Skip to main content
SpringerLink
Log in

A novel feature-based tracking approach to the detection, localization, and 3-D reconstruction of internal defects in hardwood logs using computer tomography

  • Theoretical Advances
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

A novel feature-based tracking approach based on the Kalman filter is proposed for the detection, localization, and 3-D reconstruction of internal defects in hardwood logs from cross-sectional computer tomography (CT) images. The defects are simultaneously detected, classified, localized, and reconstructed in 3-D space, making the proposed scheme computationally much more efficient than existing methods where the defects are detected and localized independently in individual CT image slices and the 3-D reconstruction of the defects accomplished via correspondence analysis across the various CT image slices. Robust techniques for defect detection and classification are proposed. Defect class-specific tracking schemes based on the Kalman filter, B-spline contour approximation, and Snakes contour fitting are designed which use the geometric parameters of the defect contours as the tracking variables. Experimental results on cross-sectional CT images of hardwood logs from select species such as white ash, hard maple, and red oak are presented.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19

Similar content being viewed by others

References

  1. Haygreen JG, Bowyer JL (1996) Forest products and wood science: an introduction, 3rd edn. Iowa State University Press, Ames, Iowa

    Google Scholar 

  2. Hodges DG, Anderson WC, McMillin CW (1990) The economic potential of CT scanners for hardwood sawmills. For Prod J 40(3):65–69

    Google Scholar 

  3. Chang SJ (1990) NMR application for internal defect detection. In: Proceedings of process control/production management of wood products: technology for the 90s, Athens, Georgia

  4. Conners RW (1987) A computer vision system for grading hardwood lumber. In: Proceedings of the 2nd international conference on scanning technology in sawmilling, Oakland, CA

  5. Conners RW (1990) A multisensor machine vision system for hardwood defect detection. In: Proceedings of process control/ production management of wood products: technology for the ’90s, Annual Meeting, SE Section FPRS, Athens, GA

  6. Funck JW (1990) Softwood veneer defect detection using machine vision. In: Proceedings of process control/production management of wood products: technology for the ’90s, Annual Meeting, SE Section FPRS, Athens, GA,

  7. Funt BV, Bryant EC (1987) Detection of internal log defects by automatic interpretation of computer tomography images. For Prod J 37(1):56–62

    Google Scholar 

  8. Hailey JRT, Swanson JS (1987) Imaging wood using magnetic resonance. In: Proceedings of the 2nd international conference scanning technology in sawmilling, Oakland, CA

  9. Taylor FW, Wagner FG Jr, McMillin CW, Morgan IL, Hopkins FF (1984) Locating knots by industrial tomography—a feasibility study. For Prod J 34(5):42–46

    Google Scholar 

  10. Wagner FG, Taylor FW, Ladd DS, McMillin CW, Roder FL (1989) Ultrafast CT scanning of an oak log for internal defects. For Prod J 39(11/12):62–64

    Google Scholar 

  11. Richards DB (1977) Value yield from simulated hardwood log sawing. For Prod J 27(12):47–50

    Google Scholar 

  12. USDA Forest Service (1988) The South’s fourth forest: alternatives for the future. Forest service report no. 24

  13. Bhandarkar SM, Faust T, Tang M (1999) CATALOG: a system for detection and rendering of internal log defects using computer tomography. J Mach Vis Appl 11:171–190

    Article  Google Scholar 

  14. Bhandarkar SM, Faust TD, Tang M (2002) Design and prototype development of a computer vision-based lumber production planning system. J Image Vis Comput 20(3):167–189

    Article  Google Scholar 

  15. Roder FL, Scheinman E, Magnuson P (1989) High-speed CT scanning of logs. In: Proceedings of the 3rd international conference on scanning technology in sawmilling, San Francisco, California

  16. Kalman RE (1960) A new approach to linear filtering and prediction problems. ASME J Basic Eng, Ser D: 35–45

  17. Chang SJ, Olson JR, Wang PC (1989) NMR imaging of internal features in wood. For Prod J 39(6):43–49

    Google Scholar 

  18. McMillin CW (1982) Application of automatic image analysis to wood science. Wood Sci 14(3):97–105

    Google Scholar 

  19. Forrer JB, Butler DA, Funck JW, Brunner CC (1988) Image sweep-and-mark algorithms: part 1, basic algorithms. For Prod J 38(11/12):75–79

