Symmetry and Asymmetry Features for Human Detection

Edge is a very important type of feature for human detection and Histogram of Oriented Gradient (HOG) is the most popular method to encode edge information since proposed. Because HOG detects edges based on intensity gradients, it is not invariant with respect to image illumination. In this paper, we propose three new types of features based on local phase: Local Phase based symmetry (LPS), Local Phase based Asymmetry (LPA), and Histogram of Oriented Asymmetry (HOA) for human detection. The LPA and HOA are similar with gradient magnitude and HOG features, but from different perspective. The key idea is the intensity around an edge point in an image is always asymmetry. Thus we can detect edges by measuring the asymmetry of the local structure at every point in the image. This is achieved by analyzing the phase of its constituent frequency components. This asymmetry measurement is invariant with respect to image contrast. After the asymmetry is computed, this value could be distributed to different orientation bins according to gradient orientation. We also measure symmetry around each point which yields LPS. This is useful to detect torso and limbs. These local phase induced features are combined with the classical Aggregated Channel Features (ACF) and are fed into the boosted decision tree (BDT) framework. Experiment shows that the proposed features are complementary to the ACF features and will increase the detection accuracy.