Welcome to the Bahria University DSpace digital repository. DSpace is a digital service that collects, preserves, and distributes digital material. Repositories are important tools for preserving an organization's legacy; they facilitate digital preservation and scholarly communication.
dc.contributor.author | Javeria Zafar, 01-235191-100 | |
dc.contributor.author | Arooba Malik, 01-235191-005 | |
dc.date.accessioned | 2023-03-06T05:46:01Z | |
dc.date.available | 2023-03-06T05:46:01Z | |
dc.date.issued | 2023 | |
dc.identifier.uri | http://hdl.handle.net/123456789/15071 | |
dc.description | Supervised by Ms. Mahwish Pervaiz | en_US |
dc.description.abstract | Abnormal event detection is one of the foremost important task in analysis applications. because the traditional and abnormal events have some similarities, a lot of discriminating ways or motion data ought to be explored. quick abnormal event detection meets the growing demand to methodology a large style of security videos. For that purpose we have proposed a model that used for event detection. System detect the event whether it’s normal or abnormal on basis of movement and velocity. For human detection we use HOG descriptor. For classification we used five different classifiers: decision tree, naïve Bayes, bagging, linear SVC and random forest. For evaluating the performance of our model we have a tendency to used 2 datasets: Avenue and Web dataset. Results shows that our model offers sensible accuracy and shows enhancement | en_US |
dc.language.iso | en | en_US |
dc.publisher | Computer Sciences | en_US |
dc.relation.ispartofseries | BS (IT);P-01969 | |
dc.subject | Security Videos | en_US |
dc.subject | Web Dataset | en_US |
dc.title | Abnormal Event Detection | en_US |
dc.type | Project Reports | en_US |