A monitoring system that monitors periphery of a shovel moving on ground and reports a tumble risk of the periphery of the shovel to an operator includes: a risk determination unit configured to determine a tumble risk in a case of movement of the shovel to the periphery based on distance information measured by a first sensor that is mounted on the shovel and measures a distance to a ground object including the ground in the periphery of the shovel and slope information measured by a second sensor measuring a slope of the shovel; and a display video generation unit configured to generate and output an image indicating the tumble risk determined by the risk determination unit.

A system on a chip (SoC) includes a digital signal processor (DSP) and a graphics processing unit (GPU) coupled to the DSP. The DSP is configured to receive a stream of received depth measurements and generate a virtual bowl surface based on the stream of received depth measurements. The DSP is also configured to generate a bowl to physical camera mapping based on the virtual bowl surface. The GPU is configured to receive a first texture and receive a second texture. The GPU is also configured to perform physical camera to virtual camera transformation on the first texture and on the second texture, based on the bowl to physical camera mapping, to generate an output image.

A safety system for a load carrying machine including: a controller, a location sensing arrangement in electronic communication with the processor, the location sensing arrangement configured to determine a location parameter of a load, a monitoring arrangement, the controller configured to receive the location parameter and determine a projected area of the load and control the monitoring arrangement to focus on the projected area to monitor the projected area.

Aspects of the present invention relate to a driver assistance system for a towing vehicle coupled to a towed vehicle. The driver assistance system includes a controller. The driver assistance system is configured to receive first image data from a towed vehicle imaging device disposed on the towed vehicle. The first image data represents a first scene behind the towed vehicle. The first image data is processed to identify object image data representative of one or more objects of interest in the first scene. An object distance is determined from a reference point to the or each object of interest identified in the first scene. A signal indicative of the object distance is output by the driver assistance system. Aspects of the present invention also relate to a vehicle including a driver assistance system; a method of assisting a driver; computer software; and a computer readable medium.

A non-contact operating apparatus, for a vehicle, includes a generating unit, a projecting device, a detecting device, a stimulation output device, a determining unit, and a stimulation response output unit. The generating unit is configured to generate and update image containing an image object. The projecting device is configured to project the image in a predetermined display region. The detecting device is configured to detect an operation site of an occupant positioned in a vicinity of the predetermined display region. The stimulation output device is configured to output and update a tactile stimulation to the operation site. The determining unit is configured to determine whether the operation site performs a non-contact operation against the image object. The stimulation response output unit is configured to cause the stimulation output device to output the tactile stimulation to the operation site on the basis of a determination result.

A system on a chip (SoC) includes a digital signal processor (DSP) and a graphics processing unit (GPU) coupled to the DSP. The DSP is configured to receive a stream of received depth measurements and generate a virtual bowl surface based on the stream of received depth measurements. The DSP is also configured to generate a bowl to physical camera mapping based on the virtual bowl surface. The GPU is configured to receive a first texture and receive a second texture. The GPU is also configured to perform physical camera to virtual camera transformation on the first texture and on the second texture, based on the bowl to physical camera mapping, to generate an output image.

A method for ascertaining a spatial orientation of a trailer of an autonomously driving towing vehicle with trailer. The method includes the steps of reading in image data of at least one rear-facing camera, assigning image points of the image data to the trailer or to the vehicle surrounding environment, ascertaining a rear trailer edge or at least one point of the rear trailer contour from the image points assigned to the trailer, and determining the trailer angle as a function of image coordinates of the trailer edge or of the point, the dimensions of the trailer, and the position of the camera relative to the support point of the trailer.

A vehicle compound-eye camera includes: a plurality of cameras arranged to be spaced apart from each other in a predetermined direction and disposed such that respective maximum image-pickup ranges of the plurality of cameras are partially shifted from each other in the predetermined direction; and a processor configured to set an overlapping image-pickup range in which each of the plurality of cameras picks up an image of a same target object from a different viewpoint. The processor is configured to set an image-pickup range of one of the cameras disposed on one end in the predetermined direction to have a relatively wide angle. The processor is configured to set an image-pickup range of another of the cameras disposed on the other end in the predetermined direction to have a relatively narrow angle.

An image processing apparatus includes a first extractor, a first object identifier, a region defining unit, a second extractor, a selector, and a second object identifier. The first extractor extracts a first feature quantity included in a captured image. The first object identifier identifies an object on the basis of the first feature quantity. The region defining unit defines an image region in the captured image. The second extractor extracts a second feature quantity included in an image in the image region. The selector selects, on the basis of data related to the image region defined by the region defining unit, a part of the first feature quantity extracted by the first extractor. The second object identifier identifies the object on the basis of the second feature quantity and the part of the first feature quantity selected by the selector.

A method for enriching a target image, which a target camera system had recorded of a scene, with additional information, with which at least one source image that a source camera system had recorded of the same scene from a different perspective, has already been enriched. The method includes: assigning 3D locations in the three-dimensional space, which correspond to the positions of the source pixels in the source image, to source pixels of the source image; assigning additional information which is assigned to source pixels, to the respective, associated 3D locations; assigning those target pixels of the target image, whose positions in the target image correspond to the 3D locations, to the 3D locations; assigning additional information, which is assigned to 3D locations, to associated target pixels. A method for training a Kl module is also described.