Volkswagen Ag

Tektronix, Inc.

Audi Ag

Tektronix Berlin Gmbh & Co. Kg

Marek Musial

Simon Steinmeyer

Thorsten Bagdonat

Tim Kubertschak

Carsten Deeg

Daniel Mossau

Thorsten Graf

Dennis Loeben

Christoph Erfurth

Patrick Glässer

Oliver Birbach

A method, a device and a computer-readable storage medium with instructions for processing sensor data. In a first step, camera images are taken by a camera. Additionally, 3D-checkpoints are detected by at least one 3D-sensor. Optionally, at least one of the camera images can be segmented. The camera images are then merged with the 3D-checkpoints by a data fusion circuit to form data of a virtual sensor. The resulting data are finally output for further processing.

Method, device and computer-readable storage medium with instructions for processing sensor data

The invention relates to a method for improved data fusion during environment detection in a motor vehicle (), comprising the following steps: detecting () an environment () of the motor vehicle () using at least one sensor (); recognising () objects () in measurement data () detected by the at least one sensor (); fusioning () of the recognised objects () and the object positions thereof in an environment map (), wherein a probability of existence is/will be assigned to objects () recorded in the environment map (), and wherein the probability of existence of a recorded object () is reduced, when a free region () is measured during the detection of the position of the recorded object, wherein a respective orientation attribute () is assigned to the objects () recorded in the environment map () and recorded in the environment map (), and for a region in the sensor region () of the at least one sensor (), in which a free region () is measured, the probability of existence of an object () recorded in the region of the environment map () corresponding to the region is reduced in accordance with the assigned orientation attribute (). The invention also relates to the associated device ().

Method and device in a motor vehicle for improved data fusion in an environment detection

A method for recognizing the shape of an object outside of a transportation vehicle, wherein a respective image is generated at at least two different measurement time points and at least one scanline is specified in a first one of the images and a corresponding scanline is specified in each other of the images, and for each scanline of the first image, a profile resulting along the scanline is determined and a corresponding profile is determined along the respective corresponding scanline of each other image, and by comparing the profile of each scanline of the first image to the respective corresponding profile of each other image a respective displacement distance resulting between the measurement time points of characteristic regions is determined, and a distinction is made of each characteristic region between object and background based on the determined displacement distance.

Method for shape recognition of an object outside of a transportation vehicle and transportation vehicle

A method for external use of a device having a wireless communication interface by a program of a mobile device. External use is possible only when a key device serving as an authentication token communicates with the program. This increases the security of an entry method for a vehicle.

Method and device for external operation of a device

The present invention relates to a process for learning a basic finite automaton of a protocol implementation, which process is characterized by the following steps: a) categorizing the times () within an example communication into equivalence classes and b) using said equivalence classes as states of the learned automaton. The invention further relates to a process for learning arithmetic classification rules for feature vectors from a training set of positive examples, which process is characterized by the following steps: a) forming derived features (y&#x2212;v; x&#x2212;z), based on statistical measures, in the form of arithmetic terms; b) formulating logic conditions (x=w+1, y=v+1, z=x) on the numerical values of the features from the training set or the derived features.

Process for learning the basic finite automation of a protocol implementation

The present invention relates to a method for checking a data exchange between participants in a call established on a communication medium in compliance with a protocol. In order to identify the various stages in a call process conforming to the protocol and to break said protocol once the checking procedure has started, the invention suggests that the data exchange be captured by-means of a protocol monitor (PM) connected to a communication medium (CM) and based on the finite state automaton principle. The test automaton contains the same states and state variables as the protocol automaton designed to define the communication protocol, apart from the fact that the test automaton is allocated a plurality of values within the same range of corresponding state variable values in the protocol automaton. The transitions in the protocol automaton as observed on the communication medium (CM) are simulated for investigation purposes in the test automaton and, by a process of logical elimination, a state is shaped in the test automaton which matches the relevant state in the protocol automaton.

Growing community of inventors

Berlin, Germany

Marek Musial