single-rb.php

JRM Vol.28 No.4 pp. 491-499
doi: 10.20965/jrm.2016.p0491
(2016)

Paper:

Human Detection by Fourier Descriptors and Fuzzy Color Histograms with Fuzzy c-Means Method

Shohei Akimoto, Tomokazu Takahashi, Masato Suzuki, Yasuhiko Arai, and Seiji Aoyagi

Kansai University
3-3-35 Yamate-cho, Suita, Osaka 564-8680, Japan

Received:
March 4, 2016
Accepted:
June 7, 2016
Published:
August 20, 2016
Keywords:
RGB-D sensor, human detection, Fourier descriptors, color histogram, fuzzy c-means method
Abstract

Human Detection by Fourier Descriptors and Fuzzy Color Histograms with Fuzzy <i>c</i>-Means Method

Result of specific person detection in Tsukuba Challenge

It is difficult to use histograms of oriented gradients (HOG) or other gradient-based features to detect persons in outdoor environments given that the background or scale undergoes considerable changes. This study involved the segmentation of depth images. Additionally, P-type Fourier descriptors were extracted as shape features from two-dimensional coordinates of a contour in the segmentation domains. With respect to the P-type Fourier descriptors, a person detector was created with the fuzzy c-means method (for general person detection). Furthermore, a fuzzy color histogram was extracted in terms of color features from the RGB values of the domain surface. With respect to the fuzzy color histogram, a detector of a person wearing specific clothes was created with the fuzzy c-means method (specific person detection). The study includes the following characteristics: 1) The general person detection requires less number of images used for learning and is robust against a change in the scale when compared to that in cases in which HOG or other methods are used. 2) The specific person detection gives results close to those obtained by human color vision when compared to the color indices such as RGB or CIEDE. This method was applied for a person search application at the Tsukuba Challenge, and the obtained results confirmed the effectiveness of the proposed method.

Cite this article as:
S. Akimoto, T. Takahashi, M. Suzuki, Y. Arai, and S. Aoyagi, “Human Detection by Fourier Descriptors and Fuzzy Color Histograms with Fuzzy c-Means Method,” J. Robot. Mechatron., Vol.28, No.4, pp. 491-499, 2016.
Data files:
References
  1. [1] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” Proc. CVPR, CA, USA, pp. 886-893, 2005.
  2. [2] J. Satake and J. Miura, “Robust stereo-based human detection and tracking for a person following robot,” IEEE ICRA, Workshop on People Detection and Tracking, 2009.
  3. [3] M. Munaro et al., “Tracking people within groups with RGB-D data,” IEEE/RSJ IEEE Int. Conf. on Intelligent Robots and Systems, pp. 2101-2107, 2012.
  4. [4] O. M. Mozos, R. Kurazume, and T. Hasegawa, “Multi-part people detection using 2d range data,” Int. J. of Social Robotics, Vol.2, No.1, pp. 31-40, 2010.
  5. [5] S. Yuta, “Open Experiment of Autonomous Navigation of Mobile Robots in the City: Tsukuba Challenge 2014 and the Results (Special Issue on Real World Robot Challenge in Tsukuba: Autonomous Technology for Useful Mobile Robot),” J. of Robotics and Mechatronics, Vol.27, No.4, pp. 318-326, 2015.
  6. [6] K. Yamauchi et al., “Person Detection Method Based on Color Layout in Real World Robot Challenge 2013,” J. of Robotics and Mechatronics, Vol.26, No.2, pp. 151-157, 2014.
  7. [7] K. Hosaka et al., “A Person Detection Method Using 3D Laser Scanner: Proposal of Efficient Grouping Method of Point Cloud Data (Special Issue on Real World Robot Challenge in Tsukuba: Autonomous Technology for Useful Mobile Robot),” J. of Robotics and Mechatronics, Vol.27, No.4, pp. 374-381, 2014.
  8. [8] Y. Uesaka, “A new Fourier descriptor applicable to open curves,” Trans. of IEICE, Vol.67-A (Vol.3), pp. 166-173, 1984 (in Japanese).
  9. [9] H. Ju and K. Ma, “Fuzzy color histogram and its use in color image retrieval,” IEEE Trans. Image Process, Vol.11, No.8, pp. 994-952, 2002.
  10. [10] J. C. Bezdek, R. Ehrlich, and W. Full, “FCM: The fuzzy c-means clustering algorithm,” Computers & Geosciences, Vol.10, No.2, pp. 191-203, 1984.
  11. [11] Y. Inaura, T. Takahashi, M. Suzuki, and S. Aoyagi, “To propose a office furniture recognizing method based on general shape concept and recoginition example using a depth map,” The 30th Annual Conf. of The Robotics Society of Japan, 2J1-6, 2012 (in Japanese).
  12. [12] O. Hori, “Labeling,” Digital Image Processing, Tokyo: Computer Graphic Arts Society, pp. 181-182, 2004.
  13. [13] D. Leon et al., “Human silhouette recognition with Fourier descriptors,” Proc. of 15th Int. Conf. on Pattern Recognition, pp. 709-712, Sep. 2000.
  14. [14] H. Ichihashi et al., “Benchmarking parameterized fuzzy c-Means classifier,” Proc. IEEE Int. Conf. on Fuzzy System, pp. 1137-1144, Aug. 2009.
  15. [15] K. Uchikawa, “Categorical perception of surface color,” Kogaku, Vol.17, No.12, pp. 47-55, 1988 (in Japanese).
  16. [16] G. Sharma et al., “The CIEDE2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observations,” Color Research & Application, Vol.30, pp. 21-30, 2004.
  17. [17] K. Lai et al., “A Large-Scale Hierarchical Multi-View RGB-D Object Dataset,” IEEE, Int. Conf. on Robotics and Automation (ICRA), pp. 1817-1824, 2011.
  18. [18] K. Takahashi, T. Takahashi, M. Suzuki, and S. Aoyagi, “Application of Kinect v2 Sensor to a Mobile Robot and Its Characterization in the Outdoor Environment (Comparison with LRF),” The Robotics and Mechatronics Conf., 2015 (in Japanese).
  19. [19] G. Overett et al., “A new pedestrian dataset for supervised learning,” IEEE Intelligent Vehicles Symposium, 2008.
  20. [20] C.-C. Chang et al., “LIBSVM: a library for support vector machines,” 2001.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, IE9,10,11, Opera.

Last updated on Nov. 16, 2018