In recent years, pedestrian detection (PD) plays a vital role in a variety of applications such as security cameras, automotive control and so forth. These applications require two essential features, i.e. high speed performance and high accuracy. Firstly, the accuracy is determined by how the image features are described. The image feature description must be robust against occlusion, rotation, and the change in object shapes and illumination conditions. A number of feature descriptors have been proposed. Previously histogram of oriented gradients(HOG) features were extensively used along with support vector machine (SVM) classifier for PD. HOG features and SVM classifier can achieve good performance for PD, but they are time consuming. To achieve high detection speed with good detection performance, a Two-step framework method was proposed by Zhen Li which was the fusion of Haar-like and HOG features to get better performance. Edgelet features were used for classification and detection. But, the detection rate was poor and computation speed was less. In order to alleviate these limitations, we propose here a new methodology for improving the detection rate and speed. The performance and accuracy of the detection can be improved by the combination of Haar-like and Triangular features for FBD and Edgelet and Shapelet for HSD. We expect an average 95% detection rate and 60% faster speed for the proposed method

1. P. Viola, M. Jones and D. Snow, 2003. Detecting Pedestrians Using Pattern of Motion and Appearance, The 9th ICCV, France, 734-741.
2. Takuya Kobayashi, Akinori Hidaka, Takio Kurita, 2007. Selection of Histograms of Oriented Gradients Features for Pedestrian Detection, Neural Information Processing: 14th International Conference. Japan, 598-607.
3. B. Wu and R. Nevatia, 2005. Detection of multiple, Partially occluded humans in a single image by bayesian combination of edgelet part detectors. IEEE International Conference on Computer Vision , China, 90-97.
4. Supriya Rao,N. C. Pramod, Chaitanya Krishna Paturu, 2008. People Detection in Image and Video Data.Proceeding of the 1st ACM workshop on Vision networks for behavior analysis, Canada, 85-92
5. J. Janta P. Kumsawat, K. Attakitmaongkol and A. Srikaew, 2007. A Pedestrian Detection System Using Applied Log-Gabor Filters. Proceedings of the 7th WSEAS International Conf. on Signal, Speech & Image Processing, China, 55-60
6. Navneet Dalal and Bill Triggs, 2005. Histograms of Oriented Gradients for Human Detection. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. USA, Vol 1, 886-893.
7. MIT Pedestrian Dataset http://cbcl.mit.edu/cbcl/softwaredatasets/PedestrianData.html
8. INRIA Person Dataset http://pascal.inrialpes.fr/data/human/

HOG Haar-like Triangular Edgelet Shapelet Adaboost Classifier and Video Processor