Abstract
Crowd size estimation is a challenging problem, especially when the crowd is spread over a significant geographical area. It has applications in monitoring of rallies and demonstrations and in calculating the assistance requirements in humanitarian disasters. Therefore, accomplishing a crowd surveillance system for large crowds constitutes a significant issue. UAV-based techniques are an appealing choice for crowd estimation over a large region, but they present a variety of interesting challenges, such as integrating per-frame estimates through a video without counting individuals twice. Large quantities of annotated training data are required to design, train, and test such a system. In this paper, we have first reviewed several crowd estimation techniques, existing crowd simulators and data sets available for crowd analysis. Later, we have described a simulation system to provide such data, avoiding the need for tedious and error-prone manual annotation. Then, we have evaluated synthetic video from the simulator using various existing single-frame crowd estimation techniques. Our findings show that the simulated data can be used to train and test crowd estimation, thereby providing a suitable platform to develop such techniques. We also propose an automated UAV-based 3D crowd estimation system that can be used for approximately static or slow-moving crowds, such as public events, political rallies, and natural or man-made disasters. We evaluate the results by applying our new framework to a variety of scenarios with varying crowd sizes. The proposed system gives promising results using widely accepted metrics including MAE, RMSE, Precision, Recall, and F1 score to validate the results.
Highlights
Crowd estimation refers to the practice of calculating the total number of people present in a crowd
Blob detection aimed to detect regions, either in a digital image or synthetic image. They were tested on the pre-existing state-of-the-art methods known as: From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting (S-DCNet) [42], Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection (LSC-convolution neural network (CNN)) [92], CNN-based Cascaded Multitask Learning of High-level Prior and Density
The estimated count of our data set against the ground truth was promising and presented in the form of mean absolute error (MAE) and root mean square error (RMSE)
Summary
Crowd estimation refers to the practice of calculating the total number of people present in a crowd. Manual estimation of a large crowd is not possible and may be very expensive and time-consuming. It has prompted scientists and researchers from various disciplines across the globe to develop automated crowd estimation systems that calculate the number of people in a large crowd. The introduction of deep learning methods, coupled with easy availability of powerful GPU based systems, has provided a step change in computer vision algorithms across a range of problem domains, starting with classification, but it has quickly moved on to other areas such as crowd estimation
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
