Journal of Korean Society for Geospatial Information Science (대한공간정보학회지)

Korea Spatial Information Society (대한공간정보학회)
권호 표지
DOI QR코드

DOI QR Code

Changes in the Number of Matching Points in CCTV's Stereo Images by Indoor/Outdoor Illuminance

실내·외 조도에 따른 스테레오 CCTV 영상 정합점 수 변화

  • Received : 2015.03.10
  • Accepted : 2015.03.20
  • Published : 2015.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

The Ubiquitous City (U-City) spatial information technology aimed to provide services freely anytime and anywhere by converging high-tech information & communication technology in urban infrastructure has been available in diverse patterns. In particular, there have been studies on the development of 3D spatial information after selecting and matching key points with stereo images from the many Closed Circuit TV (CCTV) in the U-City. However, the data mostly used in extracting matching points haven't considered external environmental impacts such as illuminance. This study tested how much the matching points needed to construct 3D spatial information with the CCTV whose image quality is dependent upon changes in illuminance fluctuate under the same hardware performances. According to analysis on the number of matching points by illuminance, the number of matching points increased up to 3,000Lux in proportion to the illuminance when IRIS, shutter speed and ISO were fixed. In addition, a border between an object and background became more distinctive. When there was too much light, however, the page became brighter, and noise occurred. Furthermore, it was difficult to name key points because of the collapse of an inter-object border. It appears that if filmed with the study results, the number of matching points would increase.

도시기반시설에 첨단 정보통신기술을 융합하여 언제 어디서나 자유롭게 서비스를 제공하고자 하는 U-City(Ubiquitous City)의 공간정보기술은 다양한 형태로 서비스 되고 있다. 그 중에서도 U-City에서 가장 많이 설치되어 있는 CCTV(Closed Circuit TV)의 스테레오 영상을 가지고 특징점(Key Point)을 선정하여 정합(Matching)하고 3차원 공간정보를 구축하는 연구가 진행되고 있다. 하지만 대부분 정합점을 추출하는데 사용된 데이터는 조도와 같은 외부 환경영향을 고려하지 않고 있다. 본 논문은 동일한 하드웨어에서 조도의 변화에 의해 영상의 질이 좌우되는 CCTV를 가지고 3차원 공간정보를 구축하는데 필요한 정합점이 조도에 따라 얼마나 변화 하는지 실험을 하였다. 조도에 따른 정합점 수의 분석 결과, 카메라의 조리개, 셔터속도, 감도를 고정하였을 때 3,000Lux까지 정합점 수가 조도에 비례하여 높아 졌으며, 물체와 배경의 경계가 뚜렷해졌다. 반대로 빛이 과도하게 들어 왔을 경우 화면이 밝이지며, 노이즈가 발생하고 사물과 사물의 경계가 없어져 특징점을 선정하기가 힘들었다. 본 논문에서 얻어진 결과를 이용하여 촬영할 경우 향상된 정합점을 가질 수 있을 것으로 기대된다.

Keywords

References

  1. Cho, Y., Pyeon, M. and Kim, D., 2013, Comparison of image matching algorithms in the spatial information system, 2013 Conference of The Korea Society for GeoSpatial Information System, pp. 139-142.
  2. Ham, J., 2012, CCTV system installation standard method, Korea Information and Communication Contractors Association, Korea, Seoul, p. 42.
  3. Jang, I., 2015, A study on the stereo CCTV optimization allocation for 3D mapping, Masters thesis, Konkuk University, p. 55.
  4. Jeon, M., Eo, Y., Han, D., Kang, N. and Pyeon, M., 2010, Experiment for 3D coregistration between scanned point clouds of building using intensity and distance images, Korean Journal of Remote Sensing, Vol. 26, No. 1, pp. 39-45. https://doi.org/10.7780/kjrs.2010.26.1.39
  5. Joo, S. and Lee, C., 2014, 3D Object recognition using appearance model space of feature point, KIPS Transactions on Software and Data Engineering, Korea Information Processing Society, Vol. 3, No. 2, pp. 93-100. https://doi.org/10.3745/KTSDE.2014.3.2.93
  6. Jung, E., Beak, S., Park, S. and Jang, H., 2012, Optical properties correction of a heterogeneous stereoscopic camera, Journal of the Institute of Electronics Engineers of Korea, Vol. 49, No. 11, pp. 74-85.
  7. Kim, B., Jang, I. and Lee. K., 2011, Real-time road-visibility measurement using CCTV camera, Journal of Korean Society of Transportation, Vol. 29, No. 4, pp. 125-138.
  8. Kim, I. and Shin, H., 2011, 3D GIS system using the CCTV camera, Information & Communications Magazine, The Korean Institute of Communications and Information Sciences, Vol. 6, No. 4, pp. 559-565.
  9. Kim, J. and Jun, H., 2014, Filtering feature mismatches using multiple descriptors, Journal of The Korea Society of Computer and Information, Vol. 19, No. 1, pp. 23-30. https://doi.org/10.9708/jksci.2014.19.1.023
  10. Kim, S., Jung, j., Lee, J., Heo, J., Hong, S. and Cho, H., 2014, Update of digital map by using the terrestrial LiDAR data and modified RANSAC, Journal of the Korean Society for Geospatial Information System, Vol. 22, No. 4, pp. 3-11. https://doi.org/10.7319/KOGSIS.2014.22.4.003
  11. Korea Meteorological Administration, http://www.kma.go.kr/
  12. Lee, G., 2014, The two faces of intelligent CCTV, MBC, http://imnews.imbc.com/replay/2014/nwdesk/article/3402496_13490.html.
  13. Lee, S.H. and Sharma, S., 2011, A real-time stereo matching using GPU programming, Workshop on Image Processing and Image Understanding, Jejudo.
  14. Lowe, D. 2004, Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, Vol. 60(2), pp. 91-110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  15. Ministry of Land, Infrastructure and Transport, 2014, 2014 Spatial information policy implementation plan, 11-1613000-000224-10, Ministry of Land, Infrastructure and Transport, Korea.
  16. Moon, K., Pyeon, M., Lee, S. and Lee, D., 2014, Setting of the operating conditions of stereo CCTV cameras by weather condition, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 32, No. 6, pp. 591-597. https://doi.org/10.7848/ksgpc.2014.32.6.591
  17. Oh, J., Lee, Sang., Lee, Boo. and Park, J., 2012, Distance measurement of small moving object using infrared stereo camera, Journal of the Institute of Electronics Engineers of Korea, The Institute of Electronics and Information Engineers, Vol. 49, No. 3, pp. 53-61.
  18. Scharstein, D. and Szeliski, R., 2002, A taxonomy and evaluation of dense two-frame stereo correspondence algorithms, International journal of computer vision, Vol. 47(1-3), pp. 7-42. https://doi.org/10.1023/A:1014573219977
  19. Song, J., 2012, Cloud computing-based system for 3D GIS case study, Communications of the Korean Institute of Information Scientists and Engineers, the Korean Institute of Information Scientists, Vol. 30, No. 5, pp. 29-34.
  20. Yun, J.Y., Kim, E.T. and Jeon, S.W,, 2008, Object recognition using SIFT algorithm, The Transactions of the Korean Institute of Electrical Engineers, Vol. 39, pp. 1841-1842.

Cited by

  1. Development of Automatic Water Level Measuring System Using Stereo Images vol.26, pp.2, 2018, https://doi.org/10.7319/kogsis.2018.26.2.077