In this paper, we present a Faster R-CNN based object detection scheme to automatically map the parking spaces in a parking lot, instead of manually mapping them. The work addresses an important gap in the recent computer vision based artificial intelligence techniques to build smart parking systems. Our results show that our approach decreases the human effort needed by upto a compelling 86%. We show that the percentage of the available parking spots that are automatically detected through our approach accumulates over time and, in theory, can approach a 100%, on a day when all the parking spots are fully occupied. In other words, the approach is designed to have its highest performance over a busy parking lot during the busiest time.
Paper
Full text
Faster R-CNN based Automatic Parking Space Detection
Semantic Scholar · Computer Science · 2020
Abstract
In this paper, we present a Faster R-CNN based object detection scheme to automatically map the parking spaces in a parking lot, instead of manually mapping them. The work addresses an important gap in the recent computer vision based artificial intelligence techniques to build smart parking systems. Our results show that our approach decreases the human effort needed by upto a compelling 86%. We show that the percentage of the available parking spots that are automatically detected through our approach accumulates over time and, in theory, can approach a 100%, on a day when all the parking spots are fully occupied. In other words, the approach is designed to have its highest performance over a busy parking lot during the busiest time.