Abstract
An experimental vehicle is being developed for the purposes of precise crop treatment, with the aim of reducing chemical use and thereby improving quality and reducing both costs and environmental contamination. For differential treatment of crop and weed, the vehicle must discriminate between crop, weed and soil. We present a two stage algorithm designed for this purpose, and use this algorithm to illustrate how empirical discrepancy methods, notably the analysis of type I and type II statistical errors and receiver operating characteristic curves, may be used to compare algorithm performance over a set of test images which represent typical working conditions for the vehicle. Analysis of performance is presented for the two stages of the algorithm separately, and also for the combined algorithm. This analysis allows us to understand the effects of various types of misclassification error on the overall algorithm performance, and as such is a valuable methodology for computer vision engineers.
Chapter PDF
Keywords
- Receiver Operating Characteristic
- Ground Truth
- Receiver Operating Characteristic Curve
- Association Region
- Automatic Tracking
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
IE Abdou. Quantitative methods of edge detection. Technical Report USCIPI Report 830, University of California Image Processing Institute, July 1978.
D C Alexander and B F Buxton. Modelling of sinlge mode distributions of colour data using directional statistics. In Proceedings Computer Vision and Pattern Recognition, 1997.
Y Bar-Shalom and T Fortmann. Tracking and Data Association. Academic Press, New York, 1988.
H.R. Biller. Reduced input of herbicides by use of optoelectronic sensors. Journal of Agricultural Engineering Research, 71:357–362, 1998.
K Bowyer, C Kranenburg, and S Dougherty. Edge detector evaluation using empirical ROC curves. In Proc. CVPR, volume 1, 1999.
G J Edwards, C J Taylor, and T F Cootes. Improving identification performance by integrating evidence from sequences. In Proc. CVPR, volume 1, 1999.
H Freeman. On the encoding of arbitrary geometric configurations. IEEE Trans. Elec. Computers, EC-10:260–268, 1961.
D M Green and J A Swets. Signal Detection Theory and Psychophysics. John Wiley and Sons, 1966.
J A Hanley and B J McNeil. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology, 143:29–36, April1982.
R M Haralick. Performance characterization protocol in computer vision. In DARPA Image Understanding Workshop, 1994.
M G M Hunink, R G M Deslegte, and M F Hoogesteger. ROC analysis of the clinicl, CT and MRI diagnosis of orbital space-occupying lesions. ORBIT, 8(3), September 1989.
M Oren and S K Nayar. Generalization of the Lambertian model and implications for machine vision. International Journal of Computer Vision, 14:227–251, 1995.
B Rao. Data association methods for tracking systems. In A Blake and A Yuille, editors, Active Vision, chapter 6. MIT Press, 1992.
M J J Scott, M Niranjan, and R W Prager. Realisable classifiers: Improving operating performance on variable cost problems. In Proceedings BMVC 1998, volume I, pages 306–315, September 1998.
B Southall, B F Buxton, and J A Marchant. Controllability and observability: Tools for Kalman filter design. In M S Nixon, editor, Proceedings 9 thBritish Machine Vision Conference, volume 1, pages 164–173, September 1998.
B Southall, T Hague, J A Marchant, and B F Buxton. Vision-aided outdoor navigation of an autonomous horticultural vehicle. In Henrik I Christensen, editor, Proceedings 1 stInternational Conference on Vision Systems. Springer Verlag, January 1999.
B Southall, J A Marchant, T Hague, and B F Buxton. Model based tracking for navigation and segmentation. In H Burkhardt and B Neumann, editors, Proceedings 5 thEuropean Conference on Computer Vision, volume 1, pages 797–811, June 1998.
J B Southall. The design and evaluation of computer vision algorithms for the control of an autonomous horticultural vehicle. PhD thesis, University of London, 2000.
M R Spiegel. Probability and Statistics. Schaum’s Outline Series. McGraw Hill, 1980.
B van Branniken, M Stavridi, and J J Koenderink. Diffuse and specular reflectance from rough surfaces. Applied Optics, 37(1):130–139, January 1998.
H L van Trees. Detection, Estimation and Modulation Theory, Part I. John Wiley and Sons, 1968.
Y J Zhang. A survey on evaluation methods for image segmentation. Pattern Recognition, 29(8):1335–1346, 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Southall, B., Buxton, B.F., Marchant, J.A., Hague, T. (2000). On the Performance Characterisation of Image Segmentation Algorithms: A Case Study. In: Vernon, D. (eds) Computer Vision — ECCV 2000. ECCV 2000. Lecture Notes in Computer Science, vol 1843. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45053-X_23
Download citation
DOI: https://doi.org/10.1007/3-540-45053-X_23
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67686-7
Online ISBN: 978-3-540-45053-5
eBook Packages: Springer Book Archive