Abstract
Abstract. This paper presents a method to estimate the occupancy ratio of parkings from SAR satellite images. The algorithm takes as input a series of Sentinel-1 images along with a mask indicating where the parking is located and returns for each image an occupancy ratio. The method is generic and can easily be extended. We validate our results in two parts. First, we have created a dataset of Sentinel-1 GRD image time series where each image is associated to a ground truth parking occupancy ratio. This ground truth is estimated thanks to a surveillance camera that permanently films and records the parking. We observe a strong correlation between the estimated occupancy rate and the ground truth occupancy rate. Secondly, we estimate the occupancy ratio of the 250 largest retail parkings in France from January 2018 to April 2020. We observe that weekly and seasonal patterns are consistent with consumer and economic trends. Parking occupancy estimations also plummet during the COVID-19 containment measures.
Highlights
Automatic parking occupancy monitoring can greatly help public and private institutions make better informed decisions
We present in this paper a method that estimates the occupancy ratio of open car parks from time series of Sentinel-1 images
If we assume a linear relationship between the brightness of a pixel and its occupancy ratio, we can adapt occupancy ratios shown in Section 3.3 by adding a second threshold
Summary
Automatic parking occupancy monitoring can greatly help public and private institutions make better informed decisions. (Aryandoust et al, 2019) use Uber Movement travel time data to infer parking occupancy These methods are accurate, they require the installation of measuring devices in parkings or cars. (Paidi, Fleyeh, 2019) use thermal cameras to detect cars Vehicle detectors, both for standard images (Behrendt, 2019) or aerial / satellite images (Xia, et al, 2018, Drouyer, de Franchis, 2019, Drouyer, 2020b), can be used to estimate parking occupancy. We present in this paper a method that estimates the occupancy ratio of open car parks from time series of Sentinel-1 images. The method takes as input a series of Sentinel-1 images along with a mask indicating where the parking is located It returns for each image an occupancy ratio comprised between 0% and 100%. We don’t have ground truth associated to them, but we observe that our obtained weekly and seasonal patterns are consistent with consumer and economic trends
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
