Abstract: In various examples, a stitched image may be generated from overlapping image frames using a dynamic seam placement that depends on scene content and/or other factors. Since an optimized seam placement may jump from a previous location from time slice to time slice, one or more constraints may be applied to limit the movement of dynamically placed seams such that any given seam moves gradually over time, limiting potential discontinuities in a visualization of the stitched image on a display. Eye tracking may be used to detect a saccade of a monitored person and/or detect that the monitored person is not looking at the display, and one or more of the constraints used to limit the movement of dynamically placed seams may be relaxed or lifted when the monitored person is experiencing a saccade and/or is looking away from the display.

Abstract: In various examples, a sensor model may be learned to predict virtual sensor data for a given scene configuration. For example, a sensor model may include a deep neural network that supports generative learning—such as a generative adversarial network (GAN). The sensor model may accept an encoded representation of a scene configuration as an input using any number of data structures and/or channels (e.g., concatenated vectors, matrices, tensors, images, etc.), and may output virtual sensor data. Real-world data and/or virtual data may be collected and used to derive training data, which may be used to train the sensor model to predict virtual sensor data for a given scene configuration. As such, one or more sensor models may be used as virtual sensors in any of a variety of applications, such as in a simulated environment to test features and/or functionality of one or more autonomous or semi-autonomous driving software stacks.

Abstract: A system for generating at least a second trajectory for a first route section of a road comprises a first interface for receiving first data representing at least a first trajectory. The first data were recorded during travel on the first route section by at least one vehicle controlled by a human driver. The first interface is additionally configured to receive second data representing ambient conditions at the time of recording of the first trajectory, and to receive third data representing vehicle-related features present during the recording of the first trajectory. The system additionally comprises a first data processing module that performs clustering of multiple first trajectories based on associated second data and/or third data, a database for retrievably storing the results of the clustering, and a second interface for receiving a request for the transmission of a second trajectory and for corresponding transmission of the requested second trajectory.

Abstract: A system for generating map information for one or more road sections of a digital road map comprises an interface for receiving data records for the one or more road sections. The data records describe properties of surfaces outside the immediate road area. The system further comprises a first module for evaluating the received data records in order to identify first surfaces outside the immediate road area that are able to be driven on by a vehicle after leaving the road and on which the vehicle can be brought to a standstill after leaving the road, a second module for generating a description of the first surfaces in a format suitable for digital road maps, and a third module for retrievably providing the description of the first surfaces in one or more formats suitable for digital road maps.

Abstract: In various examples, a sensor model may be learned to predict virtual sensor data for a given scene configuration. For example, a sensor model may include a deep neural network that supports generative learning—such as a generative adversarial network (GAN). The sensor model may accept an encoded representation of a scene configuration as an input using any number of data structures and/or channels (e.g., concatenated vectors, matrices, tensors, images, etc.), and may output virtual sensor data. Real-world data and/or virtual data may be collected and used to derive training data, which may be used to train the sensor model to predict virtual sensor data for a given scene configuration. As such, one or more sensor models may be used as virtual sensors in any of a variety of applications, such as in a simulated environment to test features and/or functionality of one or more autonomous or semi-autonomous driving software stacks.

Abstract: A system for generating map information for one or more road sections of a digital road map comprises an interface for receiving data records for the one or more road sections. The data records describe properties of surfaces outside the immediate road area. The system further comprises a first module for evaluating the received data records in order to identify first surfaces outside the immediate road area that are able to be driven on by a vehicle after leaving the road and on which the vehicle can be brought to a standstill after leaving the road, a second module for generating a description of the first surfaces in a format suitable for digital road maps, and a third module for retrievably providing the description of the first surfaces in one or more formats suitable for digital road maps.

Abstract: A method for creating a digital road model for at least one road section includes: receiving and storing at least one trajectory of a vehicle for the at least one road section; receiving at least one image showing at least parts of the road section, the image having a perspective corresponding to an image recorded vertically downward from an elevated position; superimposing the at least one image on the at least one trajectory to correspond the trajectory to the course of a road in the at least one image; analyzing the at least one image in a corridor extending along and enclosing the trajectory to identify driving-relevant or positioning-relevant features of the road section in the corridor; and generating the digital road model from the identified features, aligned on the basis of the at least one trajectory and in the corridor enclosing the trajectory.

Abstract: The invention relates to a method for operating an assistance system of a motor vehicle. An image is detected by means of a camera of the assistance system and a traffic sign is determined within the detected image. An alignment of the determined traffic sign is determined with respect to the motor vehicle, and a signal device of the assistance system is triggered by the alignment.

Abstract: A system for generating at least a second trajectory for a first route section of a road comprises a first interface for receiving first data representing at least a first trajectory. The first data were recorded during travel on the first route section by at least one vehicle controlled by a human driver. The first interface is additionally configured to receive second data representing ambient conditions at the time of recording of the first trajectory, and to receive third data representing vehicle-related features present during the recording of the first trajectory. The system additionally comprises a first data processing module that performs clustering of multiple first trajectories based on associated second data and/or third data, a database for retrievably storing the results of the clustering, and a second interface for receiving a request for the transmission of a second trajectory and for corresponding transmission of the requested second trajectory.

