Combining Histograms of Oriented Gradients with Global Feature for Human Detection

In this work, we propose an algorithm of combining Histograms of Oriented Gradients(HOGs) with shape of head for human detection from a non-static camera. We use AdaBoost algorithm to learn local characteristics of human based on HOGs. Since local feature is easily affected by complex backgrounds and noise, the idea of this work is to incorporate the global feature for improving the detection accuracy. Here, we adopt the head contour as the global feature. The score for evaluating the existence of the head contour is through the Chamfer distance. Furthermore, the matching distributions of the head and non-head are modeled by Gaussian and Anova distributions, respectively. The combination of the human detector based on local features and head contour is achieved through the adjustment of the hyperplane of support vector machine. In the experiments, we exhibit that our proposed human detection method not only has higher detection rate but also lower false positive rate in comparison with the state-of-the-art human detector.