Parkmaster

Abstract

We present the design and implementation of ParkMaster, a system that leverages the ubiquitous smartphone to help drivers find parking spaces in the urban environment. ParkMaster estimates parking space availability using video gleaned from drivers' dash-mounted smartphones on the network's edge, uploading analytics about the street to the cloud in real time as participants drive. Novel lightweight parked-car localization algorithms enable the system to estimate each parked car's approximate location by fusing information from phone's camera, GPS, and inertial sensors, tracking and counting parked cars as they move through the driving car's camera frame of view. To visually calibrate the system, ParkMaster relies only on the size of well-known objects in the urban environment for on-the-go calibration. We implement and deploy ParkMaster on Android smartphones, uploading parking analytics to the Azure cloud. On-the-road experiments in three different environments comprising Los Angeles, Paris and an Italian village measure the end-to-end accuracy of the system's parking estimates (close to 90%) as well as the amount of cellular data usage the system requires (less than one megabyte per hour). Drill-down microbenchmarks then analyze the factors contributing to this end-to-end performance, as video resolution, vision algorithm parameters, and CPU resources. CCS CONCEPTS • Information systems-> Mobile information processing systems; • Human-centered computing-> Ubiquitous and mobile computing systems and tools;

On-street parking availaibilty data in San Francisco, from stationary sensors and high-mileage probe vehicles

“…The simulation of the obtainable crowd-sensed parking availability data is based on the hypothesis that all the considered probe vehicles are equipped with sensors able to detect empty parking spots while passing by a road segment, like described in [3] or [4], and sending this information to a back-end infrastructure, where it is aggregated to obtain a dynamic parking availability map.…”

“…As a result, we obtained in total about 7 million observations of parking availability on the road segments. These observations represent the first dataset we are providing.In addition, we simulated the achievable sensing coverage of on-street parking availability that could be achieved by a fleet of taxis, if they were equipped with sensors able to detect free parking spaces, like side-scanning ultrasonic sensors [3], or windshield-mounted cameras [4]. In particular, by exploiting real taxi trajectories in San Francisco from the Cabspotting project [5], we first computed the frequencies of taxi visits for each road segment covered by the SFpark sensors.…”

Exploring Computing Paradigms for Electric Vehicles: From Cloud to Edge Intelligence, Challenges and Future Directions

“…Addressing the parking lot monitoring issue, [63] proposes an edge computing-based scheme where each vehicle uploads street contents collected by the camera for video analytics. This enables ParkMaster to estimate precise locations and track parked vehicles using information from the vehicle's camera, GPS, and inertial sensors.…”

Edge-MultiAI: Multi-Tenancy of Latency-Sensitive Deep Learning Applications on Edge

“…As the edge nodes are close to the end user's premises, they are often deemed trustworthy and data privacy is ensured to match with the computing requirements. A large body of research (e.g., [78,79,80,81,82,83]) have been conducted in the usage scenarios and performance of edge computing. However, the privacy and security of the edge computing are not much dealt with.…”