Skip to main content
Log in

Object detection using hybridization of static and dynamic feature spaces and its exploitation by ensemble classification

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

This paper presents a learning mechanism based on hybridization of static and dynamic learning. Realizing the detection performances offered by the state-of-the-art deep learning techniques and the competitive performances offered by the conventional static learning techniques, we propose the idea of exploitation of the concatenated (parallel) hybridization of the static and dynamic learning-based feature spaces. This is contrary to the cascaded (series) hybridization topology in which the initial feature space (provided by the conventional, static, and handcrafted feature extraction technique) is explored using deep, dynamic, and automated learning technique. Consequently, the characteristics already suppressed by the conventional representation cannot be explored by the dynamic learning technique. Instead, the proposed technique combines the conventional static and deep dynamic representation in concatenated (parallel) topology to generate an information-rich hybrid feature space. Thus, this hybrid feature space may aggregate the good characteristics of both conventional and deep representations, which are then explored using an appropriate classification technique. We also hypothesize that ensemble classification may better exploit this parallel hybrid perspective of the feature spaces. For this purpose, pyramid histogram of oriented gradients-based static learning has been incorporated in conjunction with convolution neural network-based deep learning to produce concatenated hybrid feature space. This hybrid space is then explored with various state-of-the-art ensemble classification techniques. We have considered the publicly available INRIA person and Caltech pedestrian standard image datasets to assess the performance of the proposed hybrid learning system. Furthermore, McNemar’s test has been used to statistically validate the outperformance of the proposed technique over various contemporary techniques. The validated experimental results show that the employment of the proposed hybrid representation results in effective detection performance (an AUC of 0.9996 for INRIA person and 0.9985 for Caltech pedestrian datasets) as compared to the individual static and dynamic representations.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Notes

  1. In the context of this paper, conventional, static, and handcrafted are interchangeably used. Likewise, the deep, dynamic, and automated are also interchangeably used.

References

  1. Deng L (2014) A tutorial survey of architectures, algorithms, and applications for deep learning. APSIPA Trans Signal Inf Process 3:e2

    Article  Google Scholar 

  2. Szarvas M, Yoshizawa A, Yamamoto M, Ogata J (2005) Pedestrian detection with convolutional neural networks. In: Proceedings of the intelligent vehicles symposium. IEEE, pp 224–229

  3. Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86:2278–2324

    Article  Google Scholar 

  4. LeCun Y, Kavukcuoglu K, Farabet C (2010) Convolutional networks and applications in vision. In: Proceedings of 2010 IEEE international symposium on circuits and systems (ISCAS), pp 253–256

  5. Ciresan DC, Meier U, Gambardella LM, Schmidhuber J (2011) Convolutional neural network committees for handwritten character classification. In: International conference on document analysis and recognition (ICDAR), pp 1135–1139

  6. Tao W, Wu DJ, Coates A, Ng AY (2012) End-to-end text recognition with convolutional neural networks. In: 21st international conference on pattern recognition (ICPR), pp 3304–3308

  7. Simard PY, Steinkraus D, Platt JC (2003) Best practices for convolutional neural networks applied to visual document analysis. In: Proceedings of the seventh international conference on document analysis and recognition, pp 958–963

  8. Chellapilla K, Puri S, Simard P (2006) High performance convolutional neural networks for document processing. In: Tenth international workshop on frontiers in handwriting recognition, La Baule

  9. Lawrence S, Giles CL, Ah Chung T, Back AD (1997) Face recognition: a convolutional neural-network approach. IEEE Trans Neural Netw 8:98–113

    Article  Google Scholar 

  10. Fasel B (2002) Robust face analysis using convolutional neural networks. In: Proceedings of the 16th international conference on pattern recognition, vol. 2, pp 40–43

  11. Abdel-Hamid O, Mohamed AR, Hui J, Li D, Penn G, Dong Y (2014) Convolutional Neural networks for speech recognition. IEEE/ACM Trans Audio Speech Lang Process 22:1533–1545

    Article  Google Scholar 

  12. Jialue F, Wei X, Ying W, Yihong G (2010) Human tracking using convolutional neural networks. IEEE Trans Neural Netw 21:1610–1623

    Article  Google Scholar 

  13. Shuiwang J, Wei X, Ming Y, Kai Y (2013) 3D convolutional neural networks for human action recognition. IEEE Trans Pattern Anal Mach Intell 35:221–231

    Article  Google Scholar 

  14. Cireşan DC, Giusti A, Gambardella LM, Schmidhuber J (2013) Mitosis Detection in breast cancer histology images with deep neural networks. In: Mori K, Sakuma I, Sato Y, Barillot C, Navab N (eds) Proceedings, Part II medical image computing and computer-assisted intervention—MICCAI 2013: 16th international conference, Nagoya. Springer, Berlin, pp 411–418, 22–26 Sept 2013

