Hybrid Feature-Assisted Neural Model for Crowd Behavior Analysis

Abstract

The exponential rise in technology and allied applications has always revitalized academia industries to achieve more efficient and robust solution to meet contemporary demands. Surveillance systems have always been the dominant area which has grabbed the attention of the scientific community to enable real-time events or target's characterization to make timely decision process. Crowd behavior analysis and classification is one of the most sought, though complex system to meet at hand surveillance purposes. However, unlike pedestrian movement detection methods, crowd analysis and behavioral characterization require robust feature learning and classification. With this motive, in this paper, a highly robust model is developed by applying hybrid deep features containing statistical features of the gray-level co-occurrence matrix (GLCM) and transferable deep learning AlexNet high-dimensional features. In addition, to perform multi-class classification multifeed forward neural network model (MFNN) is used. Here, the inclusion of hybrid features of GLCM and AlexNet provides deep spatio-temporal feature information which helps in making optimal classification decision. On the other hand, the use of MFNN algorithm enables optimal multi-class classification. Thus, the combined model with hybrid deep features and MFNN achieves crowd behavior classification with 91.35% accuracy, 89.92% precision, 88.34% recall and F-measure of 89.12%. KeywordsCrowd behavior analysis and classification • Hybrid deep features • GLCM • AlexNet • Fully connected layer (FC) • Deep learning • Multi-feed forward neural network (MFNN) • F-measure This article is part of the topical collection "Data Science and Communication" guest-edited by Kamesh Namudri, Naveen Chilamkurti, Sushma S. J. and S. Padmashree.

Acoustic Signals Based Crowd Analysis and Classification Model

“…It shows that the amalgamation of MFCC with other acoustics like GTCC and variants, pitch, HNR and other spectrum cues have helped our proposed model yielding superior and more reliable crowd analysis and classification solution. The accuracy of the proposed work is also slightly more than that of our previous research work [28] which was 91.35%, but less than another work [29] which was 96.15%.…”

“…The relative performance in terms of accuracy for the different at-hand solutions as well as our proposed model is given in Figure 3 and Table 4. 80.6% [20] 85.53% [21] 85.43% [22] 82.3% [23] 81.3% [24] 81.5% [25] 96.00% [28] 91.35% [29] 96.15% Proposed audio model 92.67%…”

Recurrence Quantification Analysis of Crowd Sound Dynamics

“…The emergent dynamics of crowd behavior have been fruitfully modeled according to biological phenomena such as swarm behavior (Kok, Lim, & Chan, 2016). Classification of emergent crowd dynamics, often using computer vision technology, has typically relied on analysis of video data for features, such as crowd density estimation, motion detection, and movement/behavior tracking of individual signals or group behavior (Kok et al., 2016; Swathi, Shivakumar, & Mohana, 2017). However, it is not always feasible to obtain high‐quality image, video, or speech data of a crowd in action, nor is it always feasible to obtain signals measured from each individual in an interacting crowd.…”