Pedestrian Attribute Recognition with Part-based CNN and Combined Feature Representations

Yiqiang Chen, Stefan Duffner, Andrei Stoian, Jean-Yves Dufour, Atilla Baskurt

2018

Abstract

In video surveillance, pedestrian attributes such as gender, clothing or hair types are useful cues to identify people. The main challenge in pedestrian attribute recognition is the large variation of visual appearance and location of attributes due to different poses and camera views. In this paper, we propose a neural network combining high-level learnt Convolutional Neural Network (CNN) features and low-level handcrafted features to address the problem of highly varying viewpoints. We first extract low-level robust Local Maximal Occurrence (LOMO) features and learn a body part-specific CNN to model attribute patterns related to different body parts. For small datasets which have few data, we propose a new learning strategy, where the CNN is pre-trained in a triplet structure on a person re-identification task and then fine-tuned on attribute recognition. Finally, we fuse the two feature representations to recognise pedestrian attributes. Our approach achieves state-of-the-art results on three public pedestrian attribute datasets.

Paper Citation

in Harvard Style

Chen Y., Duffner S., Stoian A., Dufour J. and Baskurt A. (2018). Pedestrian Attribute Recognition with Part-based CNN and Combined Feature Representations. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 114-122. DOI: 10.5220/0006622901140122

in Bibtex Style

@conference{visapp18,
author={Yiqiang Chen and Stefan Duffner and Andrei Stoian and Jean-Yves Dufour and Atilla Baskurt},
title={Pedestrian Attribute Recognition with Part-based CNN and Combined Feature Representations},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP},
year={2018},
pages={114-122},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006622901140122},
isbn={978-989-758-290-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP
TI - Pedestrian Attribute Recognition with Part-based CNN and Combined Feature Representations
SN - 978-989-758-290-5
AU - Chen Y.
AU - Duffner S.
AU - Stoian A.
AU - Dufour J.
AU - Baskurt A.
PY - 2018
SP - 114
EP - 122
DO - 10.5220/0006622901140122
PB - SciTePress