Patents by Inventor Jens Eric Markus Mehnert

Jens Eric Markus Mehnert has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11521375
    Abstract: A method and a system for improved object marking in sensor data, as the result of which an at least partially automated annotation of objects or object classes in a recorded data set is possible. The method provides that a scene is detected in a first state by at least one sensor. An association of a first object marking with at least one object contained in the scene in a first data set containing the scene in the first state then takes place. The similar or matching scene is subsequently detected in a second state that is different from the first state by the at least one sensor, and an at least partial acceptance of the first object marking, contained in the first data set, for the object recognized in the second state of the scene as a second object marking in a second data set takes place.
    Type: Grant
    Filed: September 3, 2019
    Date of Patent: December 6, 2022
    Assignee: Robert Bosch GmbH
    Inventor: Jens Eric Markus Mehnert
  • Patent number: 11410022
    Abstract: A method for classifying an object having the following: receiving at least one item of distance information of an object based on a first electromagnetic signal transmitted by a transmitter device and a first electromagnetic signal received by a receiver device; receiving at least one item of oscillation information of the object based on a second electromagnetic signal transmitted by a transmitter device and a second electromagnetic signal received by a receiver device, which represents a solid oscillation of at least one subsection of the object; and classifying the object based on the received information.
    Type: Grant
    Filed: October 4, 2018
    Date of Patent: August 9, 2022
    Assignee: Robert Bosch GmbH
    Inventor: Jens Eric Markus Mehnert
  • Publication number: 20220164654
    Abstract: A method for training an artificial neural network (ANN) whose behavior is characterized by trainable parameters. In the method, the parameters are initialized. Training data are provided which are labeled with target outputs onto which the ANN is to map the training data in each case. The training data are supplied to the ANN and mapped onto outputs by the ANN. The matching of the outputs with the learning outputs is assessed according to a predefined cost function. Based on a predefined criterion, at least one first subset of parameters to be trained and one second subset of parameters to be retained are selected from the set of parameters. The parameters to be trained are optimized. The parameters to be retained are in each case left at their initialized values or at a value already obtained during the optimization.
    Type: Application
    Filed: November 9, 2021
    Publication date: May 26, 2022
    Inventors: Alexandru Paul Condurache, Jens Eric Markus Mehnert, Paul Wimmer
  • Patent number: 11087470
    Abstract: A system includes a K1 preprocessing module designed to generate at least one intermediate image from an input image using a parameterized internal processing chain and an analysis module to detect a feature or object in the intermediate image. A method to train the system includes feeding a plurality of learning input images to the system, comparing a result provided by the analysis module for each of the learning input images to a learning value, and feeding back a deviation obtained by the comparison to an input preprocessing module and/or adapting parameters of the internal processing chain to reduce the deviation.
    Type: Grant
    Filed: June 11, 2018
    Date of Patent: August 10, 2021
    Assignee: Robert Bosch GmbH
    Inventors: Jens Eric Markus Mehnert, Stefan Bischoff, Stephan Lenor
  • Publication number: 20210192285
    Abstract: A method for configuring a neural network. The method includes: feeding image data to the neural network implemented on a training hardware; feeding the image data to a neural network implemented on an inference hardware; ascertaining a deviation between output data of the training hardware and output data of the inference hardware; and ascertaining noise parameters for the neural network in such a way that after feeding the image data to the neural network implemented on the training hardware and after feeding image data to the neural network implemented on the inference hardware, the output data of the inference hardware and the output data of the training hardware are bit-identical.
    Type: Application
    Filed: December 11, 2020
    Publication date: June 24, 2021
    Inventor: Jens Eric Markus Mehnert
  • Publication number: 20210125491
    Abstract: A method for providing annotated traffic area data. The method includes a step of reading in traffic area data that in each case represent a section of a traffic area used by a road user, and reading in automatically detected position data of the road user in the traffic area. In addition, the method includes a step of associating in each case at least one annotation data set with the traffic area data at which the road user is situated at the moment, corresponding to the detected position data, in order to obtain the annotated traffic area data that signal a use option and/or movement option of the traffic area, represented by the traffic area data, by another road user, in particular the annotation data set having been generated using a machine learning method and/or a classifier based on a machine learning algorithm.
