Skip to main content
SpringerLink
Log in

A neural network based retrainable framework for robust object recognition with application to mobile robotics

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

In this paper, we address object recognition for a mobile robot which is deployed in a multistory building. To move to another floor, a mobile robot should recognize various objects related to an elevator, e.g., elevator control, call buttons, and LED displays. To this end, we propose a neural network based retrainable framework for object recognition, which consists of four components—preprocessing, binary classification, object identification, and outlier rejection. The binary classifier, a key component of our system, is a neural network that can be retrained, the motivation of which is to adapt to varying environments, especially with illuminations. Without incurring any extra process to prepare new training samples for retraining, they are freely obtained as a result of the outlier rejection component, being extracted on-line. To realize a practical system, we adopt a parallel architecture integrating both recognition and retraining processes for seamless object recognition, and furthermore detect and cope with the deterioration of a retrained neural network to ensure high reliability. We demonstrate the positive effect of retraining on the object recognition performance by conducting experiments over hundreds of images obtained in daytime and nighttime.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Hüttenrauch H, Eklundh KS (2002) Fetch-and-carry with CERO observations from a long-term study with a service robot. In: IEEE international workshop on robot and human interactive communication, pp 158–163

  2. Thrun S, Bennewitz M, Burgard W, Cremers AB, Dellaert F, Fox D (1999) MINERVA: a second-generation museum tour-guide robot. In: IEEE international conference on robotics and automation, pp 1999–2005

  3. Bischoff R, Graefe V (2002) HERMES—a versatile personal robotic assistant. Proc IEEE 92(11):1759–1779, Special issue on human interactive robots for psychological enrichment

    Article  Google Scholar 

  4. Simmons R et al (2003) Grace: an autonomous robot for the AAAI robot Challenge. AAAI Mag 42(2):51–72

    Google Scholar 

  5. Tschichold-Gürman N, Vestli SJ, Schweitzer G (2001) The service robot MOPS: first operating experiences. Robot Auton Syst 34(2–3):165–173

    Article  MATH  Google Scholar 

  6. Ramaswamy S, Rastogi R, Shim K (2000) Efficient algorithms for mining outliers from large data sets. In: ACM SIGMOD conference on management of data, Dallas, TX, pp 427–438

  7. Breunig MM, Kriegel H, Ng RT, Sander J (2000) LOF: identifying density-based local outliers. In: Proceedings of ACM SIGMOD International conference on management of data, Dallas, TX, pp 93–104

  8. Olson E, Leonard JJ, Teller S (2006) Robust range-only beacon localization. IEEE J Ocean Eng 31(4):949–958

    Article  Google Scholar 

  9. Doulamis AD, Doulamis ND, Kollias SD (2000) On line retrainable neural networks: improving the performance of neural networks in image analysis problems. IEEE Trans Neural Netw 11(1):137–155

    Article  Google Scholar 

  10. Ioannou S, Kessous L, Caridakis G, Karpouzis K, Aharonson V, Kollias S (2006) Adaptive on-line neural network retraining for real life multimodal emotion recognition. In: International conference on artificial neural networks (ICANN), pp 81–92

  11. Chan FHY, Lam FK, Zhu H (1998) Adaptive thresholding by variational method. IEEE Trans Image Process 7(3):468–473

    Article  Google Scholar 

  12. Gonzales R, Woods R (1992) Digital image processing. Addison-Wesley, Reading

    Google Scholar 

  13. Haykin S (1999) Neural networks: a comprehensive foundation. Prentice-Hall, New Jersey

    MATH  Google Scholar 

  14. West DB (2001) Introduction to graph theory, 2nd edn. Prentice-Hall, New Jersey

    Google Scholar 

  15. Osowski S, Linh TH (2001) ECG beat recognition using fuzzy hybrid neural network. IEEE Trans Biomed Eng 48(11):1265–1271

