Bundling Multislit-HOG Features of Near Infrared Images for Pedestrian Detection

In this paper we present a novel scheme where image features are bundled into local groups. Specifically, features of Near Infrared (NIR) images extracted by using Histogram of Oriented Gradients (HOG) descriptor and those by our multislit method are bundled into a single descriptor. The method involves first localizing the spatial layout of body parts (head, torso, and legs) in individual frames using multislit structures, and associating these through a series of extracting HOG features. A bundled feature vector describing various types of poses is then constructed and used for detecting the pedestrians. Experiments with a database of NIR images show that our scheme achieves a substantial improvement in average precision over the baseline conventional HOG approach. Detection and recognition performance is less computationally expensive than existing approaches.