Abstract: Described techniques receive location data with associated timestamps from one or more location sensors spatially associated with the vehicle. Each pair of consecutive location data defines a segment of the vehicle's trajectory. The system aggregates potential stay periods of consecutive segments into an aggregated stay interval as long as a predefined segment clustering rule is fulfilled by the consecutive segments. A potential stay of the vehicle with a potential stay period for a respective segment is detected if the time interval associated with the respective segment is longer than an expected driving time needed for driving a distance associated with the respective segment at a predefined expected speed. The potential stay period is computed for the respective segment as the difference between the associated time interval and the expected driving time. The system detects a stay of the vehicle if the aggregated stay interval reaches a predefined minimum stay period.

Abstract: Described techniques receive location data with associated timestamps from one or more location sensors spatially associated with the vehicle. Each pair of consecutive location data defines a segment of the vehicle's trajectory. The system aggregates potential stay periods of consecutive segments into an aggregated stay interval as long as a predefined segment clustering rule is fulfilled by the consecutive segments. A potential stay of the vehicle with a potential stay period for a respective segment is detected if the time interval associated with the respective segment is longer than an expected driving time needed for driving a distance associated with the respective segment at a predefined expected speed. The potential stay period is computed for the respective segment as the difference between the associated time interval and the expected driving time. The system detects a stay of the vehicle if the aggregated stay interval reaches a predefined minimum stay period.