To facilitate detection, identification and tracking of targets, global information in both time and space must be collected and analyzed over a specified space-time region • However individual nodes provide spatially local information only • CSP provides data representation and control mechanisms to collaboratively process and store sensor information, respond to external events and report results

5. Distributive processing • Raw signals are sampled and processed at individual nodes but are not directly communicated over the wireless channel • Instead each node extracts relevant summary statistics from the raw signal, which are typically smaller in size • The summary statistics are stored locally in individual nodes and may be transmitted to other nodes upon request.

6. Goal oriented, on-demand processing • To conserve energy, each node should perform signal processing tasks that are relevant to the current query • In the absence of a query, each node should retreat into a standby mode to minimize energy consumption • A sensor node should not automatically publish extracted information, but should forward information only when needed

7. Information fusion • To infer global information over a certain space-time region, CSP must facilitate efficient hierarchical information fusion • High bandwidth time series data must be shared between neighboring nodes for classification purposes • Lower bandwidth data may be exchanged between more distant nodes for tracking purposes.

8. Multi-resolution processing • Depending on the nature of the query, some CSP tasks may require higher spatial resolution involving a finer sampling of sensor nodes, or higher temporal resolution involving higher sampling rates • Example: Reliable detection is achievable with relatively coarse space-time resolution, whereas classification typically requires higher resolution

9. Tracking Challenges • Data dissemination and storage • Resource allocation and control • Operating under uncertainty • Real-time constraints • Data fusion (measurement interpretation) • Multiple target disambiguation • Track modeling, continuity and prediction • Target identification and classification

10. Tracking Domains • Appropriate strategy depends on the sensors’ capabilities, domain goals and environment • Requires multiple measurements? • Bounded communication? • Target movement characteristics? • No single solution for all problems • For example… • Limited bandwidth encourages local processing • Limited sensors requires cooperation

11. Why Not Centralized? • Scale! • Data processing combinatorics • Resource bottleneck (communication, processing) • Single point of failure • Ignores benefits of locality

12. Why Not (fully) Distributed? • Redundant information and computation • Can increase uncertainty • Lack of unified view • High communication costs

13. Different Approaches of Tracking • Tree-Based • Cluster-Based • Prediction-Based

14. Scalable Tracking Using Networked Sensors (STUN) • Tree based - H. T. Kung and D. Vlah. “Efficient Location Tracking Using Sensor Networks.” WCNC, March 2003. - Chih-Yu Lin and Yu-Chee Tseng “Structures for In-Network Moving Object Tracking in Wireless Sensor Networks” BROADNETS’04

15. STUN (cont’d) • The method will need to handle a large number of moving objects at once • This method uses a hierarchy to connect the sensors • The leaves are sensors • The querying point as the root • The other nodes are communication nodes • Example of message pruning hierarchy. Consider the direction messages from sensors that detect the arrival of a car. Sensor 1’s message will update the detected sets of all its ancestors. The message from sensor 2 and 4 do not update the detected sets of their parents and thus will be pruned there. The message from sensor 3 updates only its parent Z and thus will be pruned at X

16. STUN (cont’d) -- Example

17. STUN (cont’d) • Advantage • Message pruning • Routing • Disadvantage • Building the tree (the structures of the tree)

18. Dynamic Convoy Tree-Based Collaboration (DCTC) • Wensheng Zhang and Guohong Cao, “DCTC: Dynamic Convoy Tree-Based Collaboration for Target Tracking in Sensor Networks” IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, VOL. 3, NO. 5, SEPTEMBER 2004 • Wensheng Zhang and Guohong Cao, “Optimizing Tree Reconfiguration for Mobile Target Tracking in Sensor Networks” INFOCOM 2004

19. DCTC (Cont’d) - Introduction • DCTC relies on a tree structure called “convoy tree” • The tree is dynamically configured to add some nodes and prune some nodes as the target moves.