Abstract: A method and device for determining an anomalous driving pattern of a neighboring vehicle using a vehicle camera and/or other sensor is described. Image data is received and if suitable lane markings are detected, a reference trajectory is derived from the detected lane markers. Otherwise, a reference trajectory is derived from a motion of the present vehicle. A trajectory of the neighboring vehicle is determined, characteristic parameters of the detected trajectory are derived, and the characteristic parameters are compared with predetermined trajectory data. Based on the comparison it is determined if the trajectory of the neighboring vehicle is an anomalous trajectory and in one case an alert signal is generated.

Abstract: In a method for detecting light sources operated in pulsed mode using a camera, the camera records a series of images, and the time interval between two successive recordings of individual images is varied while the series of images is recorded.

Abstract: The invention relates to a method and a device for recognizing a road sign (Hz, Zz) by means of a camera from a traveling vehicle. The method has the following steps: acquiring at least one image of the surroundings of a vehicle by means of the camera, determining the presence of at least one road sign (Hz, Zz) in the at least one acquired image of the surroundings of the vehicle, determining (also estimating) motion blur in that image segment in which the present road sign (Hz, Zz) is situated, subtracting out motion blur in this image segment, which results in a sharpened image segment, and recognizing the road sign (Hz, Zz) while taking account of the sharpened image segment.

Abstract: The invention relates to a method for operating an assistance system of a motor vehicle. An image is detected by means of a camera of the assistance system and a traffic sign is determined within the detected image. An alignment of the determined traffic sign is determined with respect to the motor vehicle, and a signal device of the assistance system is triggered by the alignment.

Abstract: The invention relates to a method and a device for recognizing a road sign (Hz, Zz) by means of a camera from a traveling vehicle. The method has the following steps: acquiring at least one image of the surroundings of a vehicle by means of the camera, determining the presence of at least one road sign (Hz, Zz) in the at least one acquired image of the surroundings of the vehicle, determining (also estimating) motion blur in that image segment in which the present road sign (Hz, Zz) is situated, subtracting out motion blur in this image segment, which results in a sharpened image segment, and recognizing the road sign (Hz, Zz) while taking account of the sharpened image segment.

Abstract: A method combines a road sign recognition system and a lane detection system of a motor vehicle. The road sign recognition system generates road sign information from sensor data of a camera-based or video-based sensor system and the lane detection system generates lane course information from the sensor data. Meaning-indicating data for road signs are generated from the lane course information, and are used to check the plausibility of and/or to interpret the road sign information. Data indicating the course of the lane are generated from the road sign information, and are used to check the plausibility of and/or to interpret the lane course information.

Abstract: This invention relates to a method for detecting light sources operated in pulsed mode using a camera. For this purpose, the camera takes a series of images, wherein the time interval between two subsequent takes of individual images is varied while the series of images is taken.

Abstract: To support a driver in guiding a road vehicle, the lane markings of the road, traffic signs and/or vehicle license plates are detected by an environment sensor system, which produces corresponding image data, which is evaluated by an image evaluation system by comparison to stored country-specific data. From that evaluation, at least one country estimation signal is generated in an image processor, and then a country signal indicating the current location of the vehicle is generated from the at least one country estimation signal by a microprocessor. The country signal correspondingly activates a driver information device outputting country-specific information for guidance of the vehicle and/or the country signal is fed to a driver assistance system that supports the guidance of the vehicle.

Abstract: The invention relates to a method for combining a road sign recognition system (1) and a lane detection system (2) of a motor vehicle, wherein the road sign recognition system (1) generates road sign information from sensor data of a camera-based or video-based sensor system (4) and the lane detection system (2) generates lane course information from said sensor data; according to the invention, meaning-indicating data for road signs are generated from the lane course information, the meaning-indicating data for road signs are used to check the plausibility of and/or to interpret the road sign information, data indicating the course of the lane are generated from the road sign information, and the data indicating the course of the lane are used to check the plausibility of and/or to interpret the lane course information.

Abstract: The invention relates to a method for supporting the driver of a road-bound vehicle in guiding the vehicle, in which the vehicle environment, in particular the markings that delimit the lanes of a road and traffic signs, are detected by means of an environment sensor system (1) and evaluated by means of an image evaluation system.

Abstract: Method of purifying sugar juice which has been prepared by extraction of a sugar beet material comprising mechanically separating undissolved components, chemically treating the juice to convert low molecular non-sugars into higher molecular compounds and to convert non-soluble compounds into soluble compounds and ultrafiltering the sugar juice thus obtained to separate high molecular components therefrom, thus obtaining a purified sugar juice which is suitable for the manufacture of crystalline sugar of a higher quality than conventionally purified sugar juice.