Abstract: The invention relates to a method for generating and/or updating a digital model of at least one sub-region of a digital map, said digital model being assembled from sections originating from different sources. First data are provided relating to a first section and comprising objects and/or feature points characterized at least by their spatial position, said objects and/or feature points being classifiable into a plurality of degrees of detail. Second data are then provided, relating to a second section and comprising objects and/or feature points characterized at least by their spatial position, said objects and/or feature points being classifiable into the plurality of degrees of detail. The first section and the second sections partially overlap.

Abstract: Various embodiments of the teachings herein include a method for training and updating a backend-side classifier comprising: receiving, in a backend-device, from at least one vehicle, classification data along with a respective classification result generated by a vehicle-side classifier; and training the backend-side classifier using the classification data and, if available, a corrected respective classification result as annotation.

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 a device for increasing the accuracy of localization. The method includes the following steps: a) detecting a selected object in an environment, using a camera of a first vehicle; b) estimating a first position of the selected object, wherein a first program uses first location coordinates of the first vehicle and a first distance estimate to the selected object; c) transferring an attribute of the selected object, the first location coordinates and the first distance estimate to a server; d) carrying out the steps a) to c) for a second vehicle; e) calculating a third position of the selected object by the server, wherein a third program performs an averaging of the plurality of location coordinates and distance estimates; f) using the third position of the selected object as a reference position for increasing the accuracy of a localization of a third vehicle.

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: Various embodiments of the teachings herein include a method for training and updating a backend-side classifier comprising: receiving, in a backend-device, from at least one vehicle, classification data along with a respective classification result generated by a vehicle-side classifier; and training the backend-side classifier using the classification data and, if available, a corrected respective classification result as annotation.

Abstract: A system for generating confidence values for objects in a digital road map comprising a backend and an object recognition device including: a capture unit, an evaluation unit, a positioning unit, and a transceiver. The capture unit captures surroundings data of a vehicle. The positioning unit determines a position of the captured surroundings data and objects contained therein. The evaluation unit recognizes the objects and concealed objects based on the surroundings data and associates them with position information. The transceiver transmits information generated by the evaluation unit to the backend. The backend generates or updates the map. Each of the objects in the map has an associated confidence value. The backend adjusts the confidence values based on the received data. The backend does not reduce the confidence value of an object if there is a corresponding concealed object in the received data.

Abstract: The invention relates to a method for generating and/or updating a digital model of at least one sub-region of a digital map, said digital model being assembled from sections originating from different sources. First data are provided relating to a first section and comprising objects and/or feature points characterized at least by their spatial position, said objects and/or feature points being classifiable into a plurality of degrees of detail. Second data are then provided, relating to a second section and comprising objects and/or feature points characterized at least by their spatial position, said objects and/or feature points being classifiable into the plurality of degrees of detail. The first section and the second sections partially overlap.

Abstract: A method and a device for increasing the accuracy of localization. The method includes the following steps: a) detecting a selected object in an environment, using a camera of a first vehicle; b) estimating a first position of the selected object, wherein a first program uses first location coordinates of the first vehicle and a first distance estimate to the selected object; c) transferring an attribute of the selected object, the first location coordinates and the first distance estimate to a server; d) carrying out the steps a) to c) for a second vehicle; e) calculating a third position of the selected object by the server, wherein a third program performs an averaging of the plurality of location coordinates and distance estimates; f) using the third position of the selected object as a reference position for increasing the accuracy of a localization of a third vehicle.

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: 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 for automatic spatial calibration of a network of cameras along a road includes, processing a frame that is obtained from each camera of the network to automatically identify an image of a pattern of road markings that have a known spatial relationship to one another. The identified images are used to calculate a position of each camera relative to the pattern of road markings that is imaged by that camera. Geographical information is applied to calculate an absolute position of a field of view of each camera. A global optimization is applied to adjust the absolute position of the field of view of each camera of the camera network relative to an absolute position of the fields of view of other cameras of the camera network.

Abstract: In queues, persons—or objects (120) in general—move inside an area (110) to a target (112), such as to a counter. The queue has movement characteristics in terms of speed, waiting times and queue form. A computer-implemented approach obtains the characteristics by receiving a sequence (140) of image frames (141, 142, 143, 49) that represent the surveillance area (110); calculating flow vectors that indicate an optical displacement for the sequence (140) of image frames (141/142, 142/143); extending one of the flow vectors as lead vector in extension directions; determining intermediate vectors by using flow vectors along the extension directions; and selecting one the intermediate vectors as the new lead vector. The steps are repeated to concatenate the lead vectors to the movement characteristics (190).

Abstract: Apparatus and method for extracting a background model from a video stream of frames. Each frame is divided into a rectangular array of blocks, and a block descriptor of each block is compared with the previous frame's corresponding block descriptor. When a block descriptor is substantially the same as the corresponding block descriptor of the preceding frame for at least a predetermined number of frames, then the background model is updated according to the block descriptor.

Abstract: The invention provides methods and systems for reliably detecting objects in a received video stream from a camera. Objects are selected and a bound around selected objects is calculated and displayed. Bounded objects can be tracked. Bounding is performed by using Histogram of Oriented Gradients and linear Support Vector Machine classifiers.

Abstract: A method for automatic spatial calibration of a network of cameras along a road includes, processing a frame that is obtained from each camera of the network to automatically identify an image of a pattern of road markings that have a known spatial relationship to one another. The identified images are used to calculate a position of each camera relative to the pattern of road markings that is imaged by that camera. Geographical information is applied to calculate an absolute position of a field of view of each camera.

Abstract: A computer implemented method for selecting at least one sensor from a plurality of sensors (130, 132, 134), wherein the at least one sensor is adapted to record sensor-data that is related to a geographical area (110, 112), wherein the sensor-data comprises information about objects (537) movable between locations (A, B, C, D, E, F) of that geographical area (110, 112), wherein a data structure (120, 121, 122, 123) with a pre-processed graph represents the geographical area (110, 112), the pre-processed graph having elements comprising nodes and edges, wherein nodes (a, b, c, d, e, f) represent the locations (A, B, C, D, E, F) of the geographical area (110, 112), wherein edges represent transition times (140) for the objects (537) if moving between the locations (A, B, C, D, E, F), and wherein the pre-processed graph has a simplified number of nodes (a, b, c, d, e, f) according to rules applied to the elements, the method comprising: receiving an event (135) indicator in relation to a particular location (B)

Abstract: In queues, persons—or objects (120) in general—move inside an area (110) to a target (112), such as to a counter. The queue has movement characteristics in terms of speed, waiting times and queue form. A computer-implemented approach obtains the characteristics by receiving a sequence (140) of image frames (141, 142, 143, 49) that represent the surveillance area (110); calculating flow vectors that indicate an optical displacement for the sequence (140) of image frames (141/142, 142/143); extending one of the flow vectors as lead vector in extension directions; determining intermediate vectors by using flow vectors along the extension directions; and selecting one the intermediate vectors as the new lead vector. The steps are repeated to concatenate the lead vectors to the movement characteristics (190).