Abstract
The most successful approach for object detection is still applying a sliding window technique, where a pre-trained classifier is evaluated on different locations and scales. In this chapter, we interrogate this strategy in the context of stationary environments. In particular, having a fixed camera position observing the same scene a lot of prior (spatio-temporal) information is available. Exploiting this specific scene information allows for (a) improving the detection performance and (b) for reducing the model complexity; both on reduced computational costs! These benefits are demonstrated for two different real-world tasks (i.e., person and car detection). In particular, we apply two different evaluation/update strategies (holistic, grid-based), where any suited online learner can be applied. In our case we demonstrate the proposed approaches for different applications and scenarios, clearly showing their benefits compared to generic methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We refer a classifier to as an oracle, if it has a high precision, even at a low recall, and can thus be used to generate new training samples.
- 2.
http://www.cvg.rdg.ac.uk/PETS2006/ (November 30, 2012).
- 3.
http://www.eecs.qmul.ac.uk/~andrea/avss2007_d.html (November 30, 2012).
- 4.
This particular task was chosen as implementations of existing approaches as well as a number of benchmark datasets are publicly available.
- 5.
http://homepages.inf.ed.ac.uk/rbf/CAVIARDATA1 (November 30, 2012).
References
Abney S (2002) Bootstrapping. In: Proc annual meeting of the association for computational linguistics, pp 360–367
Agarwal S, Awan A, Roth D (2004) Learning to detect objects in images via a sparse, part-based representation. IEEE Trans Pattern Anal Mach Intell 26(11):1475–1490
Andrews S, Tsochantaridis I, Hofmann T (2003) Support vector machines for multiple-instance learning. In: Advances in neural information processing systems, pp 561–568
Babenko B, Yang M-H, Belongie S (2009) Visual tracking with online mulitple instance learning. In: Proc IEEE conf on computer vision and pattern recognition
Balcan M-F, Blum A, Yang K (2004) Co-training and expansion: towards bridging theory and practice. In: Advances in neural information processing systems, pp 89–96
Blum A, Mitchell T (1998) Combining labeled and unlabeled data with co-training
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proc IEEE conf on computer vision and pattern recognition
Dietterich TG, Lathrop RH, Lozano-Pérez T (1997) Solving the multiple instance problem with axis-parallel rectangles. Artif Intell 89(1–2):31–71
Dollár P, Wojek C, Schiele B, Perona P (2011) Pedestrian detection: an evaluation of the state of the art. IEEE Trans Pattern Anal Mach Intell 34(4):743–761
Felzenszwalb P, McAllester D, Ramanan D (2008) A discriminatively trained, multiscale, deformable part model. In: Proc IEEE conf on computer vision and pattern recognition
Freund Y, Schapire RE (1995) A decision-theoretic generalization of on-line learning and an application to boosting. In: Proc European conf on computational learning theory, pp 23–37
Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55:119–139
Friedman J (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29(5):1189–1232
Friedman J, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting. Ann Stat 28(2):337–374
Goldberg AB, Li M, Zhu X (2008) Online manifold regularization: a new learning setting and empirical study. In: Proc European conf on machine learning and knowledge discovery in databases, vol I, pp 393–407
Grabner H, Bischof H (2006) On-line boosting and vision. In: Proc IEEE conf on computer vision and pattern recognition
Grabner H, Roth PM, Bischof H (2007) Is pedestrian detection really a hard task? In: Proc IEEE workshop on performance evaluation of tracking and surveillance
Hoiem D, Efros AA, Hebert M (2006) Putting objects in perspective. In: Proc IEEE conf on computer vision and pattern recognition
Javed O, Ali S, Shah M (2005) Online detection and classification of moving objects using progressively improving detectors. In: Proc IEEE conf on computer vision and pattern recognition
Leibe B, Leonardis A, Schiele B (2008) Robust object detection with interleaved categorization and segmentation. Int J Comput Vis 77(1–3):259–289
Leistner C, Amir R, Saffari AA, Roth PM, Bischof H (2009) On robustness of on-line boosting—a competitive study. In: Proc IEEE on-line learning for computer vision workshop
Levin A, Viola P, Freund Y (2003) Unsupervised improvement of visual detectors using co-training. In: Proc IEEE int’l conf on computer vision
