Abstract
The need for highly accurate classification systems capable of working on real-time applications has increased in recent years. Nowadays, several computer vision tasks apply a classification step as part of bigger systems, hence requiring classification models that work at a fast pace. This rendered interesting the concept of real-time object classification to several research communities. In this paper, we propose to accelerate a bio-inspired model for object classification, which has given very good results when compared with other state-of-the-art proposals using the compute unified device architecture (CUDA) and exploiting computational capabilities of graphic processing units. The classification model that is used is called the artificial visual cortex, a novel bio-inspired approach for image classification. In this work, we show that through an implementation of this model in the CUDA framework it is possible to achieve real-time functionality. As a result, the proposed system is able to process images in average of up to 90 times faster than the original system.
Similar content being viewed by others
References
Hsuan L, Chih-Yin L, Chih-Jui L, Chien-Feng H, Ri-Wei D, Tzuu-Hseng S (2014) Implementation of real-time object recognition system for home-service robot by integrating SURF and BRISK. IEEE international conference on system science and engineering (ICSSE), pp 273–278
Muller UA, Jackel LD, LeCun Y, Flepp B (2013) Real-time adaptive off-road vehicle navigation and terrain classification. Proc SPIE, Unmanned Syst Technol XV 8741:87410A–1
Salas-Moreno RF, Newcombe RA, Strasdat H, Kelly PHJ, Davison AJ (2013) SLAM++: simultaneous localisation and mapping at the level of objects. IEEE conference on computer vision and pattern recognition (CVPR) 1352(1359):23–28
Zhang X, Yang Y-H, Han Z, Wang H, Gao C (2013) Object class detection: a survey. ACM Comput Surv 46(1, 10):53
Olague G (2016) Evolutionary computer vision: the first footprints. Springer, Berlin, p 411
Dozal L, Olague G, Clemente E, Hernández DE (2014) Brain programming for the evolution of an artificial dorsal stream. Cognit Comput 6(3):528–557
Hernández DE, Clemente E, Olague G, Briseño JL (2016) Evolutionary multi-objective visual cortex for object classification in natural images. J Comput Sci 17(1):216–233
Malik ZK, Hussain A, Wu J (2014) Novel biologically inspired approaches to extracting online information from temporal data. Cognit Comput 6(3):595–607
Yang Y, Wu QMJ, Wang Y, Zeeshan KM, Lin X, Yuan X (2014) Data partition learning with multiple extreme learning machines. IEEE Trans Cybern 45(8):1463–1475
Ng LT, Suandi SA, Teoh SS (2014) Vehicle classification using visual background extractor and multi-class support vector machines. The 8th international conference on robotic, vision, signal processing & power applications. Lecture notes in electrical engineering, vol 291, pp 221–227
Asano S, Maruyama T, Yamaguchi Y (2009) Performance comparison of FPGA, GPU and CPU in image processing. International conference on field programmable logic and applications. FPL, pp 126–131
Lu M (2013) Fast implementation of scale invariant feature transform based on CUDA. Appl Math Inf Sci 7(2):717–722
Chase J, Nelson B, Bodily J, Wei Z, Lee D (2008) Real-time optical flow calculations on FPGA and GPU architectures: a comparison study. 16th international symposium on field-programmable custom computing machines. FCCM ’08, pp 173–182
Jiang S, Wang Y, Chen Z, Sun K (2014) Real-time brain extraction method from cerebral MRI volume based on graphic processing units. Neural Comput Appl 25(5):1145–1151
Ohmer J, Maire F, Brown R (2006) Implementation of kernel methods on the GPU. Digital image computing: techniques and applications, DICTA 05. Queensland, Australia, pp 1–8
Uetz R, Behnke S (2009) Large-scale object recognition with CUDA-accelerated hierarchical neural networks. IEEE international conference on intelligent computing and intelligent systems, ICIS 09, pp 1–6
Chikkerur S (2008) CUDA implementation of a biologically inspired object recognition system. MIT technical report
