Smart City Gnosys
Smart city article details
| Title | Spatio-Temporal Motion Pattern Analysis For Anomaly Recognition In Crowded Sections Using Kernel Svm |
|---|---|
| ID_Doc | 52575 |
| Authors | Rathika S.; Minhas D.; Spoorthi B.; Kumar S.; Vigenesh M.; Garg P. |
| Year | 2024 |
| Published | 2024 IEEE 4th International Conference on ICT in Business Industry and Government, ICTBIG 2024 |
| DOI | http://dx.doi.org/10.1109/ICTBIG64922.2024.10911085 |
| Abstract | The advancement of information technology, the proliferation of monitoring networks, and the automated detection of anomalous behavior in surveillance video are all becoming more crucial for the purpose of public safety and smart city development. Context modeling is the foundation upon which the new methods for recognizing moving objects are built. Consequently, these systems are vulnerable to noise and background movement. It is a challenging endeavor to keep track of individuals in crowded scenarios because of the variations in movement and appearance that are brought about by the vast number of people present in the picture. An efficient Kernel Support Vector Machine is constructed for the purpose of anomaly identification in congested settings by making use of spatio-temporal movement pattern models. This is done to find solutions to these challenges. At the outset, the movie is divided into frames by making use of the threshold value. Protracted Kalman Filters are used to segment the motions of the objects to enhance the accuracy of the categorization. The textural characteristics are used to determine which item is in the front and which is in the background. To track objects in an effective manner, enhanced vector quantization is used. To categorize the abnormalities, the Kernel Support Vector Machine is used. © 2024 IEEE. |
| Author Keywords | GLCM; ILVQ and Anomalies; Kernel support vector; LBPs |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
18358  | 0.89 | Dhingra L.; Geetha B.; Mishra A.; Savitha R.; Chavhan G.H.; Vigenesh M. | Deploying Hybrid Deep Learning Methods In Conjunction With One-Class Svm For Anomaly Detection In Crowded Spaces | 2024 IEEE 4th International Conference on ICT in Business Industry and Government, ICTBIG 2024 (2024) |
| 32034 | 0.875 | Jayasree S.; Singla A.; Renukajyothi S.; More P.D.; Jeevananthan P.; Gupta S. | Integrating Machine Learning And Swarm Intelligence For Enhanced Incongruity Recognition In Dense Crowds | IEEE International Conference on Recent Advances in Science and Engineering Technology, ICRASET 2024 (2024) |
| 9107 | 0.858 | Raja R.; Sharma P.C.; Mahmood M.R.; Saini D.K. | Analysis Of Anomaly Detection In Surveillance Video: Recent Trends And Future Vision | Multimedia Tools and Applications, 82, 8 (2023) |