Use this URL to cite or link to this record in EThOS: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.806210
Title: Robotic cameraman for Augmented Reality based broadcast and demonstration
Author: Yan, Dingtian
ISNI:       0000 0004 9349 511X
Awarding Body: University of Essex
Current Institution: University of Essex
Date of Award: 2020
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Abstract:
In recent years, a number of large enterprises have gradually begun to use various Augmented Reality technologies to prominently improve the audiences’ view of their products. Among them, the creation of an immersive virtual interactive scene through the projection has received extensive attention, and this technique refers to projection SAR, which is short for projection spatial augmented reality. However, as the existing projection-SAR systems have immobility and limited working range, they have a huge difficulty to be accepted and used in human daily life. Therefore, this thesis research has proposed a technically feasible optimization scheme so that it can be practically applied to AR broadcasting and demonstrations. Based on three main techniques required by state-of-art projection SAR applications, this thesis has created a novel mobile projection SAR cameraman for AR broadcasting and demonstration. Firstly, by combining the CNN scene parsing model and multiple contour extractors, the proposed contour extraction pipeline can always detect the optimal contour information in non-HD or blurred images. This algorithm reduces the dependency on high quality visual sensors and solves the problems of low contour extraction accuracy in motion blurred images. Secondly, a plane-based visual mapping algorithm is introduced to solve the difficulties of visual mapping in these low-texture scenarios. Finally, a complete process of designing the projection SAR cameraman robot is introduced. This part has solved three main problems in mobile projection-SAR applications: (i) a new method for marking contour on projection model is proposed to replace the model rendering process. By combining contour features and geometric features, users can identify objects on colourless model easily. (ii) a camera initial pose estimation method is developed based on visual tracking algorithms, which can register the start pose of robot to the whole scene in Unity3D. (iii) a novel data transmission approach is introduced to establish a link between external robot and the robot in Unity3D simulation work-space. This makes the robotic cameraman can simulate its trajectory in Unity3D simulation work-space and project correct virtual content. Our proposed mobile projection SAR system has made outstanding contributions to the academic value and practicality of the existing projection SAR technique. It firstly solves the problem of limited working range. When the system is running in a large indoor scene, it can follow the user and project dynamic interactive virtual content automatically instead of increasing the number of visual sensors. Then, it creates a more immersive experience for audience since it supports the user has more body gestures and richer virtual-real interactive plays. Lastly, a mobile system does not require up-front frameworks and cheaper and has provided the public an innovative choice for indoor broadcasting and exhibitions.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.806210  DOI: Not available
Keywords: QA75 Electronic computers. Computer science
Share: