Attention guided neural network models for occluded pedestrian detection

Abstract

Occluded pedestrian detection has been a research difficulty in computer vision for a long time. The conventional approach to solve this problem is to learn partial detectors, which can be properly integrated for occlusion handling. However, the efficiency of this type of methods is limited in practical applications since the partial detectors can not cover all occlusion patterns. In this paper, an attention guided neural network model (AGNN) is proposed for the occlusion handling of pedestrian detections, which is inspired by the approaches of sentiment classification. Firstly, a fixed-size window slides on a still image without overlapping to generate a set of sub-images. Secondly, a convolutional neural network is employed to extract the high-level features from resulting sub-images. Then, the attention network performs local feature weighting, from which the features representing the body parts of pedestrians are selected. Finally, the feature sequences are classified by recurrent neural network in proper order based on the weighted results. In addition, we explore different mechanisms of attention guidance on the detector for the detections. Compared with the state-of-the-art methods on two standard pedestrian datasets, experimental results demonstrate the comparable performance of our approach in terms of miss rates.