    Google Scholar 

  20. Forrer JB, Butler DA, Brunner CC, Funck JW (1988) Image sweep-and-mark algorithms: part 2, performance evaluations. For Prod J 39(1):39–42

    Google Scholar 

  21. McMillin CW, Conners RW, Huber HA (1984) ALPS—a potential new automated lumber processing system. For Prod J 34(1):13–20

    Google Scholar 

  22. Butler DA, Brunner CC, Funck JW (1989) A dual-threshold image sweep-and-mark algorithm for defect detection in veneer. For Prod J 39(5):25–28

    Google Scholar 

  23. Li P, Abbot AL, Schmoldt DL (1996) Automated analysis of CT images for inspection of hardwood logs. Proc. IEEE Int. Conf. Neural Netw: 1744–1749

  24. Schmoldt DL, Li P, Abbot AL (1997) Machine vision using artificial neural networks with local 3D neighborhoods. Comput Electron Agric 16:255–271

    Article  Google Scholar 

  25. Schmoldt DL, He J, Abbot AL (1998) A comparison of several artificial neural network classifiers for CT images of hardwood logs. In: Proceedings of the SPIE conference machine vision applications in industrial inspection VI, vol 3306, pp 34–43

  26. Butler DA, Brunner CC, Funck JW (1993) An adaptive image preprocessing algorithm for defect detection in Douglas-fir veneer. For Prod J 43(5):57–60

    Google Scholar 

  27. Coates ER, Chang SJ, Liao TW (1998) A quick defect detection algorithm for magnetic resonance images (MRI) of hardwood logs. For Prod J 48(10):68–74

    Google Scholar 

  28. Sarigul E, Abbot AL, Schmoldt DL (2003) Progress in analysis of computed tomography (CT) images of hardwood logs for defect detection. In: Proceedings of the tenth international conference on scanning technology and process optimization in the wood industry, ScanTech, Seattle, Washington, November 2003, pp 19–30

  29. Zhu D, Conners RW, Schmoldt DL, Araman PA (1996) A prototype vision system for analyzing CT imagery of hardwood logs. IEEE Trans. Syst Man Cybern Part B: Cybern 26(4):522–532

    Article  Google Scholar 

  30. Samson M (1993) Modeling of knots in logs. Wood Sci Technol 27:429–437

    Article  Google Scholar 

  31. Davis J, Wells P, Benci N, Grant J, McLachlan D (1995) Portable X-ray CT scanner for electricity power pole and tree inspection and a high resolution laboratory CT system. In: Proceedings of the 2nd international workshop on scanning technology and image processing on wood, Skelleftea, Sweden, pp 9–22

  32. Grundberg S, Grönlund A (1995) The development of a log scanner for Scots Pine. In: Proceedings of the 2nd international workshop on scanning technology and image processing on wood, Skelleftea, Sweden, pp 40–50

  33. Som S, Svalbe I, Davis J, Grant J, Gold E, Tsui K, Wells P (1995) Internal scanning of logs for grade evaluation and defect location. In: Proceedings of conference on digital image computing: techniques and applications (DICTA), Brisbane, Australia, pp 408–413

  34. Svalbe I, Som S, Davis J, Grant J, Tsui K, Wells P (1995) Internal scanning of logs for grade evaluation and defect location. In: Proceedings of the 2nd international workshop on scanning technology and image processing on wood, Skelleftea, Sweden, pp 1–8

  35. Chiorescu S, Grönlund A (2000) Validation of a CT-based simulator against a sawmill yield. For Prod J 50(6):69–76

    Google Scholar 

  36. Guddanti S, Chang SJ (1998) Replicating sawmill sawing with TOPSAW using CT images for a full-length hardwood log. For Prod J 48(1):72–75

    Google Scholar 

  37. Occena LG, Schmoldt DL (1996) GRASP: a prototype interactive graphic sawing program. For Prod J 46(11/12):40–42

    Google Scholar 

  38. Schmoldt DL, Li P, Araman PA (1996) Interactive simulation of hardwood log veneer slicing using CT images. For Prod J 46(4):41–47

    Google Scholar 

  39. Gatchell C, Klinkhachorn P, Kothari R (1992) ReGS—a realistic grading system. For Prod J 32(10):37–40

    Google Scholar 

  40. Klinkhachorn P, Schwehm CJ, McMillin CW, Huber HA (1989) HaLT: a hardwood lumber training program for graders. For Prod J 39(2):38–40

