Elbishlawi Sherif, Abdelpakey Mohamed H, Eltantawy Agwad, Shehata Mohamed S, Mohamed Mostafa M
The University of British Columbia, 3333 University Way, Kelowna, BC V1V 1V7, Canada.
Memorial University of Newfoundland, St. John's, NL A1C 5S7, Canada.
J Imaging. 2020 Sep 11;6(9):95. doi: 10.3390/jimaging6090095.
Recently, our world witnessed major events that attracted a lot of attention towards the importance of automatic crowd scene analysis. For example, the COVID-19 breakout and public events require an automatic system to manage, count, secure, and track a crowd that shares the same area. However, analyzing crowd scenes is very challenging due to heavy occlusion, complex behaviors, and posture changes. This paper surveys deep learning-based methods for analyzing crowded scenes. The reviewed methods are categorized as (1) crowd counting and (2) crowd actions recognition. Moreover, crowd scene datasets are surveyed. In additional to the above surveys, this paper proposes an evaluation metric for crowd scene analysis methods. This metric estimates the difference between calculated crowed count and actual count in crowd scene videos.
最近，我们的世界见证了一些重大事件，这些事件吸引了人们对自动人群场景分析重要性的高度关注。例如，新冠疫情的爆发以及公共活动都需要一个自动系统来管理、统计、保障安全并追踪处于同一区域的人群。然而，由于严重的遮挡、复杂的行为以及姿势变化，分析人群场景极具挑战性。本文对基于深度学习的拥挤场景分析方法进行了综述。所综述的方法分为两类：（1）人群计数和（2）人群行为识别。此外，还对人群场景数据集进行了调研。除上述综述外，本文还提出了一种用于人群场景分析方法的评估指标。该指标估计人群场景视频中计算出的人群数量与实际数量之间的差异。
