Abstract
We propose reliable outdoor object detection on mobile phone imagery from off-the-shelf devices. With the goal to provide both robust object detection and reduction of computational complexity for situated interpretation of urban imagery, we propose to apply the ’Informative Descriptor Approach’ on SIFT features (i-SIFT descriptors). We learn an attentive matching of i-SIFT keypoints, resulting in a significant improvement of state-of-the-art SIFT descriptor based keypoint matching. In the off-line learning stage, firstly, standard SIFT responses are evaluated using an information theoretic quality criterion with respect to object semantics, rejecting features with insufficient conditional entropy measure, producing both sparse and discriminative object representations. Secondly, we learn a decision tree from the training data set that maps SIFT descriptors to entropy values. The key advantages of informative SIFT (i-SIFT) to standard SIFT encoding are argued from observations on performance complexity, and demonstrated in a typical outdoor mobile vision experiment on the MPG-20 reference database.
This work is supported by the European Commission funded projects MACS under grant number FP6-004381 and MOBVIS under grant number FP6-511051, and by the FWF Austrian Joint research Project Cognitive Vision under sub-projects S9103-N04 and S9104-N04.
Chapter PDF
Similar content being viewed by others
Keywords
- Object Recognition
- Object Detection
- Object Representation
- Scale Invariant Feature Transform
- Local Descriptor
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
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 264–271 (2003)
Friedman, J.H., Bentley, J.L., Finkel, R.A.: An algorithm for finding best matches in logarithmic expected time. ACM Transactions on Mathematical Software 3(3), 209–226 (1977)
Fritz, G., Paletta, L., Bischof, H.: Object recognition using local information content. In: Proc. International Conference on Pattern Recognition, ICPR 2004, Cambridge, UK, vol. II, pp. 15–18 (2004)
Hall, D., Leibe, B., Schiele, B.: Saliency of interest points under scale changes. In: Proc. British Machine Vision Conference, BMVC 2002, Cardiff, UK (2002)
Ke, Y., Sukthankar, R.: Pca-sift: A more distinctive representation for local image descriptors. In: Proc. Computer Vision and Pattern Recognition, CVPR 2004, Washington, DC, vol. 2, pp. 506–513 (2004)
Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)
Mikolajczyk, K., Schmid, C.: An affine invariant interest point detector. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 128–142. Springer, Heidelberg (2002)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors (2004), http://www.robots.ox.ac.uk/~vgg/research/affine/
Obdrzalek, S., Matas, J.: Object recognition using local affine frames on distinguished regions. In: Proc. British Machine Vision Conference, pp. 113–122 (2002)
Quinlan, J.R.: C4.5 Programs for Machine Learning. Morgan Kaufmann, San Mateo (1993)
Vidal-Naquet, M., Ullman, S.: Object recognition with informative features and linear classication. In: Proc. International Conference on Computer Vision, ICCV 2003, Nice, France, pp. 281–288 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fritz, G., Seifert, C., Kumar, M., Paletta, L. (2005). Building Detection from Mobile Imagery Using Informative SIFT Descriptors. In: Kalviainen, H., Parkkinen, J., Kaarna, A. (eds) Image Analysis. SCIA 2005. Lecture Notes in Computer Science, vol 3540. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11499145_64
Download citation
DOI: https://doi.org/10.1007/11499145_64
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26320-3
Online ISBN: 978-3-540-31566-7
eBook Packages: Computer ScienceComputer Science (R0)