High frame-rate tracking of multiple color-patterned objects
详细信息 查看全文
- 作者：Qingyi Gu ; Tadayoshi Aoyama ; Takeshi Takaki…
- 关键词：Hardware implementation ; High ; frame ; rate vision ; Multiple color ; patterned objects tracking ; Cell ; based labeling
- 刊名：Journal of Real-Time Image Processing
- 出版年：2016
- 出版时间：February 2016
- 年：2016
- 卷：11
- 期：2
- 页码：251-269
- 全文大小：9,552 KB
- 参考文献：1.Swain, M.J., Ballard, D.H.: Color indexing. Int. J. Comput. Vis 7(1), 11–32 (1991)CrossRef
2.Funt, B.V., Finlayson, G.D.: Color constant color indexing. IEEE Trans. Patt. Mach. Anal. Intell 17(5), 522–529 (1995)CrossRef
3.Bradski, G.R.: Computer vision face tracking for use in a perceptual user interface. In: Proc. IEEE Workshop Appli. Comput. Vis. pp. 214–219 (1998)
4.Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean-shift. In: Proceedings of IEEE international conference on computer vision pattern recognition, vol. 2, pp. 142–149 (2000)
5.Leichter, I., Lindenbaum, M., Rivlin, E.: Mean Shift tracking with multiple reference color histograms. Comput. Vis. Image Underst. 114, 400–408 (2010)CrossRef
6.Koga, T., Ochiai, K., Suetake, N., Uchino, E.: Efficiency analysis of Preset Color Histogram in Mean-shift-based Crow Tracking. In: Proceedings of the international multiconference of engineering and computer scientists 2012 (IMECS2012), vol. I, pp. 736–739 (2010)
7.Hayashi, Y., Fujiyoshi, H.: Mean-shift-based color tracking in illuminance change. In: RoboCup 2007: Robot Soccer World Cup XI., pp. 302–311 (2007)
8.Jeong, D., Yang, Y.K., Kang, D.G., Ra, J.B.: Real-time head tracking based on color and shape information. In: Proceedings of the SPIE image and video communications and processing 2005, vol. 5685, pp. 912–923 (2005)
9.Isard, M., Blake, A.: CONDENSATION—conditional density propagation for visual tracking. Int. J. Comput. Vis. 29(1), 5–28 (1998)CrossRef
10.Nummiaro, K., Koller-Meier, E., Van Gool, L.: An adaptive color-based particle filter. Image Vis. Comput. 21(1), 99–110 (2003)
11.Chai, Y.J., Hwang, J.S., Chang, K., Choi, Y.J., Kim, T.Y.: Realtime User Interface using Particle Filter with Integral Histogram. In: International conference on consumer electronics (ICCE), pp. 245–246 (2010)
12.Zhao, Q., Tao, H.: A motion observable representation using color correlogram and its applications to tracking. Comput. Vis. Image Underst. 113(2), 273–290 (2009)CrossRef
13.Kalarot, R., Morris, J.: Real-time correlogram tracking for airborne traffic surveillance. In: International conference image and vision computing New Zealand, pp. 18–22 (2009)
14.Kotoulas, L., Andreadis, I.: Colour histogram content-based image retrieval and hardware implementation. In: International conference image and vision computing New Zealand, vol. 150, pp. 387–393 (2003)
15.Fleck, S., Lanwer, S., Straser, W.: A smart camera approach to real-time tracking. In: 13th European Signal Processing Conference (EUSIPCO), 4–8 Sept 2005
16.Wang, T.H., Chang, J.Y., Chen, L.G.: Algorithm and architecture for object tracking using particle filter. In: IEEE international conference on multimedia and expo, 2009 (ICME 2009), pp. 1374–1377 (2009)
17.Cherng, D.C., Yang, S.Y., Shen, C.F., Lu, Y.C.: Real time color based particle filtering for object tracking with dual cache architecture. In: 8th IEEE international conference on advanced video and signal-based surveillance (AVSS), pp. 148–153 (2011)
18.Watanabe, Y., Komuro, T., Ishikawa, M.: 955-fps real-time shape measurement of a moving/deforming object using high-speed vision for numerous-point analysis. In: Proceedings of IEEE international conference on robotics and automation, pp. 3192–3197 (2007)
19.Hirai, S., Zakoji, M., Masubuchi, A., Tsuboi, T.: Realtime FPGA-based vision system. J. Robot. Mechatron. 17(4), 401–409 (2005)
20.Ishii, I., Sukenobe, R., Taniguchi, T., Yamamoto, K.: Development of high-speed and real-time vision platform, H3 Vision. In: Proceedings of IEEE/RSJ international conference on intelligent robots systems, pp. 3671–3678 (2009)
21.Ishii, I. et al.: 2000 fps real-time vision system with high-frame-rate video recording. In: Proceedings of IEEE international conference on robotics and automation, pp. 1536–1541 (2010)
22.Cho, J., Benson, B., Mirazaei, S., Kastner, R.: Parallelized architecture of multiple classifiers for face detection. In: Proceedings of 20th IEEE international conference on application-specific systems, architecture and processors, 2009 Proceedings: Boston, MA, July 7, pp. 75–82 (2009)
23.Ishii, I., Tatebe, T., Gu, Q., Takaki, T.: Color-histogram-based tracking at 2000 fps. J. Electron. Imaging 21(1) (2012)
24.Gu, Q., Takaki, T., Ishii, I.: A fast multi-object extraction algorithm based on cell-based connected components labeling. In: IEICE Trans. Inf. Syst. E95-D(2), pp. 636–645 (2012)
25.Gu, Q., Takaki, T., Ishii, I.: 2000-fps multi-object extraction based on cell-based labeling. In: Proceedings of IEEE international conference on image processing, pp. 3761–3764 (2010)
26.Gu, Q., Takaki, T., Ishii, I.: Fast FPGA-based multi-object feature extraction. IEEE Trans. Circuits Syst. Video Technol. 23(1), 30–45 (2013)CrossRef
27.Smith, A.R.: Color gamut tranform pairs. Proc. SIGGRAPH Comput. Graph 12(3), 12–19 (1978)CrossRef
28.Ma, N., Bailey, D., Johnston, C.: (2008) Optimised single pass connected components analysis. In: International conference on field programmable technology, pp. 185–192. - 作者单位：Qingyi Gu (1)
Tadayoshi Aoyama (1)
Takeshi Takaki (1)
Idaku Ishii (1)
1. Hiroshima University, 1-4-1 Kagamiyama, Higashi-Hiroshima, Hiroshima, 739-8527, Japan - 刊物类别：Computer Science
- 刊物主题：Image Processing and Computer Vision
Multimedia Information Systems
Computer Graphics
Pattern Recognition
Signal,Image and Speech Processing - 出版者：Springer Berlin / Heidelberg
- ISSN：1861-8219
文摘
In this study, we develop a high frame-rate vision system that can execute color histogram-based tracking of multiple color-patterned objects in a 512 × 512 image at 2,000 fps by implementing an expanded cell-based labeling algorithm as the hardware logic. In the hardware implementation of the expanded cell-based labeling algorithm, the 16-bin hue-based color histograms of 1,024 color-patterned objects in an image can be extracted simultaneously by dividing the image into 8 × 8 cells concurrently, after calculating the 0th, 1st, and 2nd moment features to obtain the positions, areas, and orientation angles of multiple objects. We verified the effectiveness of our developed tracking system by performing several experiments using multiple color-patterned objects, which were always tracked even when they moved rapidly with occlusions in the camera views. Keywords Hardware implementation High-frame-rate vision Multiple color-patterned objects tracking Cell-based labeling