Advances in Convolution Neural Networks Based Crowd Counting and Density Estimation

Abstract

Automatically estimating the number of people in unconstrained scenes is a crucial yet challenging task in different real-world applications, including video surveillance, public safety, urban planning, and traffic monitoring. In addition, methods developed to estimate the number of people can be adapted and applied to related tasks in various fields, such as plant counting, vehicle counting, and cell microscopy. Many challenges and problems face crowd counting, including cluttered scenes, extreme occlusions, scale variation, and changes in camera perspective. Therefore, in the past few years, tremendous research efforts have been devoted to crowd counting, and numerous excellent techniques have been proposed. The significant progress in crowd counting methods in recent years is mostly attributed to advances in deep convolution neural networks (CNNs) as well as to public crowd counting datasets. In this work, we review the papers that have been published in the last decade and provide a comprehensive survey of the recent CNNs based crowd counting techniques. We briefly review detection-based, regression-based, and traditional density estimation based approaches. Then, we delve into detail regarding the deep learning based density estimation approaches and recently published datasets. In addition, we discuss the potential applications of crowd counting and in particular its applications using unmanned aerial vehicle (UAV) images.

Visual crowd analysis: Open research problems

“…Several studies have been conducted in the past, which typically focus on individual areas of crowd analysis. For example, Sindagi and Patel (2018), Cenggoro (2019), Ilyas, Shahzad, and Kim (2020), Gao et al (2020), Luo, Lu, and Zhang (2020), Gouiaa, Akhloufi, and Shahbazi (2021), Fan et al (2022), and Khan, Menouar, and Hamila (2023c) cover crowd counting research and mainly discuss the advancements in model architectures, benchmarking, and datasets. Hu et al (2004b), Luca et al (2020), andKumar (2021) focus on crowd motion analysis, discussing crowd motion predictions, flow classification, and behavior analysis using motion patterns.…”

“…For example, Sindagi and Patel (2018), Cenggoro (2019), Ilyas, Shahzad, and Kim (2020), Gao et al. (2020), Luo, Lu, and Zhang (2020), Gouiaa, Akhloufi, and Shahbazi (2021), Fan et al. (2022), and Khan, Menouar, and Hamila (2023c) cover crowd counting research and mainly discuss the advancements in model architectures, benchmarking, and datasets.…”

Automatic rape flower cluster counting method based on low-cost labelling and UAV-RGB images

“…Consequently, the UAV with RGB imaging characterized by high resolution and flexible acquisition is an effective way to count flower clusters. Deep learning methods for crop counting in RGB imaging have been presented in recent years [ 23 , 24 ]. Samiei et al [ 25 ] designed a deep learning CNN network to learn the cotyledon opening during plant seedling development.…”

An Extended Model for the UAVs-Assisted Multiperiodic Crowd Tracking Problem

“…In fact, this is a realistic assumption in some situations where the behavior of the crowds is known and can be predicted. To do that, there are many proposed methods in the literature that can be used to predict crowds characteristics and behavior based on machine learning techniques [56][57][58][59][60][61][62][63][64]. Tanks to this prediction, a CMA system can have a "clairvoyance" and therefore more strategic assignments of the UAVs that takes into account the future behaviors of crowds.…”