Abstract: A computer-implemented method for driving assistance in a vehicle. The method includes generating, based on radar point sensor data of an environment of the vehicle, a three-dimensional occupancy grid map (3D OGM). The method includes generating, based on the radar point sensor data, a number of feature grid maps (FGMs). A respective feature dimension of each of the FGMs corresponds to a feature of the radar point sensor data. The method includes generating, based on the 3D OGM and the number of FGMs, a refined occupancy grid (OGM). The method includes providing the refined OGM for usage by an assistance system of the vehicle.

Abstract: A method is provided for determining a pitch angle of a perception system of a vehicle with respect to a road surface on which the vehicle is located. Via the perception system, road perception information is detected from the road surface, and object perception information is detected from objects being different from the road surface. A primary pitch angle is determined by using the road perception information, and a relative pitch angle is determined by using the object perception information. The primary pitch angle and the relative pitch angle are combined in order to determine a final pitch angle of the perception system.

Abstract: A method is disclosed, which is carried out by a detection device having a transmitter element for transmitting wave signals and two vertically aligned receiver elements for receiving wave signals, separated by a given spacing. The method includes transmitting, at the transmitter element, a wave signal that is reflected by the target. Each receiver element receives the wave signal reflected by the target, where the wave signal propagates via multiple paths caused by the reflecting surface. While a target distance varies, a phase difference between the reflected wave signals received by the two receiver elements is measured. From the phase difference measurements, a physical quantity fluctuation is determined in relation to the target distance. The information on the target height is then derived from the physical quantity fluctuation.

Abstract: A computer implemented method for calibrating a motion sensor arranged at a vehicle and configured to output a raw motion measurement value indicative of a current motion condition of the vehicle comprises: computing processed motion measurement values by modifying the outputted raw motion measurement value based on a set of different calibration parameters, monitoring the vicinity of the vehicle by means of an environment perception sensor, determining a set of occupancy maps by means of mapping data acquired by the environment perception sensor in accordance with a motion model for the vehicle, wherein each of the processed motion measurement values is used to establish the motion model for one of the occupancy maps, and selecting, based on a comparison of the determined occupancy maps, one of the different calibration parameters for modifying subsequently outputted raw motion measurement values.

Abstract: A computer implemented method for estimating a height profile of a road around a vehicle, comprises the following steps carried out by computer hardware components: receiving radar responses captured by a radar sensor mounted on the vehicle; determining an elevation spectrum of the road around the vehicle based on the radar responses; and estimating the height profile based on the elevation spectrum.

Abstract: A method is provided for determining a mounting position of a radar sensor at a vehicle. The mounting position is defined with respect to a ground plane on which the vehicle is currently located. Radar responses captured by the radar sensor are received, wherein a field of view of the radar sensor covers at least a predefined area of the ground plane. A sequence of characteristics of the radar responses is determined, and the mounting position is determined by performing the operations of optimizing parameters of a predefined model with respect to the sequence of characteristics of the radar responses, and determining the mounting position based on the optimized parameters of the predefined model.

Abstract: This document describes systems and techniques for determining a height of an object in a surrounding of a vehicle. In a first aspect, the systems and techniques include acquiring radar data for each of a plurality of vertically distributed antenna elements of a radar antenna. In additional aspects, the systems and techniques include estimating an elevation spectrum from the acquired radar data, extracting one or more features representative of the shape of the estimated elevation spectrum, and determining the height of the object using the extracted one or more features.

Abstract: The present disclosure describes systems and techniques for estimating a height of an object by processing wave signals transmitted from a detection device to the object and reflected by the object. In aspects, a detection device transmits wave signals, which propagate via a direct path and an indirect path via reflection over a reflecting surface, to be reflected by the object. Operations include measuring wave signals reflected by the object and generating measurement vectors and producing a spectrum of an estimated elevation angle of the object over the range. Further, the operations include estimating the height of the object from the spectrum. The length of the window can be determined by estimating the range interval covered by a full phase cycle of a phase difference between the direct path and the indirect path from a current value of the range and a current estimate of the height of the object.

Abstract: A computer-implemented method for generating ground truth data may include the following steps carried out by computer hardware components: for a plurality of points in time, acquiring sensor data for a respective point in time; and for at least a subset of the plurality of points in time, determining ground truth data of the respective point in time based on the sensor data of at least one present and/or past point of time and at least one future point of time.

Abstract: The present disclosure describes systems and techniques for estimating a height of an object by processing wave signals transmitted from a detection device to the object and reflected by the object. In aspects, a detection device transmits wave signals, which propagate via a direct path and an indirect path via reflection over a reflecting surface, to be reflected by the object. Operations include measuring wave signals reflected by the object and generating measurement vectors and producing a spectrum of an estimated elevation angle of the object over the range. Further, the operations include estimating the height of the object from the spectrum. The length of the window can be determined by estimating the range interval covered by a full phase cycle of a phase difference between the direct path and the indirect path from a current value of the range and a current estimate of the height of the object.

