Implementing a Visual Servoing System for Robot Controlling

Authors: Maryam Vafadar, Alireza Behrad, Saeed Akbari

Abstract:

Nowadays, with the emerging of the new applications like robot control in image processing, artificial vision for visual servoing is a rapidly growing discipline and Human-machine interaction plays a significant role for controlling the robot. This paper presents a new algorithm based on spatio-temporal volumes for visual servoing aims to control robots. In this algorithm, after applying necessary pre-processing on video frames, a spatio-temporal volume is constructed for each gesture and feature vector is extracted. These volumes are then analyzed for matching in two consecutive stages. For hand gesture recognition and classification we tested different classifiers including k-Nearest neighbor, learning vector quantization and back propagation neural networks. We tested the proposed algorithm with the collected data set and results showed the correct gesture recognition rate of 99.58 percent. We also tested the algorithm with noisy images and algorithm showed the correct recognition rate of 97.92 percent in noisy images.

Keywords: Back propagation neural network, Feature vector, Hand gesture recognition, k-Nearest Neighbor, Learning vector quantization neural network, Robot control, Spatio-temporal volume, Visual servoing

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1061370

References:

[1] Pavel. A. and Buiu. C.: Development of an embedded artificial vision system for an autonomous robot, International Journal of Innovative Computing, Information and Control(ICIC 2011), Vol. 7, Num. 2, pp. 745-762, 2011.
[2] Ospina. E., Valencia. J. and Madrigal. C.: Traffic flow control using artificial vision techniques, 2011 6-th Colombian Computing Congress (CCC) available on IEEE explore, 2011.
[3] Cindy. X. You and Mark. A. Tarbell.: Microcomputer-based artificial vision support system for real-time image processing for camera-driven visual prostheses, Journal of Biomedical Optics, Vol. 15, Issue 1, Research Papers: Imaging, 2010.
[4] Harding. P.R.G. and Ellis. T.: Recognition Hand Gesture Using Fourier Descriptors, Proc. of IEEE Conf. on Pattern Recognition(ICPR2004), vol. 3, pp. 286-289, 2004.
[5] Dionisio. C.R.P., Cesar. R.M. and Jr.: A Project for Hand Gesture Recognition", Proc. of IEEE Symposium on Computer Graphics and Image Processing, pp. 345, 2000.
[6] Lamar. M.V., Bhuiyan M.S. and Iwata. A.: Hand Gesture Recognition Analysis and an Iimproved CombNET-II, Proc. Of IEEE Conf. on Man and Cybernetics, vol. 4, 1999.
[7] Moghaddam. B. and pentland. A.: Probabilistic Visual Learning for Object Detection, Conf. on Computer Vision, Cambridge, MA, 1995.
[8] Moghaddam. B.: Principal Manifolds and Bayesian Subspaces for Visual Recognition, Proc. Of IEEE Conf. on Computer Vision, ICCV99, 1999.
[9] Freeman. W.T. and Roth. M.: Orientation Histogram for Hand Gesture Recognition, IEEE Int. Workshop on Automatic face and gesture recognition, 1995.
[10] Shan. C., Yucheng. W., Xianchao. Q. and Tieniu. T.: Gesture Recognition Using Temporal Template Based Trajectories", Int. Conf. on Pattern Recognition, vol. 3, pp. 954 - 957, 2004.
[11] Kumar. S., Kumar. D.K., Sharma. A. and McLachlan. N.: Classification of Hand Movements Using Motion Templates and Geometrical based Moments, vol. 3, pp. 299 - 304, 2004.
[12] Vafadar. M. and Behrad. A.: Human Hand Gesture Recognition Using Motion Orientation Histogram for Interaction of Handicapped Persons with Computer, Proc. Of Int. Conf. on Image and Signal Processing, ICISP2008, 2008.
[13] Collins. T.: Analysing Video Sequences using the Spatio-temporal Volume, Informatic Research Review, 2004.
[14] Konrad. J. and Ristivojevic. M,: Joint Space-time image sequence segmentation:Object Tunnels and Occlusion Volumes, Proc. Of Int. Conf. on Acoustic, Speech and Signal Processing, 2004.
[15] Swaminathan. R., Kang. S.B. and Criminisi. A. and Szeliski. R.: On the Motion and Appearance of Specularities in Image Sequences, Proc. Of European Conf. in Computer Vision, 2002.
[16] Bolduc. M. M. and Deschenes. F.: Collision and Event Detection using Geometric Features in Spatio-temporal Volumes, Proc. Of IEEE Canadian Conf. on Computer and Robot Vision, CRV2005, 2005.
[17] Bloom. J. A. and Reed. T. R.: On the Compression of Video using the Derivative of Gaussian Transform, Proc. Conf. on Signals, Systems and Computers, 1998.
[18] Ohara. Y., Sagawa. R., Echigo. T. and Yagi. Y.: Gait Volume: Spatiotemporal Analysis of Walking, European Conference on Computer Vision, ECCV2004, 2004.
[19] Nianjun Liu Lovell. B. C. and Kootsookos. P. J.: Evaluation of HMM Training Algorithms for Letter Hand Gesture Recognition, IEEE Int. Sym. On Signal Processing and Information Technology, ISSPIT2003, 2003.
[20] Chang. M.C., Matshoba. L. and Preston. S., "A Gesture Driven 3D interface", Technical Report CS05-15-00, University of Cape Town, 2005.
[21] Yoon. H.S., Min. B.W., Soh. J., Bae. Y. and Yang. H.S., "Human Computer Interface for Gesture-based Editing System", IEEE Int. Conf. on Image Analysis and Processing, 1999.
[22] Liu. N., Lovell. B. C., Kootsookos. P. J., "Evaluation of HMM Training Algorithms for Letter Hand Gesture Recognition", IEEE Int. Sym. on Signal Processing and Information Technology, vol. 14-17, pp. 648 - 651, 2003.
[23] Shalbaf. R., vafadoost. M. and Shalbaf. A.: Lipreading Using Image Processing for Helping Handicap", Iranian conf. on Biomedical Engineering, 2007.