Here Global B.v.

James Adeyemi Fowe

Filippo Pellolio

Leon Stenneth

Bruce A Bernhardt

Gavril Adrian Giurgiu

Aditya Balasaheb Jadhav

Vladimir Boroditsky

Leo Modica

Kyle Jackson

Toby Tennent

Finn Swingley

Catalin Capota

Mitchell McCuiston

Piotr Knap

Michael Finn

Sam Radomy

Earl Hammond

Ömer Mubarek

Joe Ciprian

Samuel Radomy

Yingzhou Yu

Pradeep Maddineni

Bassel Sadek

Harsh Yallapantula

Corinne Bradley

Corrine Bradley

Andrew Dean

Carol Walz

Matthew Vachlon

Indu Kodali

Garvil Giurgiu

Timothy Garcia

Digan Conor

Naoko Harada

An approach is provided for computer-vision-based object motion detection. The approach involves receiving a video sequence captured from a perspective of a vehicle/device traveling at street level. The approach also involves processing frames of the videos sequence using computer vision to determine semantic localization feature(s) associated with object(s) detected in the frames. The approach further involves clustering the object(s) into object cluster(s) across the frames based on the semantic localization feature(s). The approach further involves creating an object vector connecting the object(s) in a given cluster of the object cluster(s) across the frames. The approach further involves computing an angle between the object vector and a reference vector associated with a movement of the vehicle/device across the frames. The approach further involves classifying a motion of the object(s) relative to the vehicle/device based on the angle.

Method and apparatus for computer-vision-based object motion detection

System and methods for detecting and obtaining lane level insight in unplanned incidents. Probe-based vehicles and lane-level insight using a lane-level map-matcher are used to acquire information. This information is aggregated and used to differentiate lane activity in terms of traffic and safe navigation. With the identification of probes per-lane and probe speeds per-lane, sudden reductions in probe speeds may be obtained at a lane-based level. This is used to verify or detect lane-level incident or hazard warnings and consequently alert a driver to safer navigation paths ahead of time, for example alerting the driver to maneuver to a different lane or to take an alternative route.

Detecting and obtaining lane level insight in unplanned incidents

An approach is provided for using pedestrian probe data for ridesharing. The approach involves, for example, receiving pedestrian probe data from a search zone associated with a designated location. The pedestrian probe data is collected, for instance, from one or more location sensors of at least one device associated with at least one pedestrian. The approach also involves processing the pedestrian probe data to determine one or more pedestrian paths terminating at the designated location. The approach further involves identifying at least one common origin, at least one common destination, or a combination thereof of the one or more pedestrian paths and providing the least one common origin, the at least one common destination, or a combination thereof as an output.

Method and apparatus for using pedestrian probe data for ridesharing services

System and methods for real-time lane level traffic processing. A lane level map matcher is used to map match probe data from probes to the lane level. A lane level travel time aggregator determines an optimal method to allocate travel-time per-link for a probe trajectory that traverses at least one lane. A lane aggregator aggregates the probe trajectories and probe-path speeds per-lane and obtain the representative speed for the lane.

Real-time lane-level traffic processing system and method

A plurality of instances of event data are received. Each instance of event data corresponds to a traffic event on a first segment and comprises an indication of at least one parameter characterizing travel of a vehicle along the first segment during the traffic event. Based on the plurality of instances of event data, a recurring event is identified. At least one representative parameter characterizing travel along the first segment during the recurring event is determined based on the two or more instances of event data corresponding to the recurring event. At least one element of a data structure is modified with the at least one representative parameter. The at least one element of the data structure corresponds to the first segment. A geographic database comprises the data structure and a navigation application is configured to use at least a portion of the data structure to perform a navigation function.

Use of geographic database comprising lane level information for traffic parameter prediction

A method, apparatus, and computer program product are provided for real-time map-matching of probe data. Methods may include: receiving a plurality of probe data points; receiving an indication of changes to the road network, where the indication of changes includes an addition of new road segments and a removal of closed road segments; map-matching the plurality of probe data points to one or more road segments of the road network based on closest candidate road segments to form map-matched probe data; in response to a closest candidate road segment for one or more probe data points of the plurality of probe data points corresponding to a closed road segment, map-matching the one or more probe data points to a next closest candidate road segment in the map-matched probe data; and updating dynamic map data with the map-matched probe data.

Method, apparatus, and computer program product for real-time map-matching

An approach is provided for automatically detecting a merge lane traffic jam. The approach involves, for example, determining a plurality of road links in proximity to a merge point comprising a highway and a ramp. The method also involves processing probe data collected from the plurality of road links to classify the plurality of road links, one or more sublinks of the plurality of road links, or a combination thereof into at least one of a highway upstream class, a merging area class, a highway downstream class, a ramp downstream class, and a ramp upstream class. The method further involves determining vehicle speed data for the highway upstream class, the merging area class, the highway downstream class, the ramp downstream class, the ramp upstream class, or a combination thereof. The method further involves automatically determining an occurrence of the merge lane traffic jam based on the vehicle speed data.

