Video analytics for connection discovery and user behavior monitoring | |
| Author | Rajak, Amir |
| Call Number | AIT Thesis no.IM-19-04 |
| Subject(s) | Video analytics Neural Networks Pattern recognition systems Electronic data processing--Security measures |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Information Management, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Thesis ; no. IM-19-04 |
| Abstract | Video analysis in retail business holds a lot of promise not only from a security perspective but also from the perspective of increasing the business revenue. Small businesses such as diners which often find it hard to compete with big enterprises such as fine dining restaurants, may utilize their existing surveillance video systems to track behavior of customers and make a more personalized offer to them. This may increase chances of a closed sale thereby increasing the revenue. However, identifying customers, tracking them and recognizing their behavior from video is a challenging task. In this study I apply state-of-the-art computer vision and deep learning techniques to discover groups of people at a shop using video analytics. I use real world heuristics such as, friends or people belonging to a group tend to stay closer to each other, and people who belong to same group often look at each other. |
| Year | 2019 |
| Corresponding Series Added Entry | Asian Institute of Technology. Thesis ; no. IM-19-04 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Information Management (IM) |
| Chairperson(s) | Matthew N. Dailey; |
| Examination Committee(s) | Mongkol Ekpanyapong;Guha, Sumanta; |
| Scholarship Donor(s) | His Majesty the King’s Scholarship (Thailand); |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2019 |