|
|
Monitoring the Movement of Visitors in Museum Exhibitions
Viskupič, Matej ; Dyk, Tomáš (referee) ; Drahanský, Martin (advisor)
The aim of this work is to propose a new system of monitoring visitors in museums. Incontrast to existing methods, the problem is solved here only using camera technology. This requires addressing three sub-problems: (1.) detection of visitors in camera streams using a convolutional neural network; (2.) camera configuration to exactly determine the position of the detected persons within the monitoring area; and (3.) identification and tracking the detected persons. The outcome of the proposed solution is the heatmap of most visited places, the map of visitor trajectories and the statistic of visits for individual exhibits. This monitoring method can contribute towards improved evaluation of visitor experience and more effective selection and positioning of the exhibits.
|
|
|
Smart Camera System for Museum Exhibitions
Homola, Radim ; Orság, Filip (referee) ; Rydlo, Štěpán (advisor)
This thesis focuses on development and construction of a camera system, that captures and post-processes video footage within museum environment in real time. Defined issue is resolved by separating the whole camera system into camera and computing unit, selecting correct components, mainly the camera module, and providing sufficient cooling for the computing unit. Following the solutions steps above enables to hide the powerful computing unit away from the visitor’s sight and also miniaturization of the visibly positioned camera unit. The developed camera system allows isolated operation of various algorithms, where the processed results can help exhibitors with better showpiece placements, recognition of unwanted behavior or protection from vandalism.
|
|
|
Monitoring the Movement of Visitors in Museum Exhibitions
Viskupič, Matej ; Dyk, Tomáš (referee) ; Drahanský, Martin (advisor)
The aim of this work is to propose a new system of monitoring visitors in museums. Incontrast to existing methods, the problem is solved here only using camera technology. This requires addressing three sub-problems: (1.) detection of visitors in camera streams using a convolutional neural network; (2.) camera configuration to exactly determine the position of the detected persons within the monitoring area; and (3.) identification and tracking the detected persons. The outcome of the proposed solution is the heatmap of most visited places, the map of visitor trajectories and the statistic of visits for individual exhibits. This monitoring method can contribute towards improved evaluation of visitor experience and more effective selection and positioning of the exhibits.
|
guest ::