    Google Scholar 

  41. Klinkhachorn P, McMillin CW, Kothari R, Yost D (1992) HaLT2: an enhanced lumber grading trainer. For Prod J 42(10):38–40

    Google Scholar 

  42. Klinkhachorn P, Kothari R, Prasad R, McMillin CW, Mukherjee K (1993) Prototyping an automated lumber processing system (ALPS). For Prod J 43(2):11–18

    Google Scholar 

  43. Klinkhachorn P, Kothari R, Annavajjhala R, McMillin CW (1993) TRSys—hardwood lumber grading training and remanufacturing system. For Prod J 44(9):69–72

    Google Scholar 

  44. Moody J, Gatchell CJ, Walker ES, Klinkhachorn P (1998) An introduction to UGRS: the ultimate grading and remanufacturing system. For Prod J 48(9):45–50

    Google Scholar 

  45. Chang SJ, Guddanti S, Cooper CS (1997) Measuring the benefits of internal log defect scanning: a mill-based study. In: Proceedings of the international conference on scanning technology and process optimization for the wood products industry, November 12–14, 1997, Charlotte, NC, pp 25–28

  46. Pham DT, Alcock RJ (1998) Automated grading and defect detection: a review. For Prod J 48(4):34–42

    Google Scholar 

  47. Mairinger F (2003) Strahlenuntersuchung an Kunstwerken. E.A. Seemann, Berlin

    Google Scholar 

  48. Kass M, Witkin A, Terzopoulos D (1988) Snakes: active contour models. Int J Comput Vis 1(4):321–331

    Article  Google Scholar 

  49. Sonka M, Hlavac V, Boyle R (1998) Image processing, analysis and machine vision, 2nd edn. PWS Publishing, Boston

  50. Cychosz JM (1994) Efficient binary image thinning using neighborhood maps. Graphics gems IV. Academic, New York, pp 465–473

  51. Fischler M, Bolles R (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24(6):381–395

    Article  MathSciNet  Google Scholar 

  52. Bhandarkar SM, Luo X, Daniels R, Tollner EW (2005) Detection of cracks in computer tomography images of logs. Pattern Recognit Lett 26(5):2282–2294

    Article  Google Scholar 

  53. Graham RL (1972) An efficient algorithm for determining the convex hull of a finite point set. Inf Proc Lett 1(4):132–133

    Article  MATH  Google Scholar 

  54. Xu C, Prince JL (1997) Gradient vector flow: a new external force for Snakes. In: Proceedings of the IEEE conference on computer vision pattern recognition, San Juan, Puerto Rico, pp 66–71

  55. Koller D, Weber J, Malik J (1993) Robust multiple car tracking with occlusion reasoning. Computer Science Division (EECS), University of California, Report No. UCB/CSD 93-780, Berkeley, California, USA, October 1993

  56. Koller D, Weber JW, Malik J (1994) Robust multiple car tracking with occlusion reasoning. In: Proceedings of the European conference on computer vision. Stockholm, Sweden, pp 189–196

  57. Koller D, Weber J, Huang T, Malik J, Ogasawara G, Rao B, Russell S (1994) Towards robust automatic traffic scene analysis in real-time. In: Proceedings of the international conference on pattern recognition, Jerulasem, Israel, October 1994, pp 126–131

Download references

Acknowledgments

This research was supported in part by a NRICGP award by the US Department of Agriculture to Drs. Bhandarkar, Daniels, and Tollner (Award Number 2001-35103-10049).

Author information

Authors and Affiliations

  1. Department of Computer Science, The University of Georgia, Athens, GA, 30602-7404, USA

    Suchendra M. Bhandarkar & Xingzhi Luo

  2. Warnell School of Forest Resources, The University of Georgia, Athens, GA, 30602-2152, USA

    Richard Daniels

  3. Department of Biological and Agricultural Engineering, The University of Georgia, Athens, GA, 30602-4435, USA

    E. William Tollner

Authors
  1. Suchendra M. Bhandarkar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xingzhi Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Richard Daniels
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. E. William Tollner
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Suchendra M. Bhandarkar.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Bhandarkar, S.M., Luo, X., Daniels, R. et al. A novel feature-based tracking approach to the detection, localization, and 3-D reconstruction of internal defects in hardwood logs using computer tomography. Pattern Anal Applic 9, 155–175 (2006). https://doi.org/10.1007/s10044-006-0035-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-006-0035-9

Keywords

Search

Navigation