MutualCascade Method for Pedestrian Detection
An effective and efficient feature selection method based on Gentle Adaboost (GAB) cascade and the Four Direction Feature (FDF), namely, MutualCascade, is proposed in this paper, which can be applied to the pedestrian detection problem in a single image. MutualCascade improves the classic method of cascade to remove irrelevant and redundant features. The mutual correlation coefficient is utilized as a criterion to determine whether a feature should be chosen or not. Experimental results show that the MutualCascade method is more efficient and effective than Voila and Jones’ cascade and some other Adaboost-based method, and is comparable with HOG-based methods. It also demonstrates a higher performance compared with the state-of-the-art methods.
KeywordsFDF GAB MutualCascade Pedestrian Detection Feature Selection
Unable to display preview. Download preview PDF.
- 1.Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian Detection: an Evaluation of the State of the Art. Submission to IEEE Transactions on Pattern Analysis and Machine Intelligence (2011)Google Scholar
- 3.Soga, M., Hiratsuka, S.: Pedestrian Detection for a Near Infrared Imaging System. In: Proc. the 11th International IEEE Conference on Intelligent Transportation Systems, pp. 12–15 (2008)Google Scholar
- 8.Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 886–893 (2005)Google Scholar
- 9.Zhu, Q., Avidan, S., Yeh, M.C., Cheng, K.T.: Fast Human Detection using a Cascade of Histograms of Oriented Gradients. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1491–1498 (2006)Google Scholar
- 10.Tuzel, O., Porikli, F., Meer, P.: Human Detection via Classification on Riemannian Riemannian Manifolds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)Google Scholar