Method, apparatus, and system for detecting a merge lane traffic jam

An apparatus and method for determining a traffic level in the future. A road network including graph edges for a plurality of intersections and graph nodes for a plurality of road links is identified. A road link of interest is selected from the plurality of road links. A set of related link subset are calculated for the selected road link. Historical data is queried for the related link subset. A predicted traffic level is calculated for the selected road link in response to the historical data for the related link subset.

Traffic predictions at lane level

A method, apparatus and computer program product are provided to define a strand upstream of a direction based traffic (DBT) link. In a method, a strand is defined upstream of a DBT link. The method includes extending the strand so as to include one or more links upstream of the DBT link. The strand is extended by determining whether a link is to be added to the strand based upon evaluation of a termination criteria. The termination criteria is at least partially based upon a relationship of a function class of the link to the function class of one or more other links. In an instance in which the termination criteria is satisfied, the method ceases further extension of the strand.

Method, apparatus and computer program product for defining a strand upstream of a direction-based traffic link

An approach is provided for determining tunnel speed for a vehicle travelling through a tunnel. A tunnel processing platform aggregates probe data associated with at least one vehicle into at least one tunnel path based, at least in part, on a network geometry topology for at least one tunnel. The tunnel processing platform also designates at least one probe point collected upstream of the at least one tunnel as at least one starting point of the at least one tunnel path and at least one temporary probe point as at least one endpoint of the at least one tunnel path, wherein the at least one temporary probe point is downstream of the at least one tunnel. It then determines at least one temporary tunnel speed for the at least one tunnel path based, at least in part, on the timestamp for the at least one probe point and the current time associated with the at least one temporary probe point.

Method and apparatus for determining an estimated traffic congestion status of a tunnel based on probe data

A method, apparatus and computer program product are provided to automatically detect changes in width of road segments in real-time or near real-time using probe data, such as probe data collected from vehicle and/or mobile devices traveling along a road segment. Probe data collected in real-time or near real-time is partitioned in order to identify width-defining portions of the probe data. The width-defining portions may be representative of the laterally-extreme lanes of the road segment, such as the left-most lane and the right-most lane. The width-defining portions are compared to corresponding width-defining portions of historical probe data to determine measures indicative of whether a road segment has expanded or narrowed. Indications of detected segment width changes may be provided to drivers and/or other systems or users. For example, map data for the road segment may be updated to reflect a detected width expansion or narrowing of the road segment.

Automatic detection of segment width narrowing using probe data

An approach is provided for creating an origin-destination matrix from probe trajectory data. The approach includes determining, via an outdoor positioning system, that at least one probe device has entered a point-of-interest (POI). The approach also includes initiating an indoor positioning system to determine indoor location data associated for the at least one probe device while the at least one device is within the POI. The approach further includes processing the indoor location data to generate an origin-destination (OD) matrix. The OD matrix represents an indoor movement of the at least one probe device among a plurality of sub-POIs located within the POI indicated by the indoor location data. The approach further includes providing the OD matrix as an output.

Method and apparatus for providing an indoor pedestrian origin-destination matrix and flow analytics

An approach is provided for an unknown moving object detection system. The approach, for instance, involves capturing a plurality of unknown object events indicating an unknown object detected by one or more computer vision systems. The approach also involves clustering the plurality of unknown object events into a plurality of clusters based on one or more clustering parameters. The approach further involves selecting at least one cluster of the plurality of clusters based on a selection criterion. The approach further involves determining at least one operating scenario for the one or more computer vision systems based on a combination of the one or more clustering parameters associated with the selected at least one cluster.

Method and apparatus for providing unknown moving object detection

A method, apparatus, and computer program product are provided for dynamically detecting pedestrian activity. The method includes receiving one or more data objects from a vehicle. The one or more data objects may be processed using an image processing model to determine one or more pedestrian parameters. The method further includes determining whether the one or more pedestrian parameters satisfy one or more pedestrian parameter thresholds. In an instance the one or more pedestrian parameters do not satisfy the one or more pedestrian parameter thresholds, the method further includes causing a safety alert warning to be provided to one or more other vehicles. Corresponding apparatuses and computer program products are also provided.

Method, apparatus, and computer program product for dynamic detection of pedestrian activity

One or more potential drone and/or flying car (DFC) corridors are identified based on the topology of a road network. Trajectories traveled by vehicles are determined from a plurality of instances of probe data received from a plurality of vehicle apparatuses onboard the vehicles. A volume of traffic for a path through the road network and corresponding to a potential DFC corridor is determined based on the trajectories. A delay metric for the path through the road network and corresponding to the potential DFC corridor is determined based on the trajectories. A traffic metric is then determined for the path based on a combination of the volume of traffic, the delay metric and a measure of the topology of the road network. The one or more potential DFC corridors are ranked by their corresponding traffic metrics.

Growing community of inventors

Evanston, IL, United States of America

James Adeyemi Fowe