A classification-regression deep learning model for people counting

Xu, Bolei; Zou, Wenbin; Garibaldi, Jonathan; Qiu, Guoping

Abstract

In this paper, we construct a multi-task deep learning model to simultaneously predict people number and the level of crowd density. Motivated by the success of applying " ambiguous labelling " to age estimation problem, we also manage to employ this strategy to the people counting problem. We show that it is a reasonable strategy since people counting problem is similar to the age estimation problem. Also, by applying " ambiguous labelling " , we are able to augment the size of training dataset, which is a desirable property when applying to deep learning model. In a series of experiment, we show that the " ambiguous labelling " strategy can not only improve the performance of deep learning but also enhance the prediction ability of traditional computer vision methods such as Random Projection Forest with hand-crafted features.

Citation

Xu, B., Zou, W., Garibaldi, J., & Qiu, G. (2018). A classification-regression deep learning model for people counting. In K. Arai, S. Kapoor, & R. Bhatia (Eds.), Intelligent Systems and Applications Proceedings of the 2018 Intelligent Systems Conference (IntelliSys) Volume 1. , (136-149). https://doi.org/10.1007/978-3-030-01054-6_9

• Conference Name: Intelligent Systems Conference 2018 (IntelliSys 2018)
• Start Date: Sep 6, 2018
• End Date: Sep 7, 2018
• Acceptance Date: Sep 1, 2018
• Online Publication Date: Sep 6, 2018
• Publication Date: Sep 6, 2018
• Deposit Date: Dec 13, 2018
• Publicly Available Date: Sep 7, 2019
• Journal: Intelligent Systems Conference
• Publisher: Springer Publishing Company
• Pages: 136-149
• Series Title: Advances in Intelligent Systems and Computing
• Series Number: 868
• Book Title: Intelligent Systems and Applications Proceedings of the 2018 Intelligent Systems Conference (IntelliSys) Volume 1
• Chapter Number: 9
• ISBN: 978-3-030-01053-9
• DOI: https://doi.org/10.1007/978-3-030-01054-6_9
• Keywords: People counting; Deep learning; Ambiguous la- belling
• Public URL: https://nottingham-repository.worktribe.com/output/1412867
• Publisher URL: https://link.springer.com/chapter/10.1007/978-3-030-01054-6_9