A comprehensive study towards high-level approaches for weapon detection using classical machine learning and deep learning methods
作者：
Highlights：
• This study focuses the performance of existing automatic weapon detection systems.
• A complete taxonomy and evaluation of each weapon detection technique is presented.
• Weapon detection using classical machine learning and deep learning are explained.
• We have thoroughly examined and discussed the various publicly available datasets.
• The comparison of weapon detection methods are given with advantages and flaws.
摘要
•This study focuses the performance of existing automatic weapon detection systems.•A complete taxonomy and evaluation of each weapon detection technique is presented.•Weapon detection using classical machine learning and deep learning are explained.•We have thoroughly examined and discussed the various publicly available datasets.•The comparison of weapon detection methods are given with advantages and flaws.
论文关键词：Weapon detection,Deep learning,Machine learning,Computer vision,Security and surveillance
论文评审过程：Received 5 March 2022, Revised 2 August 2022, Accepted 24 August 2022, Available online 31 August 2022, Version of Record 10 September 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.118698
