Abstract: The present disclosure relates to method and system for global localization using a combination of visual odometry and optimization approaches in order to map a vehicle trajectory to an offline map with a-priori knowledge of at least two observed streets in order to reduce the optimization parameter space from three dimensions to one dimensions compared to standard iterative closest point methods.

Abstract: A localization device for visually determining the location of a vehicle includes a camera unit for capturing image data and a control unit. The control unit is configured to recognize at least one landmark in the captured image data and to determine a quality value for each landmark. The determination of the quality value involves multiple recognitions of the particular landmark. In addition, multiple quality values for one landmark can be determined for different observation positions or observation directions. The control unit is further configured to adjust the quality value of a landmark already contained in a map, based on a new recognition by the localization device. The control unit is configured to determine the position of the localization device based on the recognized landmarks in conjunction with the map. The control unit is further configured to determine the position of landmarks in relation to a global coordinate system.

Abstract: A method and a device for evaluating image data of a vehicle camera, involves: a) recording a first image by the vehicle camera, b) recording a subsequent second image by the vehicle camera, c) extracting multiple correspondent features in the first and second images, d) assuming a motion of the vehicle camera (motion hypothesis) between the recordings of the first image and the second image, e) determining a reprojection error of an extracted feature, which indicates the difference between the flow measured from the feature extracted in the first and second images and the flow calculated from the motion hypothesis, and f) establishing outliers, wherein an extracted feature is established as an outlier if the reprojection error of this feature reaches or exceeds a threshold, wherein the threshold is not constant within an iteration that includes at least steps b) to g). This offers an improved detection and removal of outliers to estimate the motion of the vehicle camera.

Abstract: The present disclosure relates to method and system for global localization using a combination of visual odometry and optimization approaches in order to map a vehicle trajectory to an offline map with a-priori knowledge of at least two observed streets in order to reduce the optimization parameter space from three dimensions to one dimensions compared to standard iterative closest point methods.

Abstract: A method and a device for evaluating image data of a vehicle camera, involves: a) recording a first image by the vehicle camera, b) recording a subsequent second image by the vehicle camera, c) extracting multiple correspondent features in the first and second images, d) assuming a motion of the vehicle camera (motion hypothesis) between the recordings of the first image and the second image, e) determining a reprojection error of an extracted feature, which indicates the difference between the flow measured from the feature extracted in the first and second images and the flow calculated from the motion hypothesis, and f) establishing outliers, wherein an extracted feature is established as an outlier if the reprojection error of this feature reaches or exceeds a threshold, wherein the threshold is not constant within an iteration that includes at least steps b) to g). This offers an improved detection and removal of outliers to estimate the motion of the vehicle camera.

Abstract: Estimating the dynamic states of a real-world object over time using a camera, two dimensional (2D) image information and a combination of different measurements of the distance between the object and the camera. The 2D image information is used to track a 2D position of the object as well as its 2D size of the appearance and change in the 2D size of the appearance of the object. In addition, the distance between the object and the camera is obtained from one or more direct depth measurements. The 2D position, the 2D size, and the depth of the object are coupled to obtain an improved estimation of three dimensional (3D) position and 3D velocity of the object. The object tracking apparatus uses the improved estimation to track real-world objects. The object tracking apparatus may be used on a moving platform such as a robot or a car with mounted cameras for a dynamic visual scene analysis.

Abstract: The invention relates to a method for detecting the proper motion of an real-world object, comprising the steps of acquiring, by an image capturing device (ICD), a first image (I1) of the object at a first point in time (t1) and a second image (I2) at a second point in time (t2); obtaining a third (hypothetical) image (I3), based on an estimated effect of the motion of the image capturing device (ICD) itself (EMF) between the first and the second point in time (t1, t2), wherein the effect of the motion of the image capturing device (ICD) itself is estimated based on the forward kinematics of the image capturing device; determining an optical flow (OF) between the second image (I2) and the third image (I3); and evaluating the optical flow (OF) by incorporating uncertainties of the optical flow (OF) and the ego-motion-flow (EMF) in order to determine the proper motion of the object.

Abstract: The invention relates to a method for detecting the proper motion of an real-world object, comprising the steps of acquiring, by an image capturing device (ICD), a first image (I1) of the object at a first point in time (t1) and a second image (I2) at a second point in time (t2); obtaining a third (hypothetical) image (I3), based on an estimated effect of the motion of the image capturing device (ICD) itself (EMF) between the first and the second point in time (t1, t2), wherein the effect of the motion of the image capturing device (ICD) itself is estimated based on the forward kinematics of the image capturing device; determining an optical flow (OF) between the second image (I2) and the third image (I3); and evaluating the optical flow (OF) by incorporating uncertainties of the optical flow (OF) and the ego-motion-flow (EMF) in order to determine the proper motion of the object.

Abstract: Techniques are disclosed for sound source localization based on joint learning and evaluation of ITD and ILD representations that are measured in a complementary, correlation-based way using binaural time-frequency spectrums. According to one embodiment, from these measurements and learned representatives, which may, for example, be created by combinations of measurements from signals belonging to the same class, i.e., the same azimuthal location, probability distributions over frequency and class are computed. These probability distributions can be combined over cue and frequency using information-theoretic approaches to get a robust classification of the location and additionally a confidence measure for the quality of the classification result.

Abstract: Estimating the dynamic states of a real-world object over time using a camera, two dimensional (2D) image information and a combination of different measurements of the distance between the object and the camera. The 2D image information is used to track a 2D position of the object as well as its 2D size of the appearance and change in the 2D size of the appearance of the object. In addition, the distance between the object and the camera is obtained from one or more direct depth measurements. The 2D position, the 2D size, and the depth of the object are coupled to obtain an improved estimation of three dimensional (3D) position and 3D velocity of the object. The object tracking apparatus uses the improved estimation to track real-world objects. The object tracking apparatus may be used on a moving platform such as a robot or a car with mounted cameras for a dynamic visual scene analysis.

Abstract: Techniques are disclosed for sound source localization based on joint learning and evaluation of ITD and ILD representations that are measured in a complementary, correlation-based way using binaural time-frequency spectrums. According to one embodiment, from these measurements and learned representatives, which may, for example, be created by combinations of measurements from signals belonging to the same class, i.e., the same azimuthal location, probability distributions over frequency and class are computed. These probability distributions can be combined over cue and frequency using information-theoretic approaches to get a robust classification of the location and additionally a confidence measure for the quality of the classification result.