Complementary human detection and multiple feature based tracking using a stereo camera

被引：1
作者：
Masuyama G. [1 ]
Kawashita T. [2 ]
Umeda K. [1 ]
机构：
[1] Faculty of Science and Engineering, Chuo University, 1-13-27 Kasuga, Bunkyo-ku, Tokyo
[2] Graduate School of Science and Engineering, Chuo University, 1-13-27 Kasuga, Bunkyo-ku, Tokyo
来源：
ROBOMECH Journal | / 4卷 / 1期
关键词：
Human detection; Human tracking; Stereo camera;
D O I：
10.1186/s40648-017-0092-4
中图分类号：
学科分类号：
摘要：
A human detection and tracking method using a stereo camera is presented in this paper. Two human detection methods are independently implemented, and the results are combined to reduce misdetection and nondetection. The tracking step is based on particle filtering. In the data association phase, we introduce three features: distance, traveling direction, and color. The color feature is obtained from every segmented detection window. Eligibility and co-occurrence of the blocks provide robustness to occlusion. The proposed method is tested by using measurement data at the entrance of a building, where occlusion is frequently observed. The experiments demonstrate improved tracking performance over standard particle filtering. © 2017, The Author(s).
引用
收藏
相关论文
共 13 条
  • [1] Chen X., Bhamu B., Soft biometrics integrated multi-target tracking, Proc. 22nd int. conf. on pattern recognition, pp. 4146-4151, (2014)
  • [2] Satake J., Miura J., Stereo-based tracking of multiple overlapping persons, Proc. 21st int. conf. on pattern recognition, pp. 2581-2585, (2012)
  • [3] Luber M., Spinello L., Arras K.O., People tracking in RGB-D data with on-line boosted target models, Proc. 2011 IEEE/RSJ int. conf. on intelligent robots and systems, pp. 3844-3849, (2011)
  • [4] Tseng T., Liu A., Hsiao P., Huang C., Fu L., Real-time people detection and tracking for indoor surveillance using multiple top-view depth cameras. In: Proc. 2014 IEEE/RSJ int. conf. on intelligent robots and systems, pp 4077–4082, (2014)
  • [5] Fukushi K., Itsuo K., Real-time human tracking using multiple-view stereo images and continuity constraints of long duration. In: Proc. 2010 IIEEJ image electronics and visual computing workshop, 1C-2-1-7, (2010)
  • [6] Ubukata T., Shibata M., Terabayashi K., Moro A., Kawashita T., Masuyama G., Umeda K., Fast human detection combining range image segmentation and local feature based detection, Proc. 22nd int. conf. on pattern recognition, pp. 4281-4286, (2014)
  • [7] Umeda K., Hashimoto Y., Nakanishi T., Irie K., Terabayashi K., Subtraction stereo: a stereo camera system that focuses on moving regions. In: Proc. 2009 SPIE-IS & T electronic imaging, 3D imaging metrology, vol 7239. pp 1–11, (2009)
  • [8] Moro A., Terabayashi K., Umeda K., Mumolo E., Auto-adaptive threshold and shadow detection approaches for pedestrians detection, Proc. 2009 Asian workshop on sensing and visualization of city–human interaction, pp. 9-12, (2009)
  • [9] Mitsui T., Fujiyoshi H., Object detection by joint features based on two-stage boosting, Proc. 12th ICCV workshop, pp. 1169-1176, (2009)
  • [10] Gordon N., Salmond D., Ewing C., Bayesian state estimation for tracking and guidance using the bootstrap filter, J Guid Control Dyn, 18, 6, pp. 1434-1443, (1995)
12