Continental Automotive Gmbh

Bingtao Gao

Paul Barnard

Christian Thiel

James Herbst

Bo Hu

Dehao Liu

Cheng Luo

Hans Christian Thiel

Han Zhang

Tongheng Chen

A method of complementing a map of a scene with 3D reference points including four steps. In a first step, data is collected and recorded based on samples of at least one of an optical sensor, a GNSS, and an IMU. A second step includes initial pose generation by processing of the collected sensor data to provide a track of vehicle poses. A pose is based on a specific data set, on at least one data set recoded before that dataset and on at least one data set recorded after that data set. A third step includes SLAM processing of the initial poses and collected optical sensor data to generate keyframes with feature points. In a fourth step 3D reference points are generated by fusion and optimization of the feature points by using future and past feature points together with a feature point at a point of processing. This second and fourth steps provides significantly better results than SLAM or VIO methods known from prior art, as the second and the fourth steps are based on recorded data. Wherein a normal SLAM or VIO algorithm only can access data of the past, in these steps, processing may also be done by looking at positions ahead, by using the recorded data.

Method for generating 3D reference points in a map of a scene

Some embodiments include a method of generating an environment reference model for positioning comprising: receiving multiple data sets representing a scanned environment including information about a type of sensor used and data for determining an absolute position of objects or feature points represented by the data sets; extracting one or more objects or feature points from each data set; determining a position of each object or feature point in a reference coordinate system; generating a three-dimensional vector representation of the scanned environment aligned with the reference coordinate system including representation of the objects or feature points at corresponding locations, creating links between the objects or feature points in the three dimensional vector model with an identified type of sensor by which they can be detected in the environment; and storing the three-dimensional vector model representation and the links in a retrievable manner.

Environment model using cross-sensor feature point referencing

Some embodiments include a method of generating an environment reference model for positioning comprising: receiving multiple data sets representing a scanned environment including information about a type of sensor used and data for determining an absolute position of objects or feature points represented by the data sets; extracting one or more objects or feature points from each data set; determining a position of each object or feature point in a reference coordinate system; generating a three-dimensional vector representation of the scanned environment aligned with the reference coordinate system including representation of the objects or feature points at corresponding locations; creating links between the objects or feature points in the three-dimensional vector model with an identified type of sensor by which they can be detected in the environment; and storing the three-dimensional vector model representation and the links in a retrievable manner.

A top-view image of a road is composed from at least two images taken by a vehicle-mounted camera. A speed and/or an acceleration of the vehicle is recorded, as well as at least two sequential images. A first image is selected for further processing. A first selected area of the first selected image is determined, located in a zone of the image with minimum distortion. A second image captured later is selected for further processing. A second area of the second image is selected in a zone of the image with minimum distortion and located such that image content shown at a lower border of the second area is adjacent to image content at an upper border of the first selected area. The first and second selected areas are transformed into a top-view perspective, and the transformed first and second selected areas stitched together for generating a composed top-view image.

Growing community of inventors

Chengdu, China

Bingtao Gao