Crowd Density Level Estimation and Anomaly Detection Using Multicolumn Multistage Bilinear Convolution Attention Network (MCMS-BCNN-Attention)

Abstract

The detection of crowd density levels and anomalies is a hot topic in video surveillance. Especially in human-centric action and activity-based movements. In some respects, the density level variation is considered an anomaly in the event. Crowd behaviour identification relies on a computer-vision-based approach and basically deals with spatial information of foreground video information. In this work, we focused on a deep-learning-based attention-oriented classification system for identifying several basic movements in public places, especially, human flock movement, sudden motion changes and panic events in several indoor and outdoor places. The important spatial features were extracted from a bilinear CNN and a multicolumn multistage CNN with preprocessed morphological video frames from videos. Finally, the abnormal and crowd density estimation was distinguished by using an attention feature combined with a multilayer CNN feature by modifying the fully connected layer for several categories (binary and multiclass). We validate the proposed method on several video surveillance datasets including PETS2009, UMN and UCSD. The proposed method achieved an accuracy of 98.62, 98.95, 96.97, 99.10 and 98.38 on the UCSD Ped1, UCSD Ped2, PETS2009, UMN Plaza1 and UMN Plaza2 datasets, respectively, with the different pretrained models. We compared the performance between recent modern approaches and the proposed method (MCMS-BCNN-Attention) and achieved the highest accuracy. The anomaly detection performance on the UMN and PETS2009 datasets was compared with that of a state-of-the-art method and achieved the best AUC results as 0.9953 and 1.00 for both scenarios, respectively, with a binary classification.

Abnormal Crowd Behaviour Detection in Surveillance Videos Using Spatiotemporal Inter-Fused Autoencoder

“…This section provides a discussion about the proposed spatiotemporal inter-fused autoencoder and compares those results with existing methods such as LRCCDL [14], hybrid CNN and RF classifiers [16], MCMS-BCN Attention+densenet121/Efficientnetv2 [17], PGD and enhanced entropy classifier [21], and attention mechanism [22] in comparative analysis 4.3.…”

“…E. M. C. L. Ekanayake [17] presented a novel MCMS-BCNN attention network with a densenet121/ Efficientv2 architecture for identifying a variety of basic movements in public areas, particularly rapid motion changes, human flock movement, and panic occurrences in a variety of indoor and outdoor environments. With preprocessed morphological video frames, the significant spatial characteristics were retrieved from a bilinear and a multicolumn multistage CNN.…”

“…Table 4. shows the comparison of the proposed method with the existing methods such as Hybrid CNN and RF classifiers [16], MCMS-BCN Attention+densenet121/Efficientnetv2 [17], and PGD and enhanced entropy classifier [21] on UMN dataset. Table 5.…”

Knowledge Development Trajectories of Intelligent Video Surveillance Domain: An Academic Study Based on Citation and Main Path Analysis

“…A deep GMM is an expandable deep generative model, and Feng et al stacked multiple GMMs together so that their method could use relatively few parameters to achieve competitive performance [31] 2023), for crowd anomaly detection, IVS is essential. Articles related to the detection of human behavior include methods that detect abnormal crowd behaviors [38,39].…”