    Article  Google Scholar 

  16. Er MJ, Wu S, Lu J, Toh HL (2002) Face recognition with radial basis function (RBF) neural networks. IEEE Trans Neural Netw 13(3):697–710

    Article  Google Scholar 

  17. Magoulas GD, Plagianakos VP, Vrahatis MN (2004) Neural network-based colonoscopic diagnosis using on-line learning and differential Evolution. Appl Soft Comput 4(4):369–379

    Article  Google Scholar 

  18. Rowley HA, Baluja S, Kanade T (1998) Neural network-based face detection. IEEE Trans Pattern Anal Mach Intell 20(1):23–38

    Article  Google Scholar 

  19. Zou AM, Hou ZG, Fu SY, Tan M (2006) Neural networks for mobile robot navigation: a survey. In: International symposium on neural networks. LNCS, vol 3972. Springer, Berlin, pp 1218–1226

    Google Scholar 

  20. Chohra A, Benmehrez A (1998) Neural navigation approach for intelligent autonomous vehicles (IAV) in partially structured environments. Appl Intell 8(3):219–233

    Article  Google Scholar 

  21. Han SJ, Oh SY (2008) An optimized modular neural network controller based on environment classification and selective sensor usage for mobile robot reactive navigation. Neural Comput Appl 17(2):161–173

    Article  Google Scholar 

  22. Egmont-Petersen M, De Ridder D, Handels H (2002) Image processing with neural networks—a review. Pattern Recognit 35(10):2279–2301

    Article  MATH  Google Scholar 

  23. Ou G, Murphey YL (2007) Multi-class pattern classification using neural networks. Pattern Recognit 40(1):4–18

    Article  MATH  Google Scholar 

  24. Zhang ZP (2000) Neural networks for classification: a survey. IEEE Trans Syst Man Cybern, Part C, Appl Rev 30(4):451–462

    Article  Google Scholar 

  25. Lippmann RP (1989) Pattern classification using neural networks. IEEE Commun Mag 27(11):59–64

    Article  Google Scholar 

  26. Hodge VJ, Austin J (2004) A survey of outlier detection methodologies. Appl Intell Rev 22(2):85–126

    Article  MATH  Google Scholar 

  27. Dillencourt MB, Samet H, Tamminen M (1992) A general approach to connected-component labeling for arbitrary image representations. J ACM 39(2):253–280

    Article  MathSciNet  MATH  Google Scholar 

  28. Reed R (1993) Pruning algorithms—a survey. IEEE Trans Neural Netw 4(5):740–747

    Article  Google Scholar 

  29. Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110

    Article  Google Scholar 

  30. Lowe DG (1999) Object recognition from local scale-invariant features. In: Proceedings of the international conference on computer vision (ICCV), Corfu, Greece, pp 1150–1157

  31. French RM (1999) Catastrophic forgetting in connectionist networks. Trends Cogn Sci 3(4):128–135

    Article  MathSciNet  Google Scholar 

  32. Robins A (1995) Catastrophic forgetting, rehearsal and pseudorehearsal. Connect Sci 7(2):123–146

    Article  Google Scholar 

  33. Nguyen D, Widrow B (1990) Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. In: International joint conference of neural networks, vol 3, pp 21–26

Download references

Author information

Authors and Affiliations

  1. Intelligent Robotics Lab, LG-302, Dept. of Electronic and Electrical Eng., Pohang University of Science and Technology, Pohang, Gyungbuk, 790-784, South Korea

    Su-Yong An, Jeong-Gwan Kang, Won-Seok Choi & Se-Young Oh

Authors
  1. Su-Yong An
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jeong-Gwan Kang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Won-Seok Choi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Se-Young Oh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Se-Young Oh.

Rights and permissions

Reprints and permissions

About this article

Cite this article

An, SY., Kang, JG., Choi, WS. et al. A neural network based retrainable framework for robust object recognition with application to mobile robotics. Appl Intell 35, 190–210 (2011). https://doi.org/10.1007/s10489-010-0212-9

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-010-0212-9

Keywords

Search

Navigation