[Bachelor Thesis] EyeTeck: A System To Search People In Surveillance Camera Network

In this thesis, we developed an application to identify persons in surveillance cameras, using video surveillance cameras from a building as input. The target is finding a person with information, such as a photo of a person's face or personal attribute information. We designed a framework that utilizes facial features and person identification information to find persons in CCTV cameras. The goals of this thesis are as follows: first, to learn related techniques such as face detection, matching algorithms, person detection, classification of a person's descriptive information, object grouping, and so on; second, to develop a system with the function of searching people in surveillance cameras; and finally, to evaluate the application's search efficiency when combining related techniques.

Techniques:
Face Detection, Face Tracking, Face Clustering, Pedestrian Detection, Person Attributes Recognition
Languages and Frameworks:
Python, Django, OpenCV, HTML/CSS, JavaScript/AJAX

DEMO GALLERY

1 / 6
EyeTeck Slide 1
2 / 6
EyeTeck Slide 2
3 / 6
EyeTeck Slide 3
4 / 6
EyeTeck Slide 4
5 / 6
EyeTeck Slide 5
6 / 6
EyeTeck Slide 6

Supervisor
Duy-Dinh LE Duy-Dinh LE (レイ ユイデン)
Associate Professor, Head, Department of Graduate Studies – Science Technology, University of Information Technology, Vietnam