The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지
DOI QR코드

DOI QR Code

User Positioning Method Based on Image Similarity Comparison Using Single Camera

단일 카메라를 이용한 이미지 유사도 비교 기반의 사용자 위치추정

  • Song, Jinseon (Yeungnam Univ. Dept. Mobile Information and Communication Engineering) ;
  • Hur, SooJung (Yeungnam Univ. Dept. Mobile Information and Communication Engineering) ;
  • Park, Yongwan (Yeungnam Univ. Dept. Mobile Information and Communication Engineering) ;
  • Choi, Jeonghee (Daegu Univ. Dept. Computer & Communication Engineering)
  • Received : 2015.03.30
  • Accepted : 2015.07.15
  • Published : 2015.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, user-position estimation method is proposed by using a single camera for both indoor and outdoor environments. Conventionally, the GPS of RF-based estimation methods have been widely studied in the literature for outdoor and indoor environments, respectively. Each method is useful only for indoor or outdoor environment. In this context, this study adopts a vision-based approach which can be commonly applicable to both environments. Since the distance or position cannot be extracted from a single still image, the reference images pro-stored in image database are used to identify the current position from the single still image captured by a single camera. The reference image is tagged with its captured position. To find the reference image which is the most similar to the current image, the SURF algorithm is used for feature extraction. The outliers in extracted features are discarded by using RANSAC algorithm. The performance of the proposed method is evaluated for two buildings and their outsides for both indoor and outdoor environments, respectively.

본 논문에서는 Fingerprint 기법의 Resource로 신호의 세기가 아닌 이미지를 이용해 좌표정보를 포함하는 이미지 기반의 데이터베이스를 구축하고, 사용자로부터 입력되는 이미지와 유사도 비교를 통해 사용자의 위치추정 기법에 대해 제안한다. Fingerprint 기법은 신호 세기뿐만 아니라 환경에 대한 지역적 잡음 정보들까지 모두 추정에 반영하므로 높은 위치 추정 정확도를 제공한다. 이미지의 유사도는 SURF 알고리즘을 통해 데이터베이스와 사용자 입력 이미지의 특징점을 검출하고, 동일한 특징점 간의 매칭을 통해 비교된다. 여기에서 우리는 RANSAC 알고리즘을 함께 사용하여 검출된 특징점의 노이즈 제거를 통해 이미지 유사도 비교의 정확도를 높였다. 제안하는 기법의 검증을 위해 두 건물의 실내와 주변 실외 환경에서 이미지를 획득하여 데이터베이스를 구축하고, 임의의 위치에서 사용자의 위치를 추정하였다. 추정 된 최종 위치는 데이터베이스에 저장 된 이미지가 가지는 좌표가 사용자의 위치와 가장 근접한 좌표로 검출되는지 확인하였으며 RANSAC을 통해 특징점의 노이즈 제거 전과 제거 후에 대한 이미지 유사도 비교의 성능을 분석하였다.

Keywords

References

  1. H. Liu, H. Darabi, P. Banerjee, and J. Liu, "Survey of wireless indoor positioning techniques and systems," IEEE Trans. System, Man, and Cybernetics-Part C: Appl. and rev., vol. 37, no. 6, pp. 1067-1080, Nov. 2007. https://doi.org/10.1109/TSMCC.2007.905750
  2. D.-G. Kim, Y.-H. Kim, J.-W. Han, K.-H. Song, and H.-N. Kim, "Emitter geolocation based on TDOA/FDOA measurements and its analysis," J. KICS, vol. 38C, no. 9, Sept. 2013.
  3. S. Hur, J. Song, and Y. Park, "Indoor position technology in Geo-Megnetic field," J. KICS, vol. 38C, no. 1, pp. 131-140, Jan. 2013. https://doi.org/10.7840/kics.2013.38C.1.131
  4. K. Kaemarungsi, "Efficient design of indoor positioning systems based on position fingerprint," Int. Conf. Wirel. Netw., Commun. Mob. Comput., vol. 1, pp. 181-186, Jun. 2005.
  5. S. Son, Y. Park, B. Kim, and Y. Baek, "Wi-Fi fingerprint location estimation system based on reliability," J. KICS, vol. 38C, no. 6, pp. 531-539, Jun. 2013. https://doi.org/10.7840/kics.2013.38C.6.531
  6. H. Durrant-Whyte and T. Bailey, "Simultaneous localization and mapping: Part 1," IEEE Robotics and Automation Mag., pp. 99-108, Jun. 2006.
  7. M. Montemerlo, S. Thrun, D. Koller, and B. Wegbreit, "FastSLAM: A factored solution to the simultaneous localization and mapping problem," in Proc. AAAI National Conf. Artificial Intell., Edmonton, Canada, 2002.
  8. N. Karlsson, E. D. Bernardo, J. Ostrowski, L. Goncalves, P. Pirjanian, and M. E. Munich, "The vSLAM algorithm for robust localization and mapping," in Proc. IEEE Int'l Conf. Robotics and Automation, pp. 24-29, Apr. 2005.
  9. J. B. Kim and H. S. Jun, "Vision-based position positioning using augmented reality for indoor navigation," IEEE Trans. Comsumer Electron., vol. 54, No. 3, Aug. 2008.
  10. J. Wolf, W. Burgard, and H. Burkhardt, "Robust vision-based localization for mobile robots using an image retrieval system based on invariant features," in Proc. Int. Conf. Robotics and Automation (ICRA), vol. 1, pp. 359-365, 2002.
  11. H. Bay, T. Tuytelaars, and L. V. Gool, "SURF: Speeded up robust features," European Conf. Computer Vision, vol. 3951, pp. 404-417, 2006.
  12. M. A. Fischler and R. C. Bolles, "Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography," Commun. ACM, vol. 24, no. 6, pp. 381-395, Jun. 1981. https://doi.org/10.1145/358669.358692
  13. T.-W. Kim, "Speed-up of image matching using feature strength information," J. Inst. Internet, Broadcasting and Commun., vol. 13, no. 6, Dec. 2013.
  14. J.-W. Song, S.-J. Hur, Y.-W. Park, and K.-Y. Yoo, "Database investigation algorithm for high-accuracy based indoor positioning," J. IEMEK, vol. 7, no. 2, Apr. 2012.
  15. D.-J. Na and K.-H. Choi, "Step trajectory/indoor map feature-based smartphone indoor positioning system without using Wi-Fi signals," J. IEMEK, vol. 9, no. 6, Dec. 2014.
  16. N. Ravi, P. Shankar, and A. Frankel "Indoor localization using camera phones," in Proc. IEEE WMCSA 2006, p. 49, Apr. 2006.
  17. J. Kim and D. Kim "Matching points filtering applied panorama image processing using SURF and RANSAC algorithm," J. KICS, vol. 51C, No. 4, pp. 820-835, Apr. 2014.

Cited by

  1. A panorama image generation method using FAST algorithm vol.20, pp.3, 2016, https://doi.org/10.6109/jkiice.2016.20.3.630
  2. 콘텐트 기반의 이미지검색을 위한 분류기 접근방법 vol.41, pp.7, 2015, https://doi.org/10.7840/kics.2016.41.7.816
  3. 서포트 벡터 머신을 이용한 자연 연상 통계 기반 저작물 식별 알고리즘 vol.42, pp.5, 2015, https://doi.org/10.7840/kics.2017.42.5.959