Abstract: Vision sensor systems and methods detect banding and flicker. The method includes receiving camera data and identifying a light source location in a frame of camera data and assigning a luminance measure at the light source as a signal reference. A region of interest (ROI) is then associated with the light source. The frame is incremented, and then a signal to noise ratio (SNR) at the light source is calculated. A number, N of frames may be processed to identify banding when it is present, and to identify flicker when it is present. Responsive to identifying banding or identifying flicker, a response for a display system or for a machine vision system is generated.

Abstract: Systems and methods for depth estimation of images from a mono-camera by use of radar data by: receiving, a plurality of input 2-D images from the mono-camera; generating, by the processing unit, an estimated depth image by supervised training of an image estimation model; generating, by the processing unit, a synthetic image from a first input image and a second input image from the mono-camera by applying an estimated transform pose; comparing, by the processing unit, an estimated three-dimensional (3-D) point cloud to radar data by applying another estimated transform pose to a 3-D point cloud wherein the 3-D point cloud is estimated from a depth image by supervised training of the image estimation model to radar distance and radar doppler measurement; correcting a depth estimation of the estimated depth image by losses derived from differences: of the synthetic image and original images; of an estimated depth image and a measured radar distance; and of an estimated doppler information and measured radar d

Abstract: A method for vehicle tracking and localization includes receiving, by a controller, odometry data from a sensor of the first vehicle; geospatial data from a Global Positioning System (GPS) device of the first vehicle; inertial data from an inertial measurement unit (IMU) of the first vehicle; estimating an estimated-current location of the first vehicle and an estimated-current trajectory of the first vehicle using the odometry data from the sensor, the geospatial data from the GPS device, and the inertial data from the IMU of the first vehicle; inputting the inertial data into a Bayesian Network to determine a predicted location of the first vehicle and a predicted trajectory of the first vehicle, and updating the Bayesian Network using the estimated-current location and the estimated-current trajectory of the first vehicle using the odometry data and the geospatial data.

Abstract: A system and method to perform dynamic bandwidth adjustment among two or more vehicle sensors includes receiving input. The input includes data from each of the two or more vehicle sensors. The two or more vehicle sensors include a camera, an audio detector, a radar system, or a lidar system. The method also includes determining a bandwidth at which each of the two or more vehicle sensors should provide the data, and providing a control signal to each of the two or more vehicle sensors to adjust the bandwidth based on the determining.

Abstract: Methods and apparatus are provided for real time video upscaling in a vehicle display system. The apparatus includes a camera for capturing an image having a first resolution, a display operative at a second resolution, a sensor for detecting a condition, and a processor for selecting a scaling algorithm in response to the first resolution, the second resolution and the condition, the processor further operative to scale the image from the first resolution to the second resolution to generate a rescaled image and for coupling the rescaled image to the display.

Abstract: One general aspect includes a method to provide an alert to a vehicle occupant, the method includes: detecting, via an internal camera, whether the vehicle occupant is paying attention to an environment surrounding the vehicle; detecting, via an external camera, an occurrence of an event in the environment surrounding the vehicle; and based on each of the preceding steps, providing a notification configured to alert the vehicle occupant to transition the vehicle from a stopped state to a moving state.

Abstract: A method and system for gathering vehicle video data, processing the vehicle video data, and providing the processed data to a cloud layer that reconstructs the scene encountered by the vehicle. By reconstructing the encountered scene at the cloud layer, a variety of commands can be generated for that vehicle or other vehicles in the vicinity, where the commands address the conditions being experienced by the vehicles. This may be particularly useful for autonomous or semi-autonomous vehicles. If the reconstructed scene is not sufficiently accurate or detailed, one or more data extraction parameter(s) can be adjusted so that additional data is provided to the cloud layer; if the reconstructed scene is sufficiently accurate, then the data extraction parameter(s) can be adjusted so that less data is provided to the cloud layer, thus, reducing unnecessary cellular data charges.

Abstract: In various embodiments, methods, systems, and vehicles are provided for distance determinations using cameras from different vehicles. The system includes a first camera onboard a first vehicle, providing a first image, the first image having therein an object of interest (OOI) for which a distance from the first vehicle is desired; and a second camera, providing second camera data including a second image having therein the OOI. The system further includes a control module configured to process and time synchronize first camera data and second camera data to generate a distance determination for the OOI, using the first camera data, the second camera data, and a distance between the first and second camera.

Abstract: In various embodiments, methods, systems, and vehicles are provided that include obtaining first camera images from a first camera onboard a first vehicle; generating, via one or more computer processors, a first situation awareness graph with respect to objects near the first vehicle, using the first camera images; obtaining second camera images from a second camera of a second device that is in proximity to the first vehicle; generating, via one or more computer processors, a second situation awareness graph with the respect to the objects, using the second camera images; and generating, via one or more computer processor, a global situation awareness graph with respect to the objects, by merging the first situation awareness graph with the second situation awareness graph, using respective first and second weights for the first and second situation awareness graphs.

Abstract: An automotive vehicle includes an actuator configured to control vehicle steering, acceleration, or shifting, a sensor configured to capture images of a region exterior to the vehicle, and a controller in communication with the actuator and the sensor. The controller is configured to selectively control the actuator according to a primary mode and a secondary mode. The controller is additionally configured to detect liquid on a driving surface proximate the vehicle, to estimate a depth of the liquid based on images captured by the sensor, and to control the actuator in the secondary mode in response to the depth exceeding a predefined threshold.

