Abstract:
Parking occupancy detection systems help to
identify the available parking spaces and direct vehicles
efficiently to unoccupied lots by reducing time and energy. This
paper presents an approach for the design and development of
an end-to-end automated vehicle parking occupancy detection
system. The novelty of this study lies in the methodology
followed for the object detection process using RetinaNet one
stage detector and region-based convolutional neural network
deep learning technique. The proposed software architecture
consists of low coupled components that support scalability and
reliability. The developed web-based and mobile-based client
applications assist to find parking spaces easily and efficiently.
The existing solutions utilize dedicated sensors and depend on
manual segmentation of surveillance footage to detect the state
of parking spaces. The proposed approach eliminates existing
limitations while maintaining reasonable accuracy.
