Skip to main content
SpringerLink
Log in

Performance Analysis of Grey-World-based Feature Detection and Matching for Mobile Positioning Systems

  • Original Paper
  • Published:
Sensing and Imaging Aims and scope Submit manuscript

Abstract

This paper introduces a new grey-world-based feature detection and matching algorithm, intended for use with mobile positioning systems. This approach uses a combination of a wireless local area network (WLAN) and a mobile phone camera to determine positioning in an illumination environment using a practical and pervasive approach. The signal combination is based on retrieved signal strength from the WLAN access point and the image processing information from the building hallways. The results show our method can handle information better than Harlan Hile’s method relative to the illumination environment, producing lower illumination error in five (5) different environments.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Ivanov, R. (2012). RSNAVI: An RFID-based context-aware indoor navigation system for the blind. In Proceedings of the 13th international conference on computer systems and technologies (pp. 313–320). New York, NY: ACM.

  2. Esposito, C., & Ficco, M. (2011). Deployment of RSS-based indoor positioning systems. International Journal of Wireless Information Networks, 18(4), 224–242.

    Article  Google Scholar 

  3. Lee, B.-G., & Chung, W.-Y. (2011). Multitarget three-dimensional indoor navigation on a PDA in a wireless sensor network. IEEE Sensors Journal, 11(3), 799–807.

    Article  MathSciNet  Google Scholar 

  4. Liao, L., Lin, K., Wang, X., Lai, X., & Vuong, S. T. (2011). WiFi positioning overview. International Journal of Communication Networks and Distributed Systems, 7(3), 229–248.

    Article  Google Scholar 

  5. Giorgetti, G., Farley, R., Chikkappa, K., Ellis, J., & Kaleas, T. (2012). Cortina: Collaborative indoor positioning using low-power sensor networks. Journal of Location Based Services, 6(3), 137–160.

    Article  Google Scholar 

  6. Yen, C.-P., & Voltz, P. J. (2011). Indoor positioning based on statistical multipath channel modeling. EURASIP Journal on Wireless Communications and Networking, 2011(1), 189.

    Article  Google Scholar 

  7. Lu, M. (2012). A framework for indoor construction resources tracking by applying wireless sensor networks. Canadian Journal Civil Engineering, 39(9), 1083–1088.

    Article  Google Scholar 

  8. Shen X, Lu M (2012) A framework for indoor construction resources tracking by applying wireless sensor networks 11. This paper is one of a selection of papers in this Special Issue on Construction Engineering and Management. Canadian Journal Civil Engineering 39(9), 1083–1088.

  9. Nicoli, M., Gezici, S., Sahinoglu, Z., & Wymeersch, H. (2011). Localization in mobile wireless and sensor networks. Eurasip Journal on Wireless Communications and Networking, 2011(1), 197.

    Article  Google Scholar 

  10. Mensing, C., Sand, S., & Dammann, A. (2010). Hybrid data fusion and tracking for positioning with GNSS and 3GPP-LTE. International Journal of Navigation and Observation, 2010, 1–12.

  11. Liew, S. C., Tan, K. G., & Tan, C. P. (2006). Non-Taylor series based positioning method for hybrid GPS/cellphone system. Journal of Electromagnetic Waves and Applications, 20(6), 717–729.

    Article  Google Scholar 

  12. Liew, S. C., Tan, K. G., & Lim, T. S. (2006). Investigation of direct A-GPS positioning for hybrid E-OTD/GNSS. Journal of Electromagnetic Waves and Applications, 20(1), 79–87.

    Article  Google Scholar 

  13. Yang, H., Park, K., Lee, J. G., & Chung, H. (2000). A rotating sonar and a differential encoder data fusion for map-based dynamic positioning. Journal of Intelligent Robotic Systems, 29(3), 211–232.

    Article  MATH  Google Scholar 

  14. Shoval, S., Zeitoun, I., & Lenz, E. (1997). Implementation of a Kalman filter in positioning for autonomous vehicles, and its sensitivity to the process parameters. International Journal of Advanced Manufacturing Technology, 13(10), 738–746.

    Article  Google Scholar 

  15. Yost, M. G., Gadgil, A. J., Drescher, A. C., Zhou, Y., Simonds, M. A., Levine, S. P., et al. (1994). Imaging indoor tracer-gas concentrations with computed tomography: experimental results with a remote sensing FTIR system. American Industrial Hygiene Association Journal, 55(5), 395–402.

    Article  Google Scholar 

  16. Cao, Z. L., Oh, S. J., & Hall, E. L. (1986). Dynamic omnidirectional vision for mobile robots. Journal of Robotic Systems, 3(1), 5–17.

    Article  Google Scholar 

  17. Kosaka, A., Pan, J. (1995). Purdue experiments in model-based vision for hallway navigation. In Proceedings of the workshop on vision for robots in IROS’95, (pp. 87–96).

  18. Karlsson, N., di Bernardo, E., Ostrowski, J., Goncalves, L., Pirjanian, P., & Munich, M.E. (2005). The vSLAM algorithm for robust localization and mapping. In Proceedings of the 2005 IEEE international conference on robotics and automation, 2005. ICRA 2005, (pp. 24–29).

  19. Snavely, N., Seitz, S. M., & Szeliski, R. (2006). Photo tourism: Exploring photo collections in 3D. ACM Transactions on Graphics, 25(3), 835–846.

    Article  Google Scholar 

  20. Hile, H., & Borriello, G. (2008). Positioning and orientation in indoor environments using camera phones. IEEE Computer Graphics and Applications, 28(4), 32–39.

    Article  Google Scholar 

  21. T. Ruiz-López, J. L. Garrido, K. Benghazi, and L. Chung, “A Survey on Indoor Positioning Systems: Foreseeing a Quality Design,” in Distributed Computing and Artificial Intelligence, vol. 79, A. P. Leon F. de Carvalho, S. Rodríguez-González, J. F. Paz Santana, and J. M. C. Rodríguez, Eds. Berlin, Heidelberg: Springer Berlin Heidelberg, 2010, pp. 373–380.

  22. Bejuri, W. M. Y. W., Mohamad, M. M., Sapri, M., & Rosly, M. A. (2012). Investigation of Color Constancy for Ubiquitous Wireless LAN/Camera Positioning: An Initial Outcome. Int. J. Adv. Comput. Technol., 4(7), 269–280.

    Google Scholar 

  23. Bejuri, W. M. Y. W., Mohamad, M. M., & Sapri, M. (2011). Ubiquitous positioning: A taxonomy for location determination on mobile navigation system. International Journal of Signal Image Processing, 2(1), 24–34.

    Article  Google Scholar 

  24. Bejuri, W.M.Y.W., Mohamad, M.M., Sapri, M., & Rosly, M.A. (2012)“Ubiquitous WLAN/camera positioning using inverse intensity chromaticity space-based feature detection and matching: a preliminary result. In International conference on man-machine systems 2012. Penang, Malaysia.

  25. Chakrabarti, A., Hirakawa, K., & Zickler, T. (2010). Computational color constancy with spatial correlations. Tech. Rep. TR–09–10. Harvard School of Engineering and Applied Sciences.

  26. Bahl, P., & Padmanabhan, V.N. (2000). RADAR: An in-building RF-based user location and tracking system. In Proceedings IEEE INFOCOM 2000. Nineteenth annual joint conference of the IEEE computer and communications societies (Vol. 2, pp. 775–784).

  27. Wettschereck, D., Dietterich, T.G., & Sutton, R. (1995). An experimental comparison of the nearest-neighbor and nearest-hyperrectangle algorithms. In Machine learning, (pp. 5–28).

  28. Comaniciu, D., & Meer, P. (1999). Mean shift analysis and applications. In The Proceedings of the seventh IEEE international conference on computer vision, 1999 (Vol. 2, pp. 1197–1203).

  29. Guru, D.S., Dinesh, R., & Nagabhushan, P. (2004). Boundary based corner detection and localization using new ‘cornerity’ index: a robust approach. In Proceedings First Canadian conference on computer and robot vision, 2004 (pp. 417–423).

Download references

Acknowledgments

This work has been funded by the Research University Grant (RUG) under Project No. Q.130000.2628.08J05.

Author information

Authors and Affiliations

  1. Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Malaysia

    Wan Mohd Yaakob Wan Bejuri & Mohd Murtadha Mohamad

  2. Faculty of Information and Communication Technology, Universiti Teknikal Malaysia Melaka, Durian Tunggal, Malaysia

    Wan Mohd Yaakob Wan Bejuri

Authors
  1. Wan Mohd Yaakob Wan Bejuri
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mohd Murtadha Mohamad
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Wan Mohd Yaakob Wan Bejuri or Mohd Murtadha Mohamad.

Appendices

Appendix 1: Radio Data Collection

As shown in Fig. 13, four (4) steps are required in the radio data collection process: radio manager configuration, radio collection measurement, radio parameter generation and WLAN network management. In the first step, all the device information shown in the Radio Manager is polled from the managed devices on the network. The WLSE polls and receives Radio Manager aggregated data from WDS devices and provides intelligent processing of the data. The WLSE can manage multiple subnets; thus, it can receive Radio Manager data from many WDS devices. The WLSE must register with each WDS in each managed AP subnet to receive Radio Manager data. If the WLSE is unregistered, none of the Radio Manager functions will work.

Fig. 13
figure 13

Steps for radio data (signal strength) collection

Full size image

After the APs have been configured for radio management, the selections under the Radio Manager or Location Manager tabs can be used to gather radio location measurements. The Radio Manager then uses these measurements to characterise the radio environment and determine the channels and power limits for each 802.11 Basic Service Set (BSS). In the third step, those selections under the Radio Manager or Location Manager tabs can be used. The purpose is to recommend an optimal radio transmission power, channel selection, and beacon interval (optional) for each AP, then apply these configuration settings. After that, the WLAN environment can then finally be managed (Fig. 14).

