A greener AI-Based crowd counting via efficient deep learning

作     者：A. Chrysler R. Gunarso T. Puteri T. W. Cenggoro 

作者机构：Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 

出 版 物：《AIP Conference Proceedings》 

年 卷 期：2023年第2594卷第1期

学科分类：07[理学] 0702[理学-物理学] 

摘      要：Crowd counting is one of the important AI implementations, which is defined as an AI model that can automatically count humans from CCTV footage. Similar to other implementations of Artificial Intelligence (AI), a crowd counting AI development tends to produce larger models over time. It is caused by the tendency of larger models to have better performance. This trend negatively impacts the environment because the development of larger AI models generates more CO2 that causes global warming. This study instead focuses on developing crowd counting AI that has a small size with competitive performance. Our proposed model achieves competitive performance compared to other state-of-the-art crowd counting models. Currently, our proposed model is also the 3rd best model in terms of performance-size tradeoff among all crowd counting AI with known model size.