Polynomial Regression and Faster R-CNN Models for University Library Decision Implementation Discovery based on Deep Learning

Abstract

We deal with the development of a seat occupancy detection algorithm for the University’s library utilizing the Faster R-CNN algorithm. The university’s library is widely used by students, particularly during exam season when it can become difficult to find a seat. Going from one building to another is often time-consuming and useless when there are no available seats. This system uses the features of Faster R-CNN in a way to facilitate an automatic seat occupancy monitoring system. Unlike conventional methods of using manual monitoring or weights and occupancy switches as inanimate indicators, it provides real-time seat availability data which allows no human intervention to be a part of the process. Data collection and model training evaluation are considered using annotated datasets with images of library seating layouts. The Faster R-CNN model is trained such that it can accurately detect vacancy or occupancy at library seats. This work takes a futuristic approach towards smart library management systems, in which user needs are changing, and considers the use of high-end computer vision technologies to be integrated into all such libraries. The proposed system aims to leverage the effectiveness of Faster R-CNN and go a long way in redefining seat occupancy management for university libraries by enabling better efficiency, resource utilization, as well as user satisfaction in prospect.