Abstract: A parking assist system and method for aligning a capture resonator mounted on a vehicle with a source resonator, charging pad, disposed on a ground surface is disclosed. The parking assist system includes a vehicle GPS receiver, a vehicle external sensor, an ultra-wide band (UWB) sensor, a controller; and a display device. The controller is configured to process information collected from the vehicle GPS receiver, the vehicle external sensor, and the UWB sensor to determine the location of the source resonator and to calculate a path to park the vehicle such that the capture resonator is aligned with the source resonator. A rendering of a trajectory path is displayed on a display device. The calculated path may be communicated to an autonomous driving system to autonomously maneuvering the vehicle into a parking space such that the capture resonator is aligned with the source resonator.

Abstract: Systems and methods for depth estimation of images from a mono-camera by use of radar data by: receiving, a plurality of input 2-D images from the mono-camera; generating, by the processing unit, an estimated depth image by supervised training of an image estimation model; generating, by the processing unit, a synthetic image from a first input image and a second input image from the mono-camera by applying an estimated transform pose; comparing, by the processing unit, an estimated three-dimensional (3-D) point cloud to radar data by applying another estimated transform pose to a 3-D point cloud wherein the 3-D point cloud is estimated from a depth image by supervised training of the image estimation model to radar distance and radar doppler measurement; correcting a depth estimation of the estimated depth image by losses derived from differences: of the synthetic image and original images; of an estimated depth image and a measured radar distance; and of an estimated doppler information and measured radar d

Abstract: A system and method are provided for aiding an operator in operating a vehicle. In one embodiment, a system includes a sensor system configured to generate sensor data sensed from an environment of the vehicle. The system further includes a control module configured to, by a processor, to determine a scene of the environment based on the sensor data, determine a terrain feature in the environment based on the sensor data, alter a graphic of a vehicle component based on the terrain feature, and generate display data to display the altered graphic and the terrain feature in the scene for viewing by the operator of the vehicle.

Abstract: A method and system for gathering vehicle video data, processing the vehicle video data, and providing the processed data to a cloud layer that reconstructs the scene encountered by the vehicle. By reconstructing the encountered scene at the cloud layer, a variety of commands can be generated for that vehicle or other vehicles in the vicinity, where the commands address the conditions being experienced by the vehicles. This may be particularly useful for autonomous or semi-autonomous vehicles. If the reconstructed scene is not sufficiently accurate or detailed, one or more data extraction parameter(s) can be adjusted so that additional data is provided to the cloud layer; if the reconstructed scene is sufficiently accurate, then the data extraction parameter(s) can be adjusted so that less data is provided to the cloud layer, thus, reducing unnecessary cellular data charges.

Abstract: A method and system for generating a combined rearview image of an area behind a vehicle that is towing a trailer, the method including: capturing a first image from a vehicle camera that is installed on the vehicle, the first image being comprised of an area behind the vehicle; capturing a second image from a trailer camera that is installed on the trailer, the second image being comprised of an area behind the trailer; determining an obstructed viewing region within the first image, the obstructed viewing region being a region of the first image in which the trailer resides; overlaying the second image on the first image and at least partially within the obstructed viewing region; and inserting graphics in the first image, in the second image, and/or in a patch region within the obstructed viewing region and between the second image and the first image.

Abstract: A system includes an object identification module, a tailgate position module, and a user interface device (UID) control module. The object identification module is configured to identify at least one of a bumper of a vehicle and a tailgate of the vehicle in an image captured by a camera mounted to the tailgate. The tailgate position module is configured to determine that the tailgate is closed when the bumper is identified in the image, and determine that the tailgate is open when at least one of: the tailgate is identified in the image; and the bumper is not identified in the image. The UID control module is configured to adjust operation of a user interface device based on whether the tailgate is open or closed.

Abstract: Methods and systems are provided for controlling camera images for a camera of a vehicle are provided. In certain examples, a vehicle includes a camera, an input unit, and a processor. The input unit is configured to obtain data pertaining to a light pattern in proximity to the vehicle. The processor is configured to at least facilitate: (i) determining the light pattern in proximity to the vehicle using the data; and (ii) providing instructions for selectively binning the camera images based on the light pattern, the selectively binning including binning first pixels together for a particular image or portion thereof, but leaving second pixels for the particular image un-binned, based on the light pattern.

Abstract: A system and method to perform detection based on sensor fusion includes obtaining data from two or more sensors of different types. The method also includes extracting features from the data from the two or more sensors and processing the features to obtain a vector associated with each of the two or more sensors. The method further includes concatenating the two or more vectors obtained from the two or more sensors to obtain a fused vector, and performing the detection based on the fused vector.

Abstract: An automotive vehicle includes an actuator configured to control vehicle steering, acceleration, or shifting, a sensor configured to capture images of a region exterior to the vehicle, and a controller in communication with the actuator and the sensor. The controller is configured to selectively control the actuator according to a primary mode and a secondary mode. The controller is additionally configured to detect liquid on a driving surface proximate the vehicle, to estimate a depth of the liquid based on images captured by the sensor, and to control the actuator in the secondary mode in response to the depth exceeding a predefined threshold.

Abstract: A method and system to perform dynamic demosaicing for a camera in a vehicle involve an array of image sensors of the camera to obtain light intensity values. Each image sensor of the array of image sensors represents a pixel. An array of filters of the camera overlays the array of image sensors and restricts a wavelength range for which the one image sensor of the array of image sensors obtains the light intensity value. The array of filters includes at least two different types of filters corresponding with two different wavelength ranges. A processor estimates a current state associated with the vehicle and selects a demosaicing algorithm based on the current state such that, for each pixel, the demosaicing algorithm facilitates an estimate of the light intensity value at a different wavelength range than the wavelength range for which the corresponding image sensor obtained the light intensity value.