Crowdsensing Maps of On-street Parking Spaces

Abstract

It has been estimated that traffic congestion costs the world economy hundreds of billions of dollars each year, increases pollution, and has a negative impact on the overall quality of life in metropolitan areas. A significant part of congestion in urban areas is due to vehicles searching for on-street parking. Detailed and accurate on-street parking maps can help drivers easily locate areas with large numbers of legal parking spaces and thus relieve congestion. In this paper, we address the problem of mapping street parking spaces using vehicles' preinstalled parking sensors. In particular, we focus on identifying legal parking spaces from crowdsourced data, whereas earlier work has largely assumed that such maps of legal spaces are given. We demonstrate that crowdsensing data from vehicle parking sensors can be used to classify on-street areas into legal/illegal parking spaces. Based on more than 2 million data points collected in Highland Park, NJ and downtown Brooklyn, NY areas, we show that on-street parking maps can be estimated with an accuracy of ~90% using proposed weighted occupancy rate thresholding algorithm.