20. DCTC (cont’d) – Basic Idea

21. Cluster-Based • Wei-Peng Chen, Jennifer C. Hou, and Lui Sha, Fellow, IEEE “Dynamic Clustering for Acoustic Target Tracking in Wireless Sensor Networks” IEEE TRANSACTIONS ON MOBILE COMPUTING, VOL. 3, NO. 3, JULYSEPTEMBER 2004

22. Dynamic Clustering for Acoustic Target Tracking • A CH volunteers to become active • When it detects that the strength of a received acoustic signal exceeds a predetermined threshold • The signal matches one of the signal patterns which the system intends to track. • The tasks of an active CH • Broadcasting a packet that contains the energy and the extracted signature of the detected signal to sensors • Receiving replies from sensors • Estimating the location of the target based on replies • Sending the result to subscriber(s). • Energy-Based Localization • The fundamental principle applied in the energy-based approaches is that the signal strength (i.e., energy) of a received signal decreases exponentially with the propagation distance

23. Dynamic Cluster – The Continuous Objects • Continuously distributed across a region • Occupy a large area • Trend to diffuse, increase in size, change in sharp, split into multiple relatively smaller continuous objects

24. Prediction-Based • Please go through the following papers • Yingqi Xu Winter, J. Wang-Chien Lee “Prediction-based strategies for energy saving in object tracking sensor networks” 2004 IEEE International Conference on Mobile Data Management, 2004. • Xu, Y.; Winter, J.; Lee, W.-C. “Dual prediction based reporting for object tracking sensor networks” MOBIQUITOUS 2004

25. Organization-Based Tracking • Use structure, roles to control data and action flow • Can be static, or dynamically evolved • Maintain an organizational hierarchy for achieving energy efficient tracking solution

26. Distributed Target Classification and Tracking in Sensor Networks --Proceedings of the IEEE, vol. 91, no. 8, pp. 1163-1171, 2003.

27. Problem Domain • Single target • Fixed, acoustic sensors • Requires multiple measurements • Limited ad-hoc wireless network • Track and classify target • (classification, which uses a supervised learning technique, is not discussed here)

28. Location-Centric Tracking Control and data flow at each node: • Initialization: disseminate sensor information • Receive candidates: describe approaching targets • Local detections: gather measurements • Merge detections: form track, compare candidates • Determine confidence: estimate uncertainty • Estimate track: predict future target location • Transmit track: notify relevant sensors

29. Location-Centric Tracking • “Closest point of approach” (CPA) measurements • Target detection causes cell formation • Cells formed around the target’s estimated location • Intended to include relevant sensors • Manager is selected • Node with greatest signal strength • Manager collects local CPA’s • Linear regression over CPA node locations

30. Location-Centric-Tracking • Estimated location compared to prior tracks • Projections from candidate tracks • Cell created for tracking in new area • Size is a function of target velocity • Tracking information propagated to cell • Tracking repeats…

31. Location-Centric Advantages • Avoids combinatorial explosion of track association • Centralized: n targets, n candidate locations = n2 • Distributed: 1 target, n candidate locations = n • Reduces communication costs (multi-hop ad hoc) • Saves energy

32. Using and Maintaining Organization in a Large-Scale Sensor Network Bryan Horling, Roger Mailler, Mark Sims and Victor Lesser Multi-Agent Systems Lab University of Massachusetts

33. Problem Domain • Fixed doppler radars • Requires multiple, coordinated measurements • Multiple targets • Shared 8-channel RF communication

34. Sensor Characteristics • Hardware • Fixed location, orientation • Three 120° radar heads • Agent controller • Doppler radar • Amplitude and frequency data • One (asynchronous) measurement at a time

35. Organizational Control • Use organization to address scaling issues • Environment is partitioned • Constrains information propagation • Reduces information load • Exploits locality • Agents take on one or more roles • Limits sources of information • Facilitates data retrieval • Other techniques also built into negotiation protocol and individual role behaviors

36. Typical Node Layout • Nodes are arranged or scattered, and have varied orientations. • One agent is assigned to each node.

