Various embodiments include a method for operating a camera-monitor system for a motor vehicle, wherein the camera-monitor system has a side camera assigned to a longitudinal side of the motor vehicle to provide an image of surroundings of the motor vehicle. The method may include: specifying a region of interest in the surroundings; and transforming the image of the camera into a transformed image wherein the region of interest in the transformed image is arranged in a specified image region with a specified magnification independent of any change in relative position between the region of interest and the motor vehicle.

The present invention is directed to a visualisation aid for indicating to a driver of a vehicle a projected location of a front wheel (90A, 90B) of the vehicle on a ground surface, the visualisation aid including an indicator (10A, 10B), wherein: the indicator is positionable in the line of sight (5A, 5B) of the driver looking out of the vehicle at the ground surface, the indicator is positionable at or above a boundary (140) of the vehicle in the light of sight, and the line of sight (5A, 5B) beyond the boundary of the vehicle intersects with an imaginary vertical plane (7A, 7B) extending forward from the front wheel of the vehicle (90A, 90B).

A monitoring device for a vehicle that, in a case in which it is determined, based on information captured by a towing information capture device, that the vehicle is not towing another vehicle, provides support for monitoring an area to a rear of the vehicle using images captured by a first capture device, and in a case in which it is determined, based on the information captured by the towing information capture device, that the vehicle is towing another vehicle, provides support for monitoring the area to the rear of the vehicle using images captured by a second capture device.

A capturing device includes an image sensor that generates an image signal by performing photoelectric conversion for light from a subject, a control unit that generates a setting value for setting a range where an image resulting from the image signal is cut, based on a first instruction input from a user, a setting value storage unit that stores the setting value generated by the control unit, an image conversion unit that reads the setting value from the setting value storage unit, and cuts a specific region specified by the setting value from the image and enlarges the cut region, when there is a second instruction input from the user, and an output unit that converts a signal of the image cut and enlarged by the image conversion unit into an image signal of a predetermined format and outputs the converted image signal.

A vehicular trailer angle detection system includes a rear camera, a left-side camera, a right-side camera and a control having an image processor. With a trailer hitched at a vehicle, and while the vehicle is driven in a forward direction and towing the trailer, image data is captured by at least one of the cameras. The vehicular trailer angle detection system determines an expected location of the portion of the trailer based on provided vehicle-trailer parameters as the vehicle is driven forward and towing the trailer. The vehicular trailer angle detection system determines an actual location of the portion of the trailer via processing of captured image data as the vehicle is driven forward and towing the trailer. Responsive to an offset between the determined actual location of the portion of the trailer and the determined expected location, the vehicular trailer angle detection system accommodates the offset.

A mirror adjustment assistance system for trucks having as part of a vehicle body at least a cabin (3) having a front side with respect to an intended main direction of travel, a driver side, and a co-driver side. At least three adjustable mirrors (5, 7, 9, 11, 13, 19) are attached to an exterior of the vehicle body or cabin (3), each of the at least three adjustable mirrors (5, 7, 9, 11, 13, 19) has an aiming marker (43, 45, 59, 61, 65, 69) on or adjacent its reflective surface. At least two vehicle body target markers (41, 57, 63, 67) are positioned on an exterior surface of the vehicle body (3), and at least a single one (41; 57) of the at least two vehicle body target markers is associated with two of the at least three mirrors (5, 9; 7, 11). Any aiming marker (43, 45, 59, 61, 65, 69) of the at least three adjustable mirrors (5, 7, 9, 11, 13, 19) can only be aligned with a single one of the at least two vehicle body target markers (41, 57, 63, 67).

A crane creates a 3D map on the basis of three-dimensional information acquired by a three-dimensional information obtaining section that is provided on a boom. The three-dimensional information obtaining section: is configured to be capable of accumulating acquired three-dimensional information and to be capable of changing a measurement direction, a measurement range, and a measurement density; and creates the 3D map by superimposing accumulated three-dimensional information. When an operation signal for a swivel operation for a swivel base, a hoisting operation for the boom, or an extension/retraction operation for the boom has been detected, on the basis of the movement direction and movement speed of the boom as calculated from a detected value for the operation signal, the three-dimensional information obtaining section: changes the measurement direction; and narrows the measurement range and increases the measurement density as compared to when the operation signal has not been detected.

A trailering assist system includes a control and a camera disposed at a rear portion of a vehicle and having a field of view at least rearward of the vehicle. The control includes an image processor operable to process image data captured by the camera. The control, responsive to image processing of captured image data, transforms captured image data of the trailer hitch from a pivoting orientation of the portion of the trailer that pivots about the trailer hitch to a vertical orientation of the portion of the trailer that moves laterally across the transformed image data. The control transforms pivotal movement of the portion of the trailer about the trailer hitch to lateral movement of the trailer hitch in the transformed image data. The control determines a trailer angle of the trailer relative to the vehicle based on the lateral position of the trailer hitch in the transformed image data.

A computer is programmed to determine a training dataset that includes a plurality of images each including a first object and an object label, train a first machine learning program to identify first object parameters of the first objects in the plurality of images based on the object labels and a confidence level based on a standard deviation of a distribution of a plurality of identifications of the first object parameters, receive, from a second machine learning program, a plurality of second images each including a second object identified with a low confidence level, process the plurality of second images with the first machine learning program to identify the second object parameters with a corresponding second confidence level that is greater than a second confidence level, retrain the first machine learning program based on the identified second object parameters.

The described techniques relate to predicting object behavior based on top-down representations of an environment comprising top-down representations of image features in the environment. For example, a top-down representation may comprise a multi-channel image that includes semantic map information along with additional information for a target object and/or other objects in an environment. A top-down image feature representation may also be a multi-channel image that incorporates various tensors for different image features with channels of the multi-channel image, and may be generated directly from an input image. A prediction component can generate predictions of object behavior based at least in part on the top-down image feature representation, and in some cases, can generate predictions based on the top-down image feature representation together with the additional top-down representation.