90 likes | 591 Views
FPGA Based Pedestrian D etection using Histogram of Oriented Gradients (HOG). Pedestrian Detection algorithm will be implemented using HOG. The purpose of the project is to have robust pedestrian detector using parallel computation with FPGA. Koray Ozcan.
E N D
FPGA Based Pedestrian Detectionusing Histogram of Oriented Gradients(HOG) Pedestrian Detection algorithm will be implemented using HOG. The purpose of the project is to have robust pedestrian detector using parallel computation with FPGA. Koray Ozcan
FPGA Based Pedestrian detection using Histogram of Oriented Gradients(HOG) Goals HOG provide more accurate results [1]. Array of Covariance Features is faster for human detection [2]. The main goal is to have accurate and fast human detector with FPGAs.
FPGA Based Pedestrian detection using Histogram of Oriented Gradients(HOG) Figure 1. Object model for the algorithm [2]
FPGA Based Pedestrian detection using Histogram of Oriented Gradients(HOG) • Implementation details: - [-1 0 1] gradient filter with no smoothing • Linear gradient voting 9 orientation bins (0º-180º) • 16x16 pixel blocks of four 8x8 pixel cells • 64x128 detection window • Linear SVM Classifier
FPGA Based Pedestrian detection using Histogram of Oriented Gradients(HOG) Matlab Implementation:
FPGA Based Pedestrian detection using Histogram of Oriented Gradients(HOG)
FPGA Based Pedestrian detection using Histogram of Oriented Gradients(HOG) Future work: - FPGA Implementation using VHDL • Implementation of Linear SVM(Support Vector Machine) for training and classifying • Construction of object model
References [1] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in Proc. CVPR, vol. 1. IEEE, 2005, pp. 886-893. [2] S. Martelli, D. Tosato, M. Cristani, V. Murino, “FPGA-Based Pedestrian Detection Using Array of Covariance Features,” In Proceedings of ACM/IEEE International Conference on Distributed Smart Cameras, Belgium, August 2011 [3] Digital image. INRIA Person Dataset. Web. 13 Oct. 2011.