37. Partitioning of Nodes • The environment is first partitioned into sectors. • Sector managers are then assigned.

38. Competition for Sensor Agents • Sector members send their capabilities to their managers. • Each manager then generates and disseminates a scan schedule.

39. Track Manager Selection • Nodes in the scan schedule perform scanning actions. • Detections reported to manager, and a track manager selected.

40. Managing Conflicted Resources • Track manager discovers and coordinates with tracking nodes. • New tracking tasks may conflict with existing tasks at the node.

41. Data Fusion (Track Generation) • Tracking data sent to an agent which performs the fusion. • Results sent back to track manager for path prediction.

42. Sector Size • This one parameter affects many things… • Sector manager load • Smaller sector –› smaller manager directory • Larger sector –› better sector coverage • Track manager actions • Smaller sector –› fewer update messages • Larger sector –› larger manager directory • Communication distance, agent activity, • Empirical evaluation of varying these parameters

43. Recommended Reading • Efficient in-network moving object tracking in wireless sensor networks Chih-Yu Lin; Wen-Chih Peng; Yu-Chee Tseng;Mobile Computing, IEEE Transactions on Volume 5,  Issue 8,  Aug. 2006 Page(s):1044 – 1056 • Self-organizing sensor networks for integrated target surveillance Biswas, P.K.; Phoha, S.; Computers, IEEE Transactions on Volume 55,  Issue 8,  Aug. 2006 Page(s):1033 – 1047 • CollECT: Collaborative Event deteCtion and Tracking in Wireless Heterogeneous Sensor Networks Kuei-Ping Shih; Sheng-Shih Wang; Pao-Hwa Yang; Chau-Chieh Chang; Computers and Communications, 2006. ISCC '06. Proceedings. 11th IEEE Symposium on 26-29 June 2006 Page(s):935 – 940 • Wireless sensor network based model for secure railway operations Aboelela, E.; Edberg, W.; Papakonstantinou, C.; Vokkarane, V.; Performance, Computing, and Communications Conference, 2006. IPCCC 2006. 25th IEEE International 10-12 April 2006 • Adaptive tracking in distributed wireless sensor networks Lizhi Yang; Chuan Feng; Rozenblit, J.W.; Haiyan Qiao; Engineering of Computer Based Systems, 2006. ECBS 2006. 13th Annual IEEE International Symposium and Workshop on 27-30 March 2006 • A Monte Carlo Method for Joint Node Location and Maneuvering Target Tracking in a Sensor Network Miguez, J.; Artes-Rodriguez., A.; Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on Volume 4,  2006 • Target Tracking in a Two-Tiered Hierarchical Sensor Network Vemula, M.; Bugallo, M.F.; Djuric, P.M.; Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on Volume 4,  2006 • Localization and Tracking in Sensor Systems Manley, E.D.; Al Nahas, H.; Deogun, J.S.; Sensor Networks, Ubiquitous, and Trustworthy Computing, 2006. IEEE International Conference on Volume 2,  2006 Page(s):237 – 242 • Efficient Online State Tracking Using Sensor NetworksHalkidi, M.; Kalogeraki, V.; Gunopulos, D.; Papadopoulos, D.; Zeinalipour-Yazti, D.; Vlachos, M.; Mobile Data Management, 2006. MDM 2006. 7th International Conference on 10-12 May 2006 Page(s):24 – 24 • Achieving Real-Time Target Tracking UsingWireless Sensor NetworksTian He; Vicaire, P.; Ting Yan; Liqian Luo; Lin Gu; Gang Zhou; Stoleru, R.; Qing Cao; Stankovic, J.A.; Abdelzaher, T.; Real-Time and Embedded Technology and Applications Symposium, 2006. Proceedings of the 12th IEEE 04-07 April 2006 Page(s):37 - 48

44. Thanks !