Crowd Abnormal Behaviour Detection Using Deep Learning

Sonkar, Riddhi; Rathod, Sadhana; Jadhav, Renuka; Patil, Deepali

doi:10.1051/itmconf/20203203040

Cited by 7 publications

(4 citation statements)

References 11 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One-class learner models include Gaussian Mixture Models [14], Support Vector Machines (SVM) [5], Replicator Neural Networks [11,12], Convolutional Neural Networks [13], and Bayesian models [17]. If the test sample deviates substantially from the norm during testing, it is then regarded as abnormal.…”

Section: Related Workmentioning

confidence: 99%

Real Time Crowd Analysis and Anomaly Detection

AMINA

Binu

2022

Preprint

View full text Add to dashboard Cite

Crowd analysis is gaining a lot of attention in both the technological and social aspects as the population expands. As certain crowdactivity cannot be assessed easily, These techniques differ dependingon the crowd. Strikes, protests, and other crowded events are commonin overpopulated cities. Parades and other public gatherings providea variety of security challenges. Security forces are frequently enlistedto keep an eye on these issues and ensuring the safety of those whoattend meetings. In these circumstances, ensuring the safety of thosewho attend meetings are challenging . Cutting-edge crowd control methods are necessary for an intelligent surveillance system. The goal of theproposed method is to find crowd analysis subfields, such as anomalydetection, that have not yet been well explored or that seem to beaddressed infrequently. Public data sets for indoor and outdoor useare used to evaluate the proposed system’s bespoke architecture. The Experimental findings demonstrate that the custom architecture performs better than the exixting Architectures.Our aim is to providerecent state-of-the-art algorithms to provide a novel strategy that canhelp with improved crowd surveillance and crowd activity analysis.

show abstract

Section: Related Workmentioning

confidence: 99%

Real Time Crowd Analysis and Anomaly Detection

AMINA

Binu

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…This improved convolution uses an aggregation channel feature model to perform picture monitoring and selects aberrant behaviors in the image with low-level features. Sonkar [5] compared the ViBe and CNN algorithms to identify anomalous behaviors in the photos. Due to their computing flexibility, statistical approaches are extensively utilized in video frame computation designs, and real-time abnormal event detection typically makes use of fast algorithms with minimum computational costs.…”

Section: B Anomaly Detection In Crowdmentioning

confidence: 99%

A Research Perceptive on Deep Learning Framework for Pedestrian Detection in a Crowd

Shaamili¹

2022

CIML

View full text Add to dashboard Cite

In populated cities, we often find crowded events like political meetings, religious festivals, music concerts, and events in shopping malls, which have more safety issues. Smart surveillance systems are used in big cities to keep crowds safe and make crowd security less complicated and more accurate. However, the surveillance systems proposed for a crowd are monitored by human agents, which are inefficient, error-prone, and overwhelming. Even with deep learning-based feature engineering in crowds, many variants of crowd analysis still lack attention and are technically unaddressed. Considering this scenario, the smart system requires the most advanced techniques to monitor the security of the crowd. Crowd analysis is commonly divided into crowd statics and behavior analysis. This paper explores more about crowd behaviour analysis, pedestrian and group detection which describes the movements that are noticed in the crowd image. Subsequently, the issues of the current methodology of pedestrian detection, datasets, and evaluation criteria are analyzed. Keyword : Crowd Analysis, Pedestrian and group detection, deep learning, Crowd IoT analysis, Human Activity Recognition.

show abstract

“…Sometimes people get robbed or violence breaks down at a crowded place, at that moment it gets difficult to find the culprit or to keep an eye on the culprit. For keeping track of people at crowded places deep learning model are used for crowd management and for keeping track on suspicious activity [6]. According to the search, most of the research on action recognition is done on the state-of-the-arts [7] [14] and human action recognition (HAR) which is further used for the prediction of activity.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning based Human Action Recognition

Pandey¹,

Chikhale²,

Verma³

et al. 2021

ITM Web Conf.

Self Cite

View full text Add to dashboard Cite

Human action recognition has become an important research area in the fields of computer vision, image processing, and human-machine or human-object interaction due to its large number of real time applications. Action recognition is the identification of different actions from video clips (an arrangement of 2D frames) where the action may be performed in the video. This is a general construction of image classification tasks to multiple frames and then collecting the predictions from each frame. Different approaches are proposed in literature to improve the accuracy in recognition. In this paper we proposed a deep learning based model for Recognition and the main focus is on the CNN model for image classification. The action videos are converted into frames and pre-processed before sending to our model for recognizing different actions accurately..

show abstract

Crowd Abnormal Behaviour Detection Using Deep Learning

Cited by 7 publications

References 11 publications

Real Time Crowd Analysis and Anomaly Detection

Real Time Crowd Analysis and Anomaly Detection

A Research Perceptive on Deep Learning Framework for Pedestrian Detection in a Crowd

Deep Learning based Human Action Recognition

Contact Info

Product

Resources

About