Exact Acceleration of Linear Object Detectors
Conference paper
Abstract
We describe a general and exact method to considerably speed up linear object detection systems operating in a sliding, multi-scale window fashion, such as the individual part detectors of part-based models. The main bottleneck of many of those systems is the computational cost of the convolutions between the multiple rescalings of the image to process, and the linear filters. We make use of properties of the Fourier transform and of clever implementation strategies to obtain a speedup factor proportional to the filters’ sizes. The gain in performance is demonstrated on the well known Pascal VOC benchmark, where we accelerate the speed of said convolutions by an order of magnitude.
Keywords
linear object detection part-based models Download
to read the full conference paper text
References
- 1.Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2007 (VOC 2007) (2007) Results, http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html
- 2.Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2011 (VOC 2011) (2011) Results, http://www.pascal-network.org/challenges/VOC/voc2011/workshop/index.html
- 3.Felzenszwalb, P., Huttenlocher, D.: Pictorial Structures for Object Recognition. International Journal of Computer Vision 61, 55–79 (2005)CrossRefGoogle Scholar
- 4.Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object Detection with Discriminatively Trained Part-Based Models. IEEE Transactions on Pattern Analysis and Machine Intelligence 32(9) (2010)Google Scholar
- 5.Felzenszwalb, P., Girshick, R., McAllester, D.: Discriminatively Trained Deformable Part Models, Release 4, http://people.cs.uchicago.edu/~pff/latent-release4/
- 6.Viola, P., Jones, M.: Robust Real-time Object Detection. International Journal of Computer Vision (2001)Google Scholar
- 7.Perko, R., Leonardis, A.: Context Driven Focus of Attention for Object Detection. In: Paletta, L., Rome, E. (eds.) WAPCV 2007. LNCS (LNAI), vol. 4840, pp. 216–233. Springer, Heidelberg (2007)CrossRefGoogle Scholar
- 8.Maji, S., Malik, J.: Object detection using a max-margin Hough transform. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1038–1045 (2009)Google Scholar
- 9.Lampert, C., Blaschko, M., Hofmann, T.: Beyond sliding windows: Object localization by efficient subwindow search. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008)Google Scholar
- 10.Felzenszwalb, P., Girshick, R., McAllester, D.: Cascade object detection with deformable part models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2241–2248 (2010)Google Scholar
- 11.Zhang, C., Viola, P.: Multiple-Instance Pruning For Learning Efficient Cascade Detectors. In: Advances in Neural Information Processing Systems (2007)Google Scholar
- 12.Cecotti, H., Graeser, A.: Convolutional Neural Network with embedded Fourier Transform for EEG classification. In: International Conference on Pattern Recognition, pp. 1–4 (2008)Google Scholar
- 13.Dollar, P., Belongie, S., Perona, P.: The Fastest Pedestrian Detector in the West. In: British Machine Vision Conference (2010)Google Scholar
- 14.Felzenszwalb, P., Huttenlocher, D.: Distance transforms of sampled functions. Technical report, Cornell Computing and Information Science (2004)Google Scholar
- 15.Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 886–893 (2005)Google Scholar
- 16.Frigo, M., Johnson, S.: The design and implementation of FFTW3. Proceedings of the IEEE 93(2), 216–231 (2005)CrossRefGoogle Scholar
- 17.Chazelle, B.: The Bottom-Left Bin-Packing Heuristic: An Efficient Implementation. IEEE Transactions on Computers, 697–707 (1983)Google Scholar
- 18.Guennebaud, G., Jacob, B.: Eigen v3, http://eigen.tuxfamily.org
Copyright information
© Springer-Verlag Berlin Heidelberg 2012