Citation

Junejo IN, Ahmed N. Heliyon 2020; 6(3): e03563.

Affiliation

University of Sharjah, United Arab Emirates.

Copyright

(Copyright © 2020, Elsevier Publishing)

DOI

10.1016/j.heliyon.2020.e03563

PMID

32195393

PMCID

PMC7078519

Abstract

Video surveillance applications have made great strides in making the world a safer place. Extracting visual attributes from a scene, such as the type of shoes, the type of clothing, carrying any object or not, or wearing any accessory etc., is a challenging problem and an efficient solution holds the key to a great number of applications. In this paper, we present a multi-branch convolutional neural network that uses depthwise separable convolution (DSC) layers to solve the pedestrian attribute recognition problem. Researchers have proposed various solutions over the years making use of convolutional neural networks (CNN), however, we introduce DSC layers to the CNN for the problem of pedestrian attribute recognition. In addition, we make a novel use of the different color spaces and create a 3-branch CNN, denoted as 3bCNN, that is efficient, especially with smaller datasets. We experiment on two benchmark datasets and show results with improvement over the state of the art.

© 2020 The Authors.

Language: en

Keywords

Computer Vision; Computer science; Deep learning; Image processing; Pedestrian attribute recognition