Ford Global Technolgoies, LLC

Robert Boschgmbh

Michigan State University

Mark Gehrke

Jonathan Diedrich

Brian Bennie

Jeffrey Allen Bochenek

Mahmoud Yousef Ghannam

Devesh Upadhyay

Cynthia M Neubecker

Eric L Reed

Adil Nizam Siddiqui

Hayder Radha

Nicholas Alexander Scheufler

James Stephen Miller

Jake S Schwartz

Greg Sypitkowski

Gunter Rottner

Alireza Rahimpour

David Hiskens

Eric Robert Krieger

Michael Huebner

Jon Diedrich

Martin Van Hoeckel

Mazin Hnewa

A plurality of thermal images forward of a vehicle are collected. Thermal data in the plurality of thermal images is normalized based on an ambient air temperature to generate a plurality of normalized thermal images. The plurality of normalized thermal images are input to a machine learning program trained to output an identification of an object based on the ambient air temperature and a risk of collision between the vehicle and the object. A vehicle component is actuated based on the identification of the object and the risk of collision with the object.

Object identification with thermal imaging

A vehicle characterizes a sunload on the vehicle using an imaging system including at least one camera capturing image data (e.g., without using an ambient light sensor). The image data includes at least a portion of a passenger cabin. A region of interest (ROI) overlay receives the image data and extracts selected image data according to predetermined scene elements of the vehicle environment. An occupant overlay is configured to detect a vehicle occupant represented in the selected image data and configured to generate truncated image data by subtracting image data corresponding to the vehicle occupant from the selected image data. An ambient light model uses environmental parameters including a sun position to estimate an expected sunload range. A mapper generates a sunload map comprising respective sunload values for a plurality of locations on the vehicle according to the truncated image data and the expected sunload range.

Camera-based vehicle sunload mapping

Advanced automotive active-safety systems, in general, and autonomous vehicles, in particular, rely heavily on visual data to classify and localize objects, most notably pedestrians and other nearby cars, to assist the corresponding vehicles maneuver safely in their environment. However, the performance of object detection methods is anticipated to degrade under challenging rainy conditions. Nevertheless, and despite major advancements in the development of deraining approaches, the impact of rain on object detection has largely been understudied, especially in the context of autonomous systems. This disclosure analyzes this problem space and presents an improved system for detecting objects under rainy conditions.

Object detection under rainy conditions for autonomous systems

Real-time wind data for a location is determined based on a detected movement of an object relative to a vehicle. The real-time wind data includes a wind speed and a wind direction. Upon receiving stored wind data for the location from a remote computer, a crosswind risk is determined based on the real-time wind data and the stored wind data. A vehicle component is actuated to compensate for the crosswind risk.

Crosswind risk determination

Methods and apparatus are disclosed for concealed fiducial markers for vehicle camera calibration. An example vehicle includes a frame, at least one panel coupled to the frame, and fiducial markers arranged in a predefined grid. The fiducial markers are configured to be detectable by a camera and concealed from observation by the human eye. The predefined grid of the fiducial markers is arranged to facilitate calibration of the thermal camera.

Concealed fiducial markers for vehicle camera calibration

Methods and apparatus are disclosed to facilitate environmental visibility determination. An example vehicle comprises a sensor and a processor and memory. The sensor is to generate road image information. The processor and memory are in communication with the sensor and are configured to: detect vanishing points of lane markings in the road image information, convert an average pixel row value of the vanishing points to a distance value, and if the distance value is below a threshold, stop execution of at least one road condition monitoring feature.

Methods and apparatus to facilitate environmental visibility determination

Method and apparatus are disclosed for vehicle security monitoring in a key-off state. An example vehicle includes low-power sensors and high-power sensors for security monitoring, a communication module, and a controller. The controller is to, when in a key-off state, determine a first score based on the low-power sensors. The controller also is to, responsive the first score exceeding a first threshold, activate the high-power sensors and determine a second score based on the high-power sensors. The controller also is to, responsive the second score exceeding a second threshold, send an alert via the communication module.

Vehicle security monitoring in a key-off state

Systems and methods are presented for operating a vehicle camera system to detect, identify, and mitigate camera lens contamination. An image is received from a camera mounted on the vehicle and one or more metrics is calculated based on the received image. The system determines whether a lens of the camera is contaminated based on the one or more calculated metrics and, if so, determines a type of contamination. A specific mitigation routine is selected form a plurality of mitigation routines based on the determined type of contamination and is applied to the received image to create an enhanced image. The enhanced image is analyzed to determine whether the contamination is acceptably mitigated after application of the selected mitigation routine and a fault condition signal is output when the contamination is not acceptably mitigated.

Detection, identification, and mitigation of lens contamination for vehicle mounted camera systems

Systems and methods are described for monitoring movement of a trailer relative to the towing vehicle and providing driver-assistance information to the driver of the towing vehicle. The system determines a velocity vector for the host vehicle at a location near a rear of the host vehicle at a defined lateral distance from a trailer hitch installed on the host vehicle. The system also determines a velocity vector for the trailer at a corresponding location on the trailer&#x2014;that is a location on the front of the trailer at approximately the same defined lateral distance from the trailer hitch. The system compares the velocity vector for the host vehicle to the velocity vector for the trailer and determines, based on the comparison, whether a jack-knife condition is likely to occur. If a jack-knife condition is likely to occur, the system generates a warning signal.

Vector-based driver assistance for towing vehicle

Systems and methods are described for creating a unified output image based on image data from multiple cameras with overlapping fields of view by converting a raw image from each camera into a rectified output image using a look-up table. Camera misalignments are mitigated by generating an updated look-up table based on feature point detection and matching in the overlapping fields of view.

Vehicle camera system with multiple-camera alignment

Systems and methods for using a hitch connection system to attach a vehicle to a trailer. The hitch connection system includes at feast one camera and a controller. The camera is configured to collect snags data of a vehicle hitch and a trailer coupler. The controller is configured to generate an overhead view image based on the image data. The controller is farther configured to calculate a relative height between the vehicle hitch and the trailer coupler based on the image data and generate an alert when the relative height is less ton a predetermined threshold.

Overhead view for hitch connection

A method and system for determining a distance and direction between a video camera secured on a vehicle and a target point relies on an electronic control unit. The system maps and stores grid points representing a world coordinate grid onto a screen coordinate grid and displays the video image on a display using the screen coordinate grid. The system obtains a target point of an object in the video image and determines a locus of four closest grid points of the screen coordinate grid that encircle the target point. The system determines screen distances from the target point to each of the four grid points and maps the four grid points onto the world coordinate grid. The electronic control unit interpolates the location of the target point in the world coordinate grid as weighted by the screen distances. Using the video camera location in world coordinates and the target point location in world coordinates, the system determines a distance between the video camera and the target point.

Distance and direction estimation of a target point from a vehicle using monocular video camera

A method and system for guiding a vehicle having a hitch connector to a trailer operates with a monocular vehicle video camera secured to a rear of the vehicle. In operation, the vehicle video camera generates video images from a rearward direction of the vehicle that are displayed. An electronic control unit including a processor is configured to: receive and display the video images, analyze the video images to confirm the location of a trailer coupler, analyze the video images to determine distance from a hitch connector of the vehicle to the trailer coupler, analyze the video images to determine height of the hitch connector of the vehicle, height of the trailer coupler of the trailer, and the relative height difference between the hitch connector of the vehicle and the trailer coupler of the trailer, and assist in guiding the vehicle to a trailer coupling position.

Growing community of inventors

Ypsilanti, MI, United States of America

Mark Gehrke