DSpace Repository

Particle Filtering for people tracking and heat mapping in surveillance video

Show simple item record

dc.contributor.advisor Dailey, Matthew
dc.contributor.author Jayet-laraffe, Alexandre
dc.contributor.other Sumanta, Guha
dc.contributor.other Mongkol, Ekpanyapong
dc.date.accessioned 2017-04-28T08:21:32Z
dc.date.available 2017-04-28T08:21:32Z
dc.date.issued 2017-05
dc.identifier.uri http://www.cs.ait.ac.th/xmlui/handle/123456789/849
dc.description 51p en_US
dc.description.abstract Surveillance and security are two main notions in public debates all around the world. Due to both terrorist attacks and crime, people want more surveillance but want it to be less intrusive. That is why video surveillance is currently a key technology. However, monitoring everyone is impossible, not only because of hardware costs, but also because of human resources. Automating video surveillance could be the best way to improve the power and the efficiency of surveillance. Particle filtering is one of the most powerful ways to track objects in video. I define and explore the possibility of adapting particle filtering to the video surveillance problem. However, I will go further by tackle the issue of the use of the Histogram of Oriented Gradi- ents (HOG) as an appearance model for the particle filtering. This study deals with the huge possibilities offered by the HOG but also with the problem created by this use, especially the computational resources needed. That why I will develop my own methodology to compute multiple HOG in the particle filtering context. This method is based on a pre-multiscale- computation of the HOG. And finally all this method will be combined not only for a monitoring purpose, but espe- cially for an economic goal, which is the building of statistic about the customers. That is why the last step of this study will be the 3D computation of the location of the customers to create a heat map of the shop. en_US
dc.description.sponsorship Télécom SudParis en_US
dc.publisher AIT en_US
dc.relation.ispartofseries Jayet-laraffe;
dc.relation.ispartofseries Jayet-laraffe;
dc.subject Particle filtering en_US
dc.subject Histogram of Oriented Gradients en_US
dc.subject HOG en_US
dc.subject Heat Map en_US
dc.subject Color Histograms en_US
dc.subject Tracking en_US
dc.subject Detection en_US
dc.subject Face detection en_US
dc.subject HOG precomputation en_US
dc.subject Multi scale HOG en_US
dc.title Particle Filtering for people tracking and heat mapping in surveillance video en_US
dc.type Thesis en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account