  15. Biglari O, Ahsan R, Rahi M (2014) Human detection using SURF and SIFT feature extraction methods in different color spaces. J Math Comput Sci (JMCS) 11:111–122

    Article  Google Scholar 

  16. Lowe DG (1999) Object recognition from local scale-invariant features. In: The proceedings of the seventh IEEE international conference on computer vision, vol. 2, pp 1150–1157

  17. Lowe D (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60:91–110

    Article  Google Scholar 

  18. Bay H, Tuytelaars T, Gool L (2006) SURF: speeded up robust features. In: Leonardis A, Bischof H, Pinz A (eds) Proceedings, Part I computer vision—ECCV 2006: 9th European conference on computer vision, Graz. Springer, Berlin, pp 404–417, 7–13 May 2006

  19. Bay H, Ess A, Tuytelaars T, Van Gool L (2008) Speeded-up robust features (SURF). Comput Vis Image Underst 110:346–359

    Article  Google Scholar 

  20. Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE computer society conference on computer vision and pattern recognition (CVPR), vol. 1, pp 886–893

  21. Anna B, Andrew Z, Xavier M (2007) Representing shape with a spatial pyramid kernel. In: Proceedings of the 6th ACM international conference on Image and video retrieval, Amsterdam, pp 401–408

  22. Murtza I, Abdullah D, Khan A, Arif M, Mirza S (2015) Cortex-inspired multilayer hierarchy based object detection system using PHOG descriptors and ensemble classification. Vis Comput 33:99–112

    Article  Google Scholar 

  23. Jin W, Ping L, She MFH, Kouzani A, Nahavandi S (2011) Human action recognition based on Pyramid Histogram of Oriented Gradients. In: 2011 IEEE international conference on systems, man, and cybernetics (SMC), pp 2449–2454

  24. Serre T, Wolf L, Bileschi S, Riesenhuber M, Poggio T (2007) Robust object recognition with cortex-like mechanisms. IEEE Trans Pattern Anal Mach Intell (PAMI) 29:411–426

    Article  Google Scholar 

  25. Serre T, Wolf L, Poggio T (2005) Object recognition with features inspired by visual cortex. In IEEE computer society conference on computer vision and pattern recognition (CVPR), vol. 2, pp 994–1000

  26. Watanabe T, Ito S, Yokoi K (2009) Co-occurrence histograms of oriented gradients for pedestrian detection. In: Wada T, Huang F, Lin S (eds) Advances in image and video technology, vol 5414. Springer, Berlin, pp 37–47

  27. Dalal N, Triggs B, Schmid C (2006) Human detection using oriented histograms of flow and appearance. In: Leonardis A, Bischof H, Pinz A (eds) Proceedings, Part II computer vision—ECCV 2006: 9th European conference on computer vision, Graz. Springer, Berlin, pp 428–441, 7–13 May 2006

  28. Hong H, Minglei T (2013) Human detection based on optical flow and spare geometric flow. In: 2013 seventh international conference on image and graphics (ICIG), pp 459–464

  29. Landwehr N, Hall M, Frank E (2005) Logistic model trees. Mach Learn 59:161–205

    Article  MATH  Google Scholar 

  30. Friedman J, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting. Ann Stat 28:337–407

    Article  MathSciNet  MATH  Google Scholar 

  31. Freund Y, Schapire RE (1996) Experiments with a new boosting algorithm. In Thirteenth international conference on machine learning, pp 148–156

  32. van de Sande KEA, Gevers T, Snoek CGM (2010) Evaluating Color descriptors for object and scene recognition. IEEE Trans Pattern Anal Mach Intell (PAMI) 32:1582–1596

    Article  Google Scholar 

  33. Levine MD (1969) Feature extraction: a survey. Proc IEEE 57:1391–1407

    Article  Google Scholar 

  34. Yanwei P, He Y, Yuan Y, Kongqiao W (2012) Robust CoHOG feature extraction in human-centered image/video management system. IEEE Trans Syst Man Cybern B Cybern 42:458–468

    Article  Google Scholar 

  35. Azar AT (2013) Fast neural network learning algorithms for medical applications. Neural Comput Appl 23:1019–1034

    Article  Google Scholar 

  36. Ebied HM, Revett K, Tolba MF (2013) Evaluation of unsupervised feature extraction neural networks for face recognition. Neural Comput Appl 22:1211–1222