    Type: Application
    Filed: October 9, 2020
    Publication date: April 29, 2021
    Inventor: Jens Eric Markus Mehnert
  • Publication number: 20210081668
    Abstract: A method and a system for improved object marking in sensor data, as the result of which an at least partially automated annotation of objects or object classes in a recorded data set is possible. The method provides that a scene is detected in a first state by at least one sensor. An association of a first object marking with at least one object contained in the scene in a first data set containing the scene in the first state then takes place. The similar or matching scene is subsequently detected in a second state that is different from the first state by the at least one sensor, and an at least partial acceptance of the first object marking, contained in the first data set, for the object recognized in the second state of the scene as a second object marking in a second data set takes place.
    Type: Application
    Filed: September 3, 2019
    Publication date: March 18, 2021
    Inventor: Jens Eric Markus Mehnert
  • Publication number: 20210078168
    Abstract: A method for generating a training data set for training an artificial intelligence (AI) module. An image sequence is provided in which surroundings of a robot are recorded. A trajectory in the recorded surroundings is determined. At least one future image sequence is generated which extends to a time segment in the future, and, based on the at least one determined trajectory, encompasses a prediction of images for the event that the determined trajectory was followed during the time segment in the future. At least one sub-section of the determined trajectory in the generated image sequence is assessed as positive or as negative when a movement predicted by following the trajectory corresponds to a valid movement situation, or as an invalid movement situation, respectively. The generated future image sequence with the assessment assigned thereto of the trajectory are combined for generating a training data set for the AI module.
    Type: Application
    Filed: March 7, 2019
    Publication date: March 18, 2021
    Inventor: Jens Eric Markus Mehnert
  • Publication number: 20200394519
    Abstract: A method for operating an artificial neural network is provided, including at least one convolution layer that is configured to convert an input matrix of the convolution layer into an output matrix, based on a convolution operation and a shift operation. The method includes ascertaining at least one first normalization value and one second normalization value based on inputs of the input matrix and/or based on a training data set, ascertaining a modified filter matrix based on an original filter matrix and based on at least one of the first normalization value and the second normalization value, and ascertaining a modified shift matrix based on an original shift matrix and based on at least one of the first normalization value and the second normalization value. The method further includes converting the input matrix into the output matrix by applying the modified filter matrix and the modified shift matrix.
    Type: Application
    Filed: January 3, 2019
    Publication date: December 17, 2020
    Inventors: Pia Petrizio, Jens Eric Markus Mehnert, Rolf Michael Koehler
  • Publication number: 20200160530
    Abstract: A system includes a K1 preprocessing module designed to generate at least one intermediate image from an input image using a parameterized internal processing chain and an analysis module to detect a feature or object in the intermediate image. A method to train the system includes feeding a plurality of learning input images to the system, comparing a result provided by the analysis module for each of the learning input images to a learning value, and feeding back a deviation obtained by the comparison to an input preprocessing module and/or adapting parameters of the internal processing chain to reduce the deviation.
    Type: Application
    Filed: June 11, 2018
    Publication date: May 21, 2020
    Inventors: Jens Eric Markus Mehnert, Stefan Bischoff, Stephan Lenor
  • Publication number: 20190108435
    Abstract: The present invention describes a method for classifying an object having the following steps: receiving at least one item of distance information of an object based on a first electromagnetic signal transmitted by a transmitter device and a first electromagnetic signal received by a receiver device; receiving at least one item of oscillation information of the object based on a second electromagnetic signal transmitted by a transmitter device and a second electromagnetic signal received by a receiver device, which represents a solid oscillation of at least one subsection of the object; classifying the object based on the received information.
    Type: Application
    Filed: October 4, 2018
    Publication date: April 11, 2019
    Inventor: Jens Eric Markus Mehnert