Bayerische Motoren Werke Aktiengesellschaft

Veoneer Sweden Ab

Dominik Kellner

Georg Tanzmeister

Sascha Steyer

Armin Stangl

Michael Aeberhard

Nicolas Schneider

A method for detecting objects in the surroundings of a vehicle includes receiving sensor data which describe the objects in the surroundings from a surroundings sensor of the vehicle; determining each of the corners of the objects, with the corners describing outer delimitations of each object; determining a relative position of each of the corners to the surroundings sensor; sorting the determined corners in a predetermined angle direction; checking, for each of the corners in the angle direction, whether the corners are covered by another of the objects, on the basis of the relative position of each of the corners to the surroundings sensor; and determining regions of each of the objects that can be detected by the surroundings sensor, on the basis of checking the corners.

Method for detecting objects in the surroundings of a vehicle by determining coverage of the objects, computing device, and sensor system

Camera data and radar echoes are received from the surroundings. At least one radar echo is assigned to a delimiting frame of an object detected on the basis of a camera, the delimiting frame being generated using the camera data by comparing corresponding azimuth angles and specified distances of the radar echo and the object detected on the basis of a camera. In the event of a successful assignment, a distance which is assumed on the basis of a camera is corrected according to the distance of the respective detected object in the surroundings, said distance being determined in a radar-based manner. The respective delimiting frame together with the corrected distance is then output as an object data set which indicates a successful object detection.

Method for detecting moving objects in the surroundings of a vehicle, and motor vehicle

A method () for determining the value of a size of an object () is described. The method () comprises determining () an occupancy grid () indicating evidence that individual cells () are vacant or occupied by the object (). Further, the method () comprises determining () a subset of cells () associated with the object (). Further, the method () comprises detecting () two opposing bounding edges of the object (), and determining () a measurement value of the size of the object () based on the distance between the detected edges of the object (). The method () further comprises determining () a quality measure indicating how well the two opposing edges of the object () could be detected, and determining () a measurement probability distribution of the size of the object () dependent on the quality measure. Further, the method () comprises determining () a cumulative probability distribution based on the measurement probability distribution, and determining () a value of the size of the object () based on the cumulative probability distribution.

Method and processing unit for determining the size of an object

A concept of characterizing an object based on measurement samples from one or more location sensors, the measurement samples having a first spatial resolution. The measurement samples are quantized to a grid map of weighted cells having a second spatial resolution lower than the first spatial resolution, wherein a measurement sample contributes to a weight coefficient of one or more weighted cells depending on a measurement accuracy. Parameters of one or more lines fitting the weighted cells are computed to obtain a characterization of the object.

Apparatus and method for characterizing an object based on measurement samples from one or more location sensors

A method and system for integrating multiple measurement hypotheses in an efficient labeled multi-Bernoulli (LMB) filter. The LMB filter estimates a plurality of tracks for a plurality of objects, each track of the plurality of tracks having a unique label, a probability, and a state, wherein each track of the plurality of tracks is associated to an object of a plurality of objects to be tracked, each object having an object state. The method receives one or more measurement hypotheses of the multiple measurement hypotheses for each object of the plurality of objects; updates each track of the plurality of tracks based on the respective track and the one or more measurement hypotheses of the multiple measurement hypotheses; determines, for each combination of track of the plurality of tracks and measurement hypothesis, a likelihood &#x3b7;(j, k); samples, for each iteration of a plurality of iterations, an update hypothesis &#x3b3;, based on an association of each track of the plurality of tracks to one of: a measurement hypothesis, an events missed detection, or a track dying detection; determining the state of each track of the plurality of tracks based on its respective associations in the updated hypotheses &#x3b3;; extracts, for each track of the plurality of tracks, an existence probability; predicting the object state of each object of the plurality of objects with respect to a next measurement time; determines, whether another update is to be performed; and if another update is to be performed, repeats again the method steps from and including updating each track of the plurality of tracks.

Object tracking based on multiple measurement hypotheses

A vehicle environment detection system () including a control unit () and a sensor arrangement () that in turn includes at least two sensor arrangement parts (). The control unit () is arranged to determine one or more systematic errors in a certain direction () for one sensor arrangement part () by combining acquired sensor data for the sensor arrangement part () with acquired sensor data from another sensor arrangement part (). The another sensor arrangement part () has a lower degree of systematic error in the certain direction () than the sensor arrangement part ().

Error estimation for a vehicle environment detection system

A vehicle environment detection system () that includes a detection device and a processing unit (), arranged to detect at least two feature points at objects () outside a vehicle (). Each feature point constitutes a retrievable point that has a fixed position (x, y; x, y) on the object (). The processing unit () is arranged to determine the positions (x, y; x, y) and the resulting velocities (v, v) for each one of the feature points for multiple frames by use of a feature point tracker; and determine a reference position (x, y), a corresponding reference velocity (v) and reference angular velocity (&#x3c9;), constituting a common motion state for the object (), by use of the results from the feature point tracker. A feature point tracker is constituted by a tracking algorithm which is arranged to track multiple features and which includes temporal filtering.

Growing community of inventors

Dachau, Germany

Dominik Kellner