Li M, Sethi IK (2006) Confidence-based active learning. IEEE Trans Pattern Anal Mach Intell 28(8):1251–1261
Li L-J, Wang G, Fei-Fei L (2007) Optimol: automatic online picture collection via incremental model learning. In: Proc IEEE conf on computer vision and pattern recognition
Liu R, Cheng J, Lu H (2009) A robust boosting tracker with minimum error bound in a co-training framework. In: Proc IEEE int’l conf on computer vision
Mason L, Baxter J, Bartlett P, Frean M (1999) Functional gradient techniques for combining hypotheses. In: Advances in large margin classifiers. MIT Press, Cambridge, pp 221–247
McFarlane NJB, Schofield CP (1995) Segmentation and tracking of piglets. Mach Vis Appl 8(3):187–193
Nair V, Clark JJ (2004) An unsupervised, online learning framework for moving object detection. In: Proc IEEE conf on computer vision and pattern recognition
Park J-H, Choi Y-K (1996) On-line learning for active pattern recognition. IEEE Signal Process Lett 3(11):301–303
Rosenberg C, Hebert M, Schneiderman H (2005) Semi-supervised self-training of object detection models. In: IEEE workshop on applications of computer vision
Roth PM, Bischof H (2008) Conservative learning for object detectors. Machine learning techniques for multimedia. Springer, Berlin
Roth PM, Sternig S, Grabner H, Bischof H (2009) Classifier grids for robust adaptive object detection. In: Proc IEEE conf on computer vision and pattern recognition
Schapire RE (1990) The strength of weak learnability. Mach Learn 5(2):197–227
Schapire RE, Singer Y (2000) Boostexter: a boosting-based system for text categorization. Mach Learn 39(2/3):135–168
Skočaj D, Leonardis A (2008) Incremental and robust learning of subspace representations. Image Vis Comput 26(1):27–38
Sternig S, Godec M, Roth PM, Bischof H (2010) TransientBoost: on-line boosting with transient data. In: Proc IEEE online learning for computer vision workshop (in conj CVPR)
Sternig S, Roth PM, Bischof H (2012) On-line inverse multiple instance boosting for classifier grids. Pattern Recognit Lett 33(1):890–897
Tieu K, Viola P (2000) Boosting image retrieval. In: Proc IEEE conf on computer vision and pattern recognition, vol I, pp 228–235
Turtinen M, Pietikänien M (2005) Labeling of textured data with co-training and active learning. In: Proc workshop on texture analysis and synthesis, pp 137–142
Vapnik VN (1995) The nature of statistical learning theory. Springer, New York
Viola P, Jones MJ (2001) Rapid object detection using a boosted cascade of simple features. In: Proc IEEE conf on computer vision and pattern recognition
Viola P, Jones MJ, Snow D (2003) Detecting pedestrians using patterns of motion and appearance. In: Proc IEEE int’l conf on computer vision
Viola P, Platt JC, Zhang C (2005) Multiple instance boosting for object detection. In: Advances in neural information processing systems
Wei W, Zhou Z-H (2007) Analyzing co-training style algorithms. In: Proc European conf on machine learning, pp 454–465
Wu B, Nevatia R (2005) Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors. In: Proc IEEE int’l conf on computer vision
Wu B, Nevatia R (2007) Improving part based object detection by unsupervised, online boosting. In: Proc IEEE conf on computer vision and pattern recognition
Yan R, Yang J, Hauptmann A (2003) Automatically labeling video data using multi-class active learning. In: Proc IEEE int’l conf on computer vision, vol I, pp 516–523
Zhu Q, Avidan S, Cheng K-T (2005) Learning a sparse, corner-based representation for background modelling. In: Proc IEEE int’l conf on computer vision, vol I, pp 678–685
Acknowledgements
The work was supported by the Austrian Science Foundation (FWF) project Advanced Learning for Tracking and Detection in Medical Workflow Analysis (I535-N23) and by the Austrian Research Promotion Agency (FFG) projects SHARE (831717) in the IV2Splus program and MobiTrick (8258408) in the FIT-IT program.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag London
About this chapter
Cite this chapter
Roth, P.M., Sternig, S., Bischof, H. (2013). Learning Object Detectors in Stationary Environments. In: Farinella, G., Battiato, S., Cipolla, R. (eds) Advanced Topics in Computer Vision. Advances in Computer Vision and Pattern Recognition. Springer, London. https://doi.org/10.1007/978-1-4471-5520-1_13
Download citation
DOI: https://doi.org/10.1007/978-1-4471-5520-1_13
Publisher Name: Springer, London
Print ISBN: 978-1-4471-5519-5
Online ISBN: 978-1-4471-5520-1
eBook Packages: Computer ScienceComputer Science (R0)