A Real-Time and Effective Object Recognition and Localization Method

Abstract:

In this paper, we realize object recognition and localization in a real time based on appearance features of object. For object recognition, we proposed to use global feauture (color) of images, and with an improved color image segmentation algorithm to realize threshold segmentation based on pixels in the image’s HSV color model by using the tool OpenCV, so we can realize the special color object recognition. Further the object can be localized with the ground constrained method by using the camera perspective geometry model. In the lab conditions, we realized single color object recognition and localization by transplanting the algorithm into Amigobots mobile robot and proved this method is simple, effective and real-time.

• Periodical: Applied Mechanics and Materials (Volume 615)
• Pages: 107-112
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.615.107
• Online since: August 2014
• Authors: Xiao Ling Ding*, Qiang Zhao, Yi Bin Li, Xin Ma
• Keywords: Camera Perspective Geometry Model, Color Image Segmentation Algorithm, Localization, Object Recognition, OpenCV, Threshold Segmentation Based on Pixels

References

[1] A. Torralba, K. Murphy. Context-based vision system for place and object recognition [C]. In: Proceedings of the International Conference on Computer Vision(ICCV), 2003: 273-280.

DOI: 10.1109/iccv.2003.1238354

[2] Ulrich, I. Nourbakhsh. Appearance-based place recognition for topological location[C]. In: International Conference on Robotics and Automation(ICRA), 2000: 1023-1029.

DOI: 10.1109/robot.2000.844734

[3] P. Blaer, P. Allen. Topological mobile robot localization using fast vision techniques[C]. In: International Conference on Robotics and Automation(ICRA), 2002: 1031-1036.

DOI: 10.1109/robot.2002.1013491

[4] C. Siagian, L. Itti. Rapid biologically-inspired scene classification using features shared with visual attention[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(PAMI), 2007, 29(2): 300-312.

DOI: 10.1109/tpami.2007.40

[5] S. Melacci, M. Maggini, M. Gori. Semi–supervised learning with constraints for multi–view object recognition[C]. Artificial Neural Networks(ICANN 2009), 2009: 653-662.

DOI: 10.1007/978-3-642-04277-5_66

[6] E. Delponte, N. Noceti, F. Odone, et. al. Appearance-based 3d object recognition with time-invariant features[C]. 14th International Conference on Image Analysis and Processing (ICIAP2007). Modena, Italy, 2007: 467-474.

DOI: 10.1109/iciap.2007.4362822

[7] H. Jun, W. Xi-Zhao, Z．Su-Fang, et. al．View-based 3d object recognition using wavelet multiscale singular-value decomposition and support vector machine[C]. Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition, Beijing, China, 2007: 1428-1432.

DOI: 10.1109/icwapr.2007.4421659

[8] J. Zhaoyin, C. Yao-Jen, C. Tsuhan. Active view selection for object and pose recognition[C]. 2009 IEEE 12th International Conference on Computer Vision Workshops(ICCV Workshops), 2009: 641-648.

DOI: 10.1109/iccvw.2009.5457643

[9] M. J. Swain, D. H. Ballard. Color indexing [J]. International Journal of Computer Vision, 1991, 7(1): 11-32.

[10] D. Roth, M. H. Yang. Learning to recognize three-dimensional objects [J]. Neural Computation, 2002, 14(5): 1071-1103.

DOI: 10.1162/089976602753633394

[11] M. H. Yang, D. Roth. Learning to recognize 3d objects with snow[C]. Proceedings of the Sixth European Conference on Computer Vision, 2000: 439-454.

DOI: 10.1007/3-540-45054-8_29

[12] Kurugollu. F, Sankur. B and Harmanci. A. E. Color Image Segmentation Using Histogram Multithresholding and Fusion[J]. Image and Vision Computing. 2001, 19(13): 915-92.

DOI: 10.1016/s0262-8856(01)00052-x