Robert Boschgmbh

Matthew Baran

James Stephen Miller

Rajen Bhatt

Frederic Marcel Sejalon

Naman Kumar

Rajani Janardhana

Stephen Miller

A camera system comprising a first video camera having a first field of vision, an orientation adjustment switch, a first display, and an electronic processor. The electronic processor is configured to receive, from the first video camera, a non-rectilinear image of the first field of vision and receive, from the orientation adjustment switch, input defining an axis of a second field of vision within the first field of vision. The electronic processor is also configured to apply a distortion correction method to the non-rectilinear image of the first field of vision to produce a rectilinear image of the first field of vision. The electronic processor is further configured to determine a rectilinear image of the second field of vision within the rectilinear image of the first field of vision, and display the rectilinear image of the second field of vision on the first display.

Virtual camera panning and tilting

An object detection system for used in a vehicle includes an object detector is provided. One or more fisheye lens cameras coupled to an object detection system are positioned at various location of the vehicle for capturing a field of view (FOV) into an image. The image is split into multiple different set of perspective images. Each perspective images may include a portion of overlap having common or identical object of interest. The object detector classifies various objects of interest in the perspective images, estimates distance of objects of interest from the vehicle using camera calibration information stored in one of the camera, and transmits the sensed information that corresponds to the distance of interest to a processor. The processor includes sequence of instruction or object code either located in one of the object detection system, in-vehicle network, and an electronic device processes the sensed information and applies bounding boxes around objects of interest the vehicle or in the electronic device. One or more images incorporated the colored bounding boxes are transmitted to a display unit or screen for display as human readable format.

Object detection system and method thereof

System and method of performing various transformations between an omnidirectional image model and a rectilinear image model for use in vehicle imaging systems. In particular, a panel transform system and method for transforming an omnidirectional image from an omnidirectional camera positioned on a vehicle to a rectilinear image. The rectilinear image is then displayed to the driver for use while performing vehicle maneuvers. The panel transform system and method also provide a rectilinear image model based on the omnidirectional camera for use with existing rectilinear imaging processing systems. The rectilinear image model is determined based on a variable set of input parameters that are defined by both automatic and manual system inputs such as a steering wheel angle sensor and a user interface.

Panel transform

A method and system of locating a position of an object with an omnidirectional camera affixed to a vehicle. An electronic control unit receives movement data of the vehicle from a vehicle communication bus. Simultaneously, the electronic control unit receives a plurality of omnidirectional image frames of a stationary object with the omnidirectional camera. Based on the received omnidirectional image frames, the electronic control unit identifies an object of interest in the omnidirectional image frames and tracks the object of interest in the omnidirectional image frames while the vehicle is moving. The electronic control unit determines a change in position of the object of interest in the omnidirectional image frames as the vehicle is moving and determines a distance to the object of interest based on the change of position of the vehicle and the change in position of the object of interest in the omnidirectional image frames.

Object position measurement with automotive camera using vehicle motion data

A trailer angle detection system and method of detecting a trailer of a vehicle including a wide-angle camera and a controller. The controller is configured to receive a signal from the wide-angle camera representative of an area behind the vehicle. The controller transforms the signal into a top-down image. The controller determines a first plurality of values. Each of the first plurality of values is indicative of an amount of symmetry in a region of the top-down image. The controller determines a second plurality of values. Each of the second plurality of values is indicative of how closely a shape in the top-down image matches a predetermined shape. Then, the controller determines an estimate of an articulation angle based on the first plurality of values and the second plurality of values. Then controller performs an automated vehicle maneuver based on the estimate of the articulation angle.

Growing community of inventors

Northville, MI, United States of America

Matthew Baran