    Article  Google Scholar 

  37. Bengio Y (2009) Learning deep architectures for AI. Found Trends Mach Learn 2:1–127

    Article  MATH  Google Scholar 

  38. Rebai I, BenAyed Y, Mahdi W (2016) Deep multilayer multiple kernel learning. Neural Comput Appl 27:2305–2314

    Article  Google Scholar 

  39. Liu W, Wang Z, Liu X, Zeng N, Liu Y, Alsaadi FE (2017) A survey of deep neural network architectures and their applications. Neurocomputing 234:11–26

    Article  Google Scholar 

  40. He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37:1904–1916

    Article  Google Scholar 

  41. Haykin S (2007) Neural networks: a comprehensive foundation, 3rd edn. Prentice-Hall Inc., Upper Saddle River, NJ, USA

    MATH  Google Scholar 

  42. Zhang GP (2000) Neural networks for classification: a survey. IEEE Trans Syst Man Cybern C (Appl Rev) 30:451–462

    Article  Google Scholar 

  43. Vedaldi A, Lenc K (2015) MatConvNet—convolutional neural networks for MATLAB. In: Proceeding of association of computing machinery (ACM) international conference on multimedia

  44. Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems 25 (NIPS 2012), pp 1097–1105

  45. Sutton RS, Barto AG (1998) Softmax action selection. In: Reinforcement learning: an introduction, Adaptive Computation and Machine Learning series, vol 17, no 2. MIT Press, Cambridge, pp 229–235. ISBN 0-262-19398-1

  46. Wintz PA (1972) Transform picture coding. Proc IEEE 60:809–820

    Article  Google Scholar 

  47. Jain A (1976) A fast Karhunen-Loeve transform for a class of random processes. IEEE Trans Commun 24:1023–1029

    Article  MathSciNet  MATH  Google Scholar 

  48. Sumner M, Frank E, Hall M (2005) Speeding up logistic model tree induction. In: Jorge AM, Torgo L, Brazdil P, Camacho R, Gama J (eds) Proceedings of the knowledge discovery in databases: PKDD 2005: 9th European conference on principles and practice of knowledge discovery in databases, Porto. Springer, Berlin, pp 675–683, 3–7 Oct 2005

  49. Witten IH, Frank E, Hall MA (2011) Data mining: practical machine learning tools and techniques with Java implementations, 3rd edn. Morgan Kaufmann Publishers Inc., Burlington, USA

    Google Scholar 

  50. Zhao L, Chen Y, Schaffner DW (2001) Comparison of logistic regression and linear regression in modeling percentage data. Appl Environ Microbiol 67: 2129–2135, Received 11 March Accepted 27 Feb 2001

  51. Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The WEKA data mining software: an update. ACM SIGKDD Explor Newsl 11:10–18

    Article  Google Scholar 

  52. Dalal N (2006) Finding people in images and videos. Doctoral Dissertation, Grenoble Institute of Technology, Grenoble, France

    Google Scholar 

  53. Dalal N (2005) INRIA person dataset. http://pascal.inrialpes.fr/data/human/

  54. Dollar P, Wojek C, Schiele B, Perona P (2009) Pedestrian detection: a benchmark. In: IEEE conference on computer vision and pattern recognition CVPR 2009, pp 304–311

  55. Dollar P, Wojek C, Schiele B, Perona P (2012) Pedestrian detection: an evaluation of the state of the art. IEEE Trans Pattern Anal Mach Intell 34:743–761

    Article  Google Scholar 

  56. McNemar Q (1947) Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika 12:153–157

    Article  Google Scholar 

  57. Forbes C, Evans M, Hastings N, Peacock B (2010) Chi squared distribution. In: Statistical distributions, 4th edn. Wiley, New Jersey, USA, pp 69–73. doi:10.1002/9780470627242.ch11

  58. Lancaster HO, Seneta E (2005) Chi square distribution. In: Encyclopedia of biostatistics. Wiley, New Jersey, USA. doi:10.1002/0470011815.b2a15018

Download references

Acknowledgements

We acknowledge Pakistan Institute of Engineering and Applied Sciences (PIEAS) for healthy research environment and Higher Education Commission (HEC) for providing funds which lead to the research work presented this article. This work is supported by the Higher Education Commission of Pakistan under NRPU Research Grant No. 20–3408 and Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2014R1A1A2053780).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Asifullah Khan.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Human and animal rights

No experiments were performed that involved humans/animals.

Informed consent

No human participants-based experiments were performed so not needed.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (DOCX 16 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Murtza, I., Khan, A. & Akhtar, N. Object detection using hybridization of static and dynamic feature spaces and its exploitation by ensemble classification. Neural Comput & Applic 31, 347–361 (2019). https://doi.org/10.1007/s00521-017-3050-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-017-3050-4

Keywords

Navigation