Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry

TL;DR

This paper introduces novel non-neighboring features inspired by appearance constancy and shape symmetry to improve pedestrian detection, achieving state-of-the-art results with enhanced accuracy and efficiency without using CNNs.

Contribution

It proposes SIDF and SSF features based on inherent pedestrian attributes and combines them with neighboring features for superior detection performance.

Findings

Non-neighboring features reduce miss rate by 4.44%.

Achieves best detection performance on Caltech dataset.

Outperforms existing methods without CNNs.

Abstract

The discrimination and simplicity of features are very important for effective and efficient pedestrian detection. However, most state-of-the-art methods are unable to achieve good tradeoff between accuracy and efficiency. Inspired by some simple inherent attributes of pedestrians (i.e., appearance constancy and shape symmetry), we propose two new types of non-neighboring features (NNF): side-inner difference features (SIDF) and symmetrical similarity features (SSF). SIDF can characterize the difference between the background and pedestrian and the difference between the pedestrian contour and its inner part. SSF can capture the symmetrical similarity of pedestrian shape. However, it's difficult for neighboring features to have such above characterization abilities. Finally, we propose to combine both non-neighboring and neighboring features for pedestrian detection. It's found that non-neighboring features can further decrease the average miss rate by 4.44%. Experimental results on INRIA and Caltech pedestrian datasets demonstrate the effectiveness and efficiency of the proposed method. Compared to the state-of-the-art methods without using CNN, our method achieves the best detection performance on Caltech, outperforming the second best method (i.e., Checkboards) by 1.63%.