Abstract
In this chapter we outline object detection and object recognition techniques which are of relevance for the remainder of the book. We focus on supervised and unsupervised learning approaches. The chapter provides technical details for each method, discussions on the strengths and weaknesses of each method, and gives examples and various applications for each method. Material is provided to support a decision for an appropriate object detection technique for computer vision applications, including driver-assistance systems.
This is a preview of subscription content, log in via an institution to check access.
Notes
- 1.
Named after the Hungarian mathematician Alfréd Haar (1885–1933).
- 2.
A region of interest is commonly a rectangular sub-image, say of size k × l, with \(\;k \ll N_{rows}\;\) and \(\;l \ll N_{cols}\;\), in which a weak classifier searches for an object.
- 3.
The sliding window, which defines the ROI, is a moving window starting from the top-left corner of an image, which moves over the image, from left to right, and top to bottom, in order to find feature matches in the query image. The sliding window starts with a small size (e.g. k = l = 20), and its size increases in each search iteration (up to the Max size of N cols × N rows ). The aim is to find feature matches for different window sizes, so ultimately detect any existing object, in any size, that falls in the region of a sliding window (or ROI).
- 4.
Different to a shadow, which is a silhouette cast by an object that blocks the source of either an indoor (e.g. candle) or outdoor light (e.g. sun), a shade is “darkness” that only applies to outdoor applications such as the shade underneath a tree, or the shade underneath a car. Of course, a car itself can also have a shadow. In our application, there are many challenges for driver’s face or vehicle detection, due to existing outdoor shades.
Bibliography
C.M. Bishop, Pattern Recognition and Machine Learning (Springer, New York, 2006)
G.R. Bradski, Computer vision face tracking for use in a perceptual user interface. Intel Technology J. 2nd Quarter (1998)
G. Bradski, A. Kaehler, Learning OpenCV (O’Reilly Media, Beijing, 2008)
R.G. Brown, P.Y.C. Hwang, Introduction to Random Signals and Applied Kalman Filtering: With MATLAB Exercises and Solutions, 2nd edn. (Wiley Publishing, New York, 1991)
Y. Cheng, Mean shift, mode seeking, and clustering. IEEE Trans. Pattern Anal. Mach. Intell. 17, 790–799 (1998)
D. Comaniciu, V. Ramesh, P. Meer, Real-time tracking of non-rigid objects using mean shift, in Proceedings of the IEEE Computer Vision Pattern Recognition (2000), pp. 673–678
C. Cortes, V. Vapnik, Support-vector networks. Mach. learn. 20, 273–297 (1995)
N. Dalal, B. Triggs, Histograms of oriented gradients for human detection, in Proceedings of the IEEE Computer Vision Pattern Recognition (2005), pp. 886–893
A.P. Dempster, N.M. Laird, D.B. Rubin, Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. 39, 1–38 (1997)
E.W. Forgy, Cluster analysis of multivariate data: efficiency versus interpretability of classifications. Biometrics 21, 768–769 (1965)
Y. Freund, R.E. Schapire, A decision-theoretic generalization of on-line learning and an application to boosting, in Proceedings of the European Conference on Computational Learning Theory (1995), pp. 23–37
INRIA Person Data Set, lear.inrialpes.fr/data (2005)
O.L.R. Jacobs, Introduction to Control Theory, 2nd edn. (Oxford University Press, Oxford/New York, 1993)
R. Jain, K. Rangachar, G.S. Brian, Machine Vision (McGraw-Hill, New York, 1995)
R.E. Kalman, A new approach to linear filtering and prediction problems. J. Basic Eng. 82, 35–45 (1960)
L.W. Kheng, Mean Shift Tracking. Department of Computer Science, National University of Singapore (2012), pp. 1–28
R. Klette, Concise Computer Vision: An Introduction into Theory and Algorithms (Springer, London, 2014)
S.P. Lloyd, Least square quantization in PCM. Bell Telephone Laboratories Paper (1982)
B.S. Lucas, T. Kanade, An iterative image registration technique with an application to stereo vision, in Proceedings of International Joint Conference on Artificial Intelligence, vol. 2 (1981), pp. 674–679
G.J. McLachlan, T. Krishnan, The EM algorithm and its extensions. J. Am. Stat. Assoc. 93, 403–405 (1997)
C. Papageorgiou, T. Poggio, A trainable system for object detection. Int. J. Comput. Vis. 38, 15–33 (2000)
J. Shi, C. Tomasi, Good features to track, in Proceedings of the IEEE Computer Vision Pattern Recognition (1994), pp. 593–600
K. Teknomo, k-means clustering tutorials. Medicine 100, 1–12 (2005)
C. Tomasi, T. Kanade, Detection and tracking of point features. Technical report CMU-CS-91-132. Int. J. Comput. Vis. (1991)
P. Viola, M. Jones, Rapid object detection using a boosted cascade of simple features, in Proceedings of the IEEE Computer Vision Pattern Recognition, vol. 1 (2001), pp. 511–518
Wikipedia, k-means clustering (2016), en.wikipedia.org/wiki/K-means_clustering
O.R. Zaiane, Principals of knowledge discovery in data. University of Alberta (2016)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this chapter
Cite this chapter
Rezaei, M., Klette, R. (2017). Object Detection, Classification, and Tracking. In: Computer Vision for Driver Assistance. Computational Imaging and Vision, vol 45. Springer, Cham. https://doi.org/10.1007/978-3-319-50551-0_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-50551-0_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-50549-7
Online ISBN: 978-3-319-50551-0
eBook Packages: Computer ScienceComputer Science (R0)