Abstract: A method is disclosed, which is carried out by a detection device having a transmitter element for transmitting wave signals and two vertically aligned receiver elements for receiving wave signals, separated by a given spacing. The method includes transmitting, at the transmitter element, a wave signal that is reflected by the target. Each receiver element receives the wave signal reflected by the target, where the wave signal propagates via multiple paths caused by the reflecting surface. While a target distance varies, a phase difference between the reflected wave signals received by the two receiver elements is measured. From the phase difference measurements, a physical quantity fluctuation is determined in relation to the target distance. The information on the target height is then derived from the physical quantity fluctuation.

Abstract: An illustrative example embodiment of a computer implemented method for estimating a vertical profile of a road in front of or behind a host vehicle includes monitoring a detection point at a surrounding or preceding vehicle by a sensor on the host vehicle, determining at least one value for a height of the detection point with respect to a reference level at the host vehicle based on the elevation angle of the detection point, and estimating the vertical profile of the road based on the at least one value for the height of the detection point. An estimation of a height of the object with respect to a road surface may be corrected by the estimated vertical profile.

Abstract: An illustrative example embodiment of a computer implemented method for estimating a vertical profile of a road in front of or behind a host vehicle includes monitoring a detection point at a surrounding or preceding vehicle by a sensor on the host vehicle, determining at least one value for a height of the detection point with respect to a reference level at the host vehicle based on the elevation angle of the detection point, and estimating the vertical profile of the road based on the at least one value for the height of the detection point. An estimation of a height of the object with respect to a road surface may be corrected by the estimated vertical profile.

Abstract: A method of generating a confidence measure for an estimation derived from images captured by a camera mounted on a vehicle includes: capturing consecutive training images by the camera while the vehicle is moving; determining ground-truth data for the training images; computing optical flow vectors from the training images and estimating a first output signal based on the optical flow vectors for each of the training images, the first output signal indicating an orientation of the camera; classifying the first output signal for each of the training images as a correct signal or a false signal depending on how good the first output signal fits to the ground-truth data; determining optical flow field properties for each of the training images derived from the training images; and generating a separation function that separates the optical flow field properties into two classes based on the classification of the first output signal.

Abstract: A method of generating an occupancy map representing free and occupied space around a vehicle, wherein the occupancy map is divided into a plurality of cells Mx,y, the method includes: capturing two consecutive images by a camera mounted on the vehicle; generating optical flow vectors from the two consecutive images; estimating 3D points in the space around the vehicle from the optical flow vectors; generating rays from the camera to each of the estimated 3D points, wherein intersection points of the rays with the cells Mx,y defining further 3D points; determining for each of the cells Mx,y a function L_(x,y)^t for a time step t; and determining an occupancy probability from the function L_(x,y)^t for each of the cells Mx,y.

Abstract: A method of generating an occupancy map representing free and occupied space around a vehicle, wherein the occupancy map is divided into a plurality of cells Mx,y, the method includes: capturing two consecutive images by a camera mounted on the vehicle; generating optical flow vectors from the two consecutive images; estimating 3D points in the space around the vehicle from the optical flow vectors; generating rays from the camera to each of the estimated 3D points, wherein intersection points of the rays with the cells Mx,y defining further 3D points; determining for each of the cells Mx,y a function L_(x,y)?t for a time step t; and determining an occupancy probability from the function L_(x,y)?t for each of the cells Mx,y.

Abstract: A method of estimating an orientation of a camera relative to a surface includes providing a first image and a subsequent second image captured by the camera; selecting a first point from the first image and a second point from the second image, where the first and second points represent the same object; defining a first optical flow vector connecting the first point and the second point; carrying out a first estimation step comprising estimating two components of the normal vector in the camera coordinate system by using the first optical flow vector and restricting parameter space to only the two components of the normal vector, wherein a linear equation system derived from a homography matrix that represents a projective transformation between the first image and the second image is provided and the two components of the normal vector in the camera coordinate system are estimated by solving the linear equation system; and determining the orientation of the camera relative to the surface using the results

Abstract: A method of generating a confidence measure for an estimation derived from images captured by a camera mounted on a vehicle includes: capturing consecutive training images by the camera while the vehicle is moving; determining ground-truth data for the training images; computing optical flow vectors from the training images and estimating a first output signal based on the optical flow vectors for each of the training images, the first output signal indicating an orientation of the camera; classifying the first output signal for each of the training images as a correct signal or a false signal depending on how good the first output signal fits to the ground-truth data; determining optical flow field properties for each of the training images derived from the training images; and generating a separation function that separates the optical flow field properties into two classes based on the classification of the first output signal.

Abstract: A method of estimating an orientation of a camera relative to a surface includes providing a first image and a subsequent second image captured by the camera; selecting a first point from the first image and a second point from the second image, where the first and second points represent the same object; defining a first optical flow vector connecting the first point and the second point; carrying out a first estimation step comprising estimating two components of the normal vector in the camera coordinate system by using the first optical flow vector and restricting parameter space to only the two components of the normal vector, wherein a linear equation system derived from a homography matrix that represents a projective transformation between the first image and the second image is provided and the two components of the normal vector in the camera coordinate system are estimated by solving the linear equation system; and determining the orientation of the camera relative to the surface using the results