Download PDFOpen PDF in browser

Crowd Anomaly Detection In City Crime Video

EasyChair Preprint no. 5986

7 pagesDate: July 3, 2021


Anomaly analysis is of great interest to diverse fields, including data processing and machine learning, and plays a critical role during a wide selection of applications, like medical health, mastercard, fraud, and intrusion detection. Recently, a big number of anomaly detection methods with a spread of types are witnessed. This paper intends to supply a comprehensive overview of the prevailing work on anomaly detection, especially for the info with high dimensionalities and mixed types, where identifying anomalous patterns or behaviours may be a nontrivial work. Specifically, we first present recent advances in anomaly detection, discussing the pros and cons of the detection methods. Then we conduct extensive experiments on public datasets to guage several typical and popular anomaly detection methods. the aim of this paper is to supply a far better understanding of the state-of-the-art techniques of anomaly detection for practitioners. Finally, we conclude by providing some directions for future research.

 A framework and design that is suitable for anomaly detection in crowded videos is represented by three properties. Modeling of appearance and physical properties of such scene, Temporal abnormalities, Spatial abnormalities. The proposed model for normal crowd behavior is based upon the dynamic texture and outliers. The probability of event handling in temporal anomalies is very low as compared to spatial anomalies. We can handle these events using discriminant salience. Our consist of hundreds videos and five well-defined abnormality categories in which we experiment and evaluate

Keyphrases: anomaly detection, City scenes Video, video surveillance

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Kshitiz Gupta and Kunal Varshney},
  title = {Crowd Anomaly Detection In City Crime Video},
  howpublished = {EasyChair Preprint no. 5986},

  year = {EasyChair, 2021}}
Download PDFOpen PDF in browser