cvpr cvpr2013 cvpr2013-383 cvpr2013-383-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Rodrigo Benenson, Markus Mathias, Tinne Tuytelaars, Luc Van_Gool
Abstract: The current state of the art solutions for object detection describe each class by a set of models trained on discovered sub-classes (so called “components ”), with each model itself composed of collections of interrelated parts (deformable models). These detectors build upon the now classic Histogram of Oriented Gradients+linear SVM combo. In this paper we revisit some of the core assumptions in HOG+SVM and show that by properly designing the feature pooling, feature selection, preprocessing, and training methods, it is possible to reach top quality, at least for pedestrian detections, using a single rigid component. We provide experiments for a large design space, that give insights into the design of classifiers, as well as relevant information for practitioners. Our best detector is fully feed-forward, has a single unified architecture, uses only histograms of oriented gradients and colour information in monocular static images, and improves over 23 other methods on the INRIA, ETHand Caltech-USA datasets, reducing the average miss-rate over HOG+SVM by more than 30%.
[1] K. Ali, F. Fleuret, D. Hasler, and P. Fua. A real-time deformable detector. PAMI, 2011. 2, 5
[2] R. Benenson, M. Mathias, R. Timofte, and L. Van Gool. Pedestrian detection at 100 frames per second. In CVPR, 2012. 2, 3, 5, 7
[3] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In CVPR, 2005. 1, 2, 3, 5
[4] P. Dollár, R. Appel, and W. Kienzle. Crosstalk cascades for frame-rate pedestrian detection. In ECCV,
[5]
[6]
[7]
[8]
[9]
[10]
[11]
[12] 2012. 2, 7 P. Dollár, Z. Tu, P. Perona, and S. Belongie. Integral channel features. In BMVC, 2009. 1, 2, 3, 5, 6 P. Dollár, C. Wojek, B. Schiele, and P. Perona. Pedestrian detection: An evaluation of the state of the art. TPAMI, 2011. 1, 2, 3, 6 P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained part-based models. PAMI, 2010. 1, 2 K. Jarrett, K. Kavukcuoglu, M. Ranzato, and Y. LeCun. What is the best multi-stage architecture for object recognition? In ICCV, 2009. 2 Y. Jia, C. Huang, and T. Darrell. Beyond spatial pyramids: Receptive field learning for pooled image features. In CVPR, 2012. 2, 4 W. Nam, B. Han, and J. Han. Improving object localization using macrofeature layout selection. In ICCV, Visual Surveillance Workshop, 2011. 2, 3, 4, 6 M. Ozuysal, M. Calonder, V. Lepetit, and P. Fua. Fast keypoint recognition using random ferns. PAMI, 2010. 6 D. Park, D. Ramanan, and C. Fowlkes. Multiresolution models for object detection. In ECCV, 2010. 2, 7
[13] A. Rizzi, C. Gatta, and D. Marini. A new algorithm for unsupervised global and local color correction. Pattern Recognition Letters, 2003. 5
[14] P. Sermanet, K. Kavukcuoglu, and Y. LeCun. Traffic
[15]
[16]
[17]
[18] signs and pedestrians vision with multi-scale convolutional networks. In Snowbird Machine Learning Workshop, 2011. 2, 3, 8 P. Shivaswamy and T. Jebara. Variance penalizing AdaBoost. In NIPS, 2011. 6 P. Viola and M. Jones. Robust real-time face detection. In IJCV, 2004. 2, 3 C. Wojek, S. Walk, and B. Schiele. Multi-cue onboard pedestrian detection. In CVPR, 2009. 2 X. Zhu, C. Vondrick, D. Ramanan, and C. Fowlkes. Do we need more training data or better models for object detection? In BMVC, 2012. 6 333666777311