Fig. 14
figure 14

Four (4) users’ orientations during WLAN data collection

Full size image

Appendix 2: Radio (WLAN Signal Strength) Data Collection Results

For WLAN signal strength collection, Figs. 15, 16, 17 and 18 show the signal strength for various distances between the mobile node and the APs, in different user orientations. As evident from these figures, the signal strength trend appears to be normal; the value increases as the distance decreases. The trend in relation to signal strength, is that the value increases as the distance decreases; this is almost the same as that depicted in Figs. 19, 20, 21 and 22. The significant difference in signal strengths between points at similar distances is explained by several factors; i.e. the layout of the rooms in the building, the placement of the base stations and the location of the mobile user. Figures 15, 16, 17 and 18 reveal that the signal strength value obtained by the mobile device depends on different aspects of the user orientation in Area 1. For example, the signal strength value of AP2 is highest when the user is orientated at 270° (see Fig. 20 for details), compared with the signal strength obtained at 0° (see Fig. 15 for details). Meanwhile, in Area 2, the value of the signal strength obtained by the mobile device can be seen in Figs. 19, 20, 21 and 22. These also show the signal strength depends on user orientation, although the distance between the mobile device receiver and the AP is minimal. In this case, the signal strength value of AP3 is highest when the user is orientated at 270° (see Fig. 24 for details) compared with the signal strength obtained at 0° (see Fig. 19). This is because the orientation of the user may contribute to the blockage; thus the signal strength obtained by the mobile device will be reduced. This also applies toother values in the graph. In this analysis, the result of the 37.35 % distance error at Area 1 falls below 3.4 m. In addition, the 56.67 % distance error at Area 2 was below 2.9 m. As an overall result, the average error of the WLAN positioning was 7.69777193 m (Area 1) and 6.12233997 m (Area 2). The results of WLAN positioning reveal that this applies under normal conditions, since the average distance error is <10 m.

Fig. 15
figure 15

Distance and RSSI during data collection in Location 1 (User Orientation: 0°). (Note signal strength in −dBm and distance in metres)

Full size image
Fig. 16
figure 16

Distance and RSSI during data collection in Location 1 (User Orientation: 90°). (Note signal strength in −dBm and distance in metres)

Full size image
Fig. 17
figure 17

Distance and RSSI during Data Collection in Location 1 (User Orientation: 180°). (Note signal strength in –dBm and distance in metres)

Full size image
Fig. 18
figure 18

Distance and RSSI during Data Collection in Location 1 (User Orientation: 270°). (Note signal strength in −dBm and distance in metres)

Full size image
Fig. 19
figure 19

Distance and RSSI during Data Collection in Location 2 (User Orientation: 0°) (Note signal strength in −dBm and distance in metres)

Full size image
Fig. 20
figure 20

Distance and RSSI during Data Collection in Location 2 (User Orientation: 180°). (Note signal strength in −dBm and distance in metres)

Full size image
Fig. 21
figure 21

Distance and RSSI during data collection in Location 2 (User Orientation: 90°) (Note signal strength in −dBm and distance in metres)

Full size image
Fig. 22
figure 22

Distance and RSSI during data collection in Location 2 (User Orientation: 270°). (Note signal strength in −dBm and distance in metres)

Full size image

Appendix 3: Results of Feature Detection in Five (5) Locations

See Figs. 23 and 24.

Fig. 23
figure 23

Conventional feature detection in five (5) locations

Full size image
Fig. 24
figure 24

Results of Grey-World based feature detection in five (5) Locations

Full size image

Appendix 4: The Results of Localisation Comparison Between Real Position and Experimental Position

See Figs. 25 and 26.

Fig. 25
figure 25

Localisation comparison between real position and experimental position at Location 1, Location 2 and Location 5 (Area 1)

Full size image
Fig. 26
figure 26

Localisation comparison between real position and experimental position at Location 3 and Location 4 (Area 2)

Full size image

Appendix 5: The Illustration of Recommended Technology

See Figs. 27 and 28.

Fig. 27
figure 27

Illustration of WLAN and augmented reality integration positioning approach

Full size image
Fig. 28
figure 28

Illustration of the GSM and augmented reality integration positioning approaches

Full size image

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bejuri, W.M.Y.W., Mohamad, M.M. Performance Analysis of Grey-World-based Feature Detection and Matching for Mobile Positioning Systems. Sens Imaging 15, 95 (2014). https://doi.org/10.1007/s11220-014-0095-7

Download citation

  • Received:

  • Revised:

  • Published:

  • DOI: https://doi.org/10.1007/s11220-014-0095-7

Keywords

Search

Navigation