ABSTRACT
We present an approach to infer relative position and orientation of ubiquitous building-installed low-resolution spatial sensors using real-life measurements. Commercial buildings accumulate a "zoo" of heterogeneous devices, as new generations of sensors and emerging modalities become available. The increasing number of building sensors pose challenging commissioning and maintenance tasks that require sensor arrangement information. In this work we focus on sensors which can track objects in their field of view, i.e., spatial sensors. Furthermore, our proposed approach is fined tuned for low-resolution spatial sensors, i.e., where objects can be detected but not identified. We exploit user walking trajectories within building spaces and the resulting sensor signatures to identify spatial relations between sensors. We start by tracking objects through each sensor's field of view, then create link rules between pairs of sensors, and finally, based on the mined link rules, infer relative sensor arrangement. We evaluated our mining and sorting approach using thermopile array sensors in four real-life building scenarios: corridor, T-crossing, meeting room, and a foyer, involving different sensor arrangements and network sizes. Based on data acquired over multiple weeks in each scenario, we found that sensor arrangements could be inferred with accuracies ranging from 77% to 100% on the best days, depending on scenario complexity and use. Our approach can be beneficial to derive and maintain heterogeneous spatial sensor networks, independent of the sensor's communication protocol.
Supplemental Material
- J. Aspnes, T. Eren, D. K. Goldenberg, A. S. Morse, W. Whiteley, Y. R. Yang, B. D. Anderson, and P. N. Belhumeur. A theory of network localization. Mob. Comput. IEEE Trans. On, 5(12):1663--1678, 2006. Google ScholarDigital Library
- R. Bodor, P. Schrater, and N. Papanikolopoulos. Multi-camera positioning to optimize task observability. In Advanced Video and Signal Based Surveillance, 2005. AVSS 2005. IEEE Conference on, pages 552--557. IEEE, 2005.Google ScholarCross Ref
- A. J. Eronen, V. T. Peltonen, J. T. Tuomi, A. P. Klapuri, S. Fagerlund, T. Sorsa, G. Lorho, and J. Huopaniemi. Audio-based context recognition. IEEE Trans. Audio Speech Lang. Process., 14(1):321--329, Jan. 2006. Google ScholarDigital Library
- J. Han and B. Bhanu. Human Activity Recognition in Thermal Infrared Imagery. In IEEE Computer Vision and Pattern Recognition Conference - Workshops., pages 17--17. IEEE, 2005. Google ScholarDigital Library
- P. Hevesi, S. Wille, G. Pirkl, N. Wehn, and P. Lukowicz. Monitoring Household Activities and User Location with a Cheap, Unobtrusive Thermal Sensor Array. In Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp '14, pages 141--145, New York, NY, USA, 2014. ACM. Google ScholarDigital Library
- A. Jain, L. Hong, and S. Pankanti. Biometric Identification. Commun ACM, 43(2):90--98, Feb. 2000. Google ScholarDigital Library
- P. Jaramillo-Garcia, L. I. Lopera Gonzalez, and O. Amft. Using implicit user feedback to balance energy consumption and user comfort of proximity-controlled computer screens. J. Ambient Intell. Humaniz. Comput., 6(2):207--221, Feb. 2014.Google ScholarCross Ref
- L. I. Lopera Gonzalez and O. Amft. Mining relations and physical grouping of building-embedded sensors and actuators. In PerCom 2015: Proceedings of the International Conference on Pervasive Computing and Communications, pages 2--10. IEEE, Mar. 2015.Google Scholar
- L. I. Lopera Gonzalez and O. Amft. Mining hierarchical relations in building management variables. Pervasive and Mobile Computing, 26:91--101, 2016. Google ScholarDigital Library
- L. I. Lopera Gonzalez, U. Großekathöfer, and O. Amft. An Intervention Study on Automated Lighting Control to Save Energy in Open Space Offices. In PerEnergy 2015: IEEE International Conference on Pervasive Computing and Communications Workshops, pages 317--322. IEEE, Mar. 2015.Google Scholar
- L. I. Lopera Gonzalez, M. Troost, and O. Amft. Using a thermopile matrix sensor to recognize energy-related activities in offices. In SEIT 2013: Proceedings of the 3rd International Conference on Sustainable Energy Information Technology, Procedia Computer Science, pages 678--685. Elsevier, 2013. Recipient of the Best Paper Award at SEIT 2013.Google Scholar
- S. Mashiyama, J. Hong, and T. Ohtsuki. Activity recognition using low resolution infrared array sensor. In Communications (ICC), 2015 IEEE International Conference on, pages 495--500, June 2015.Google ScholarCross Ref
- M. Milenkovic and O. Amft. Recognizing energy-related activities using sensors commonly installed in office buildings. In SEIT 2013: Proceedings of the 3rd International Conference on Sustainable Energy Information Technology, Procedia Computer Science, pages 669--677. Elsevier, 2013.Google ScholarCross Ref
- D. Nistér. Reconstruction from Uncalibrated Sequences with a Hierarchy of Trifocal Tensors. In Computer Vision - ECCV 2000, number 1842 in Lecture Notes in Computer Science, pages 649--663. Springer Berlin Heidelberg, June 2000. Google ScholarDigital Library
- N. Patwari, J. Ash, S. Kyperountas, A. Hero, R. Moses, and N. Correal. Locating the nodes: Cooperative localization in wireless sensor networks. Signal Process. Mag. IEEE, 22(4):54--69, July 2005.Google ScholarCross Ref
- N. Patwari, A. O. Hero, M. Perkins, N. S. Correal, and R. J. O'dea. Relative location estimation in wireless sensor networks. Signal Process. IEEE Trans. On, 51(8):2137--2148, 2003. Google ScholarDigital Library
- A. Payal, C. Rai, and B. Reddy. Analysis of Radial Basis Function network for localization framework in Wireless Sensor Networks. In Confluence The Next Generation Information Technology Summit (Confluence), 2014 5th International Conference -, pages 432--435, Sept. 2014.Google ScholarCross Ref
- Y. Rui and Y. Chen. Better proposal distributions: Object tracking using unscented particle filter. In Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001. CVPR 2001, volume 2, pages II-786--II-793 vol. 2, 2001.Google Scholar
- R. Zetik, S. Crabbe, J. Krajnak, P. Peyerl, J. Sachs, and R. Thomä. Detection and localization of persons behind obstacles using M-sequence through-the-wall radar. volume 6201, pages 62010I--62010I--12, 2006.Google Scholar
- J. Zhao and S.-c. Cheung. Multi-camera surveillance with visual tagging and generic camera placement. In Distributed Smart Cameras, 2007. ICDSC'07. First ACM/IEEE International Conference on, pages 259--266. IEEE, 2007.Google ScholarCross Ref
Recommendations
Methods of Sensors Localization in Wireless Sensor Networks
ECBS '07: Proceedings of the 14th Annual IEEE International Conference and Workshops on the Engineering of Computer-Based SystemsIn recent years there has been a growing interest in wireless sensor networks (WSN) applications. Such sensor networks can be used to control temperature, humidity, contamination, pollution etc. Self-organization and routing algorithms dedicated to ...
Barrier coverage with line-based deployed mobile sensors
Barrier coverage of a wireless sensor network is a critical issue in military and homeland security applications, aiming to detect intruders that attempt to cross the deployed region. While a range of problems related to barrier coverage have been ...
Error analysis of quantised RSSI based sensor network localisation
Localising sensor nodes is an essential process for self-organising Wireless Sensor Networks (WSNs). A few recently-proposed localisation algorithms use Received Signal Strength Indication (RSSI) readings usually available in WSNs for node localisation. ...
Comments