Indoor Mapping based on recorded videos

Knowledge of indoor spatial information is vital to stores, warehouses, industries, and homes alike. It is used to optimize layouts to achieve easier navigation for humans, machines, and autonomous robots. Maps provide limited data about the specific placement of objects in the environment and inferring information about the physical space can be impossible. The objective of the study is: (i) to design a comprehensive indoor mapping solution based on the processing of previously recorded videos, (ii) experiment with sensor data to enrich the indoor mapping solution, and (iii) research spatial recognition patterns and optimal navigation to enable efficient spatial discovery and mapping. After a successful research, the partner organization will have a decent architecture for spatial recognition with recorded videos, and this can either be used to be integrated into an individual product or to assist the development of other diversify techniques.

Faculty Supervisor:

Sven Dickinson;Anthony Bonner;Kiriakos Neoklis Kutulakos

Student:

Lipai Xu;Qinyu Lei;Rahul Singh Shekhawat

Partner:

SOTI Inc

Discipline:

Computer science

Sector:

University:

University of Toronto

Program: