Daimler Ag

Daimler Chrysler Ag

Siemens Aktiengesellschaft

Joachim Gloger

Stefan Hahn

Bernd Woltermann

Eberhard Mandler

Mathias Hartl

Lars Krüger

Thomas Ruland

Werner Ritter

Torsten Caesar

Matthias Oberlaender

Volker Stampa

Stefan Franz

Matthias Reichmann

The invention relates to a device for monitoring an environment of a vehicle, wherein the environment is captured by means of a plurality of image capturing units, the capture ranges () thereof at least partially overlapping each other and forming an overlap range (), wherein an overall image is generated from the individual images captured by means of the image capturing units by means of an image processing unit, said overall image showing the vehicle and the environment thereof from a bird's-eye view. According to the invention, the image capturing units are designed as wafer-level cameras ().

Device for monitoring an environment of a vehicle with pairs of wafer level cameras using different base distances

A method for monitoring an environment (U) of a vehicle (F), wherein the environment (U) and objects (O, O) present therein are detected by means of at least a first image detection unit () and a second image detection unit (), of which the detection regions overlap at least partially and form an overlap region, wherein an overall image (G) is produced from individual images detected by means of the image detection units () by means of an image processing unit, the overall image (G) showing the vehicle (F) and its environment (U) from a bird's eye view. There is a progression of at least one boundary line (Lto L) which extends from an origin to the image edge of the overall image in such a way that the boundary line (Lto L) extends away from the objects (O, O).

Method for monitoring an environment of a vehicle

A method for characterizing a pattern present as stored information, includes the steps of generating a characterizing proposal for the pattern using a server computer system, presenting the pattern and the characterizing proposal to a client computer using a computer program via the Internet so as to enable a user to perform an evaluation of the characterizing proposal, and receiving an evaluation input from the user at the server computer system. The evaluation input is one of an acceptance input of the characterizing proposal and a rejection input of the characterizing proposal. The rejection input includes an alternative characterizing proposal.

Method for characterizing stored information

The invention concerns a device for improving the view in vehicles, in particular at night, bad weather and fog. In the process images of actual traffic scenes are recorded by a camera (), which is sensitive outside the visible spectrum, and these images are reproduced in the visible spectrum in the vehicle via a display optic (). According to the invention the type of object which is contained in a traffic scene recorded by the camera () is automatically classified according to type, and depending upon the type of the recognized object it is reproduced on the display optic () in an intensity and/or color, which corresponds to the intensity and/or color which the associated object typically has by daylight. The process facilitates the recognition by the vehicle operator of images of traffic scenes recorded outside the visible spectrum.

Process and device for improving the visibility in vehicles

A method and a device for detecting road users and obstacles on the basis of camera images, in order to determine their distance from the observer and to classify them. In a two-step classification, potential other parties involved in a collision are detected and identified. In so doing, in a first step, potential other parties involved in a collision are marked in the image data of a mono-image camera; their distance and relative velocity are subsequently determined so that endangering objects can be selectively subjected to a type classification in real time. By breaking down the detection activity into a plurality of steps, the real-time capability of the system is also rendered possible using conventional sensors already present in the vehicle.

Camera-based precrash detection system

Described is a method of recognizing sequences of handwritten and/or joined-up numerals, in particular post codes, the method calling for the conversion of of feature vectors, thus enabling the sequence of numerals to be recognized using an HMM recognition device without the need for segmentation of the image. Also described are particularly relevant examples of feature extraction.

Growing community of inventors

Bibertal, Germany

Joachim Gloger