Mutch J, Knoblich U, Poggio T (2010) CNS: a GPU-based framework for simulating cortically-organized networks. MIT technical report
Parks D, Jain A, McInerney J, Itti L (2010) GPGPU-based real-time object detection and recognition system. J Vis 10(7):997
Woodbeck K, Roth G, Huiqiong C (2008) Visual cortex on the GPU: biologically inspired classifier and feature descriptor for rapid recognition. IEEE computer society conference on computer vision and pattern recognition workshops. CVPRW ’08, pp 1–8
Olague G, Clemente E, Dozal L (2014) Evolving an artificial visual cortex for object recognition with brain programming. EVOLVE—A bridge between probability set oriented numeric and evolutionary computation III, studies in computational intelligence, Springer, vol 500, pp 97–119
LeCun Y, Bottou L, Orr GB, Müller KR (1998) Efficient backprop. Neural Netw Tricks Trade LNCS 1524:9–50
Bouvrie J (2006) Notes on convolutional neural networks. Center for biological and computational learning, MIT tutorial
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Ciresan D, Meier U, Masci J, Gambardella LM, Schmidhuber J (2011) Flexible, high performance convolutional neural networks for image classification. IJCAI’11 proceedings of the twenty-second international joint conference on artificial intelligence, vol 2, pp 1237 –1242
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(10):1929–1958
Dhanasekaran B, Rubin N (2011) A new method for GPU based irregular reductions and its application to K-means clustering. In: Proceedings of the fourth workshop on general purpose processing on graphics processing units, vol 2, pp 2- 8
Xiao Y, Leung CS, Ho T, Lam P (2011) A GPU implementation for LBG and SOM training. Neural Comput Appl 20(7):1035–1042
Nantes A, Brown R, Maire F (2013) Neural network-based detection of virtual environment anomalies. Neural Comput Appl 23(6):1711–1728
Milner AD, Goodale MA (2006) The visual brain in action, 2nd edn. Oxford University Press, Oxford, p 297
Clemente E, Chavez F, Fernandez de Vega F, Olague G (2015) Self-adjusting focus of attention in combination with a genetic fuzzy system for improving a laser environment control device system. Appl Soft Comput 32:250–265
Olesen SM, Lyder S (2010) Applying 2D filters using GPU’s and CUDA. Vision 3—advanced topics in computer vision
Sanders J, Kandrot E (2010) CUDA by example: an introduction to general-purpose gpu programming. Addison-Wesley, Boston, p 290
Podlozhnyuk V (2007) Image convolution with CUDA. NVIDIA corporation technical report, pp 1–21
Huang Y, Huang K, Tao D, Tan T, Li X (2011) Enhanced biologically inspired model for object recognition. IEEE Trans Syst Man Cybern Part B 41(6):1668–1680
Opelt A, Pinz A, Fussenegger M, Auer P (2006) Generic object recognition with boosting. IEEE Trans Pattern Anal Mach Intell 28(3):416–431
Ghodrati M, Khaligh-Razavi S, Ebrahimpour R, Rajaei K, Pooyan M (2012) How can selection of biologically inspired features improve the performance of a robust object recognition model? Plos ONE 7(2):1–15
Mutch J, Lowe DG (2008) Object class recognition and localization using sparse features with limited receptive fields. Int J Comput Vis 80(1):45–57
Pshikhopov VKh, Medvedev MY, Sirotenko MY, Kostjukov VA (2009) Control system design for robotic airship. 9th IFAC symposium on robot control. Gifu, Japon, vol 42, no 16, pp 26–31
Acknowledgements
This research was funded by CONACyT through Project 155045—“Evolución de Cerebros Artificiales en Visión por Computadora” and by CICESE project number 634119. Dr. Olague graciously acknowledges the support of the Seventh Framework Programme of the European Union through the Marie Curie International Research Staff Scheme, FP7-PEOPLE-2013-IRSES, Grant 612689 ACoBSEC, project Analysis and Classification of Mental States of Vigilance with Evolutionary Computation.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hernández, D.E., Olague, G., Hernández, B. et al. CUDA-based parallelization of a bio-inspired model for fast object classification. Neural Comput & Applic 30, 3007–3018 (2018). https://doi.org/10.1007/s00521-017-2873-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-017-2873-3