Abstract: A method and a driver assistance system recognize the intention of a pedestrian to move on the basis of a sequence of images of a camera. The method includes detecting a pedestrian in at least one camera image. The method also includes selecting a camera image that is current at the time t and selecting a predefined selection pattern of previous camera images of the image sequence. The method further includes extracting the image region in which the pedestrian was detected in the selected camera images of the image sequence. The method also includes classifying the movement profile of the detected pedestrian on the basis of the plurality of extracted image regions. The method outputs the class that describes the movement intention determined from the camera images of the image sequence.

Abstract: The present disclosure relates to a method and system for recognizing road users, in particular persons in road traffic The method includes the following steps: recording at least one ambient image or a sequence of ambient images by means of an optical sensor of a vehicle, detecting a person in the ambient image, determining a pose of the detected person; determining a presence of a means of transport of the person; and assigning a movement profile to the person based on the determined means of transport of the person.

Abstract: A method and a driver assistance system recognize the intention of a pedestrian to move on the basis of a sequence of images of a camera. The method includes detecting a pedestrian in at least one camera image. The method also includes selecting a camera image that is current at the time t and selecting a predefined selection pattern of previous camera images of the image sequence. The method further includes extracting the image region in which the pedestrian was detected in the selected camera images of the image sequence. The method also includes classifying the movement profile of the detected pedestrian on the basis of the plurality of extracted image regions. The method outputs the class that describes the movement intention determined from the camera images of the image sequence.

Abstract: A method for autocalibration of a (monocular) vehicle camera has the following steps: a) acquiring from the vehicle camera (1), a series of images of a region of the surroundings in front of the vehicle, b) detecting a cornering maneuver (25) of the vehicle suitable for autocalibration, when the curve radius (21) described by the vehicle is less than or equal to a maximum radius and the traversed curve angle (22) is greater than or equal to a minimum angle, and c) performing autocalibration, when at least one cornering maneuver (25) has been identified as suitable for autocalibration, wherein the autocalibration takes account of movement of stationary objects in the surroundings of the vehicle in the image sequence or sequences of one or more cornering maneuvers (25) suitable for autocalibration. An autocalibration apparatus is also provided.

Abstract: The invention relates to a method and an apparatus for the autocalibration of a (monocular) vehicle camera (1). The method has the following steps: a) acquiring a series of images from the vehicle camera (1), wherein the vehicle camera maps a region of the surroundings in front of the vehicle, b) detecting a cornering maneuver (25) of the vehicle suitable for autocalibration, if the curve radius (21) described by the vehicle is less than or equal to a (defined or predetermined) maximum radius and the curve angle (22) covered is greater than or equal to a (defined or predetermined) minimum angle, c) performing autocalibration, if at least one cornering maneuver (25) has been identified as suitable for autocalibration, wherein d) the autocalibration takes account of movement of stationary objects in the surroundings of the vehicle in the image sequence or in the image sequences of one or more cornering maneuvers (25) suitable for autocalibration.