Here Global B.v.

Jan Van Sickle

Carolyn Johnston

Robert Ledner

Eric Dieckman

Timm Kayser

Dietmar Rabel

Nicholas Dronen

Brad Keserich

Stephen O'Hara

An apparatus, or corresponding method, for building or updating a map database is described. In one example, the apparatus includes an image correlation module, a training device, and a learned model or neural network. The image correlation module is configured to correlate a first aerial image and terrestrial sensor data collected at a terrestrial vehicle based on at least one control point from the terrestrial data. The learned model training device is configured to define a learned model based using at least one control point from the terrestrial sensor data as ground truth for analysis of the first aerial image. The learned model inference module is configured to receive a second aerial image and apply the learned model on the second aerial image for identification of mapping information for the map data.

Automatic feature extraction from imagery

An apparatus onboard a vehicle and in communication with sensors onboard the vehicle is configured to receive a maplet request identifying a request region; determine that the apparatus has entered the request region; process and fuse sensor data captured by two or more sensors of the sensors to generate a multi-sensor data stream comprising a plurality of observations corresponding to a portion of a road network; generate a maplet based on the multi-sensor data stream and the maplet request, wherein generating the maplet comprises using a predetermined data model to encode road data, from the multi-sensor data stream, corresponding to at least one environment element of the road network; and provide the maplet such that a network apparatus receives the maplet. The network apparatus is configured to (a) validate or (b) update map data of a digital map representing the road network based at least in part on the maplet.

Maplets for maintaining and updating a self-healing high definition map

An apparatus is onboard a vehicle and in communication with sensors onboard the vehicle. The apparatus receives a maplet request identifying a request region; and, responsive to determining that the vehicle is within the request region, processes sensor data captured by sensors to generate a multi-sensor data stream corresponding to a road network segment. The apparatus identifies an observation corresponding to a pole-like object within the multi-sensor data stream; and generates a maplet based on the observation and the maplet request. Generating the maplet comprises using a predetermined data model and a predetermined data format corresponding to a pole-like object observation class to encode road data corresponding to the observation corresponding to the pole-like object. The apparatus provides the maplet such that a network apparatus receives the maplet. The network apparatus is configured to validate/update map data of a digital map representing the road network based on the maplet.

An apparatus is onboard a vehicle and in communication with sensors onboard the vehicle. The apparatus receives a maplet request identifying a request region; and, responsive to determining that the vehicle is within the request region, processes sensor data captured by sensors to generate a multi-sensor data stream corresponding to a road network segment. The apparatus identifies an observation corresponding to a construction marker within the multi-sensor data stream; and generates a maplet based on the observation and the maplet request. Generating the maplet comprises using a predetermined data model and a predetermined data format corresponding to a construction marker observation class to encode road data corresponding to the observation corresponding to the construction marker. The apparatus provides the maplet such that a network apparatus receives the maplet. The network apparatus is configured to validate/update map data of a digital map representing the road network based on the maplet.

An apparatus is onboard a vehicle and in communication with sensors onboard the vehicle. The apparatus receives a maplet request identifying a request region; and, responsive to determining that the vehicle is within the request region, processes sensor data captured by sensors to generate a multi-sensor data stream corresponding to a road network segment. The apparatus identifies an observation corresponding to a traffic signal within the multi-sensor data stream; and generates a maplet based on the observation and the maplet request. Generating the maplet comprises using a predetermined data model and a predetermined data format corresponding to a traffic signal observation class to encode road data corresponding to the observation corresponding to the traffic signal. The apparatus provides the maplet such that a network apparatus receives the maplet. The network apparatus is configured to validate/update map data of a digital map representing the road network based on the maplet.

An apparatus is onboard a vehicle and in communication with sensors onboard the vehicle. The apparatus receives a maplet request identifying a request region; and, responsive to determining that the vehicle is within the request region, processes sensor data captured by sensors to generate a multi-sensor data stream corresponding to a road network segment. The apparatus identifies an observation corresponding to a road marking within the multi-sensor data stream; and generates a maplet based on the observation and the maplet request. Generating the maplet comprises using a predetermined data model and a predetermined data format corresponding to a road marking observation class to encode road data corresponding to the observation corresponding to the road marking. The apparatus provides the maplet such that a network apparatus receives the maplet. The network apparatus is configured to validate/update map data of a digital map representing the road network based on the maplet.

An apparatus, method and computer program product are provided to train a feature detector to identify a respective feature from images captured by a camera. With respect to an apparatus, the apparatus causes at least one feature from one or more images that have been labelled to be projected onto a map. The apparatus is also caused to refine a representation of a path of a vehicle that carries a camera that captured the one or more images based upon registration of the at least one feature that has been projected with the map. Based upon the path of the vehicle following refinement, the apparatus projects one or more other features that have not been labelled from the map into the one or more images and then utilizes the images to train a feature detector.

Growing community of inventors

Eindhoven, Netherlands

Jan Van Sickle