Gm Global Technolgoy Operations, Inc.

Carnegie Mellon University

Dan Levi

Noa Garnett

Michael Baltaxe

Oded Bialer

Tzvi Philipp

Wende Zhang

Igal Bilik

Fernando De La Torre

Debbie E Nachtegall

Aharon Bar Hillel

Roy Uziel

Ron M Hecht

Yael Shmueli Friedland

Omer Tsimhoni

Shaul Oron

Emanuel Mordechai

Shai Silberstein

Eran Kishon

Gershon Celniker

Shuqing Zeng

Ariel Lipson

Michael Slutsky

Claudia V Goldman-Shenhar

Ariel Telpaz

Asaf Degani

Inna Stainvas Olshansky

Bat El Shlomo

Dong Huang

Max Bluvstein

Amit Batikoff

Yuval Haitman

Andrea Forgacs

Xuehan Xiong

Michael Baitaxe

Doron Portnoy

Tal Furman

Netalee Efrat Sela

Zehua Huang

Franscisco Vicente

Shahar Ben Ezra

Ohad Rahamim

Tomer Pe'er

Ariel Rubanenko

Ethan Fetaya

Francisco Vicente

Herein, a technology that facilitates the optimization of vision-language (VL) based classifiers with text embeddings is discussed. The technology includes tuning the VL-based classifier employing a pre-trained image encoder of a visual-language model (VLM) for imaging embedding of pre-classified images and a pre-trained textual encoder of the VLM for textual embedding of a set of differing textual sentences. The technology further includes determining an optimized set of differing textual sentences of a superset of textual sentences. The optimized set of differing textual sentences has a minimal classification loss of the VL-based classifier when classifying the pre-classified images.

Classification by vision-language model with optimized text embeddings

A method of training a disparity estimation network. The method includes obtaining an eye-gaze dataset having first images with at least one gaze direction associated with each of the first images. A gaze prediction neural network is trained based on the eye-gaze dataset to develop a model trained to provide a gaze prediction for an external image. A depth database is obtained that includes second images having depth information associated with each of the second images. A disparity estimation neural network for object detection is trained based on an output from the gaze prediction neural network and an output from the depth database.

System and method for eye-gaze direction-based pre-training of neural networks

A computer-implemented method when executed by data processing hardware causes the data processing hardware to perform operations. The operations include generating, at an occupancy estimation network, an occupancy probability at one or more voxels, predicting, via a gaze prediction model, a gaze direction of a gaze prediction, and identifying, based on the predicted gaze direction, an object of interest. The operations also include generating, via an occupancy estimation application, a gaze saliency map based on the gaze direction and identified object of interest, and updating, based on the determined gaze direction and the gaze saliency map, the occupancy probability of the one or more voxels.

Occupancy estimation system for a vehicle

A system for classifying a road crossing intention of a pedestrian includes a processor including a pretrained image encoder generating an image embedding based upon an input image. The system further includes a remote server receiving the image embedding. The remote server device further references a plurality of pretrained image and text embeddings each corresponding to either a positive road crossing intention or a negative road crossing intention. The remote server device further determines a plurality of proximity values evaluating whether the input image is closer to the positive road crossing intention or the negative road crossing intention, evaluating the image embedding against each of the pretrained embeddings. The remote server device further classifies a road crossing intention of the pedestrian based upon the plurality of proximity values. The system further includes generates a road crossing intention output based upon the road crossing intention of the pedestrian.

System and method for pedestrian road crossing intention detection

A method, system and vehicle that repetitively correct angle offsets in a synthetic aperture radar image of a vehicle while the vehicle is in motion by utilizing a radar system and a camera to determine accurate velocity of a measured object by matching angles of the object in the SAR image with angles of the object in the camera image, thereby reducing angle offsets of objects in the SAR image. The method includes obtaining an SAR image of another vehicle via a radar unit of the vehicle, obtaining a camera image of the other vehicle via a camera unit of the vehicle, determining an association between at least one object in the SAR image and a corresponding at least one object in the camera image, correcting a velocity estimation of the vehicle based on the determined association, and adjusting the SAR image based on the corrected velocity estimation.

Velocity estimation and angle offset correction in SAR images by performing image matching

A disclosure is presented for estimating height of an object using ultrasonic sensors carried onboard a vehicle. The height may be estimated by generating ultrasonic distance measurements based on a time of flight associated with ultrasonic reflections detected with the ultrasonic sensors, generating a three-dimensional (3D) occupancy grid to volumetrically represent at least a portion of an environment within field of view of the ultrasonic sensors, the 3D occupancy grid including a plurality of volumetric pixels (voxels), assigning a count value to each of the voxels based on the distance measurements, and estimating the height according to a relative spatial relationship between the vehicle and the voxel having the count value with a greatest value.

Object height estimation using ultrasonic sensors

A detection system for a host vehicle includes a camera, global positioning system ('GPS') receiver, compass, and electronic control unit (“ECU”). The camera collects polarimetric image data forming an imaged drive scene inclusive of a road surface illuminated by the Sun. The GPS receiver outputs a present location of the vehicle as a date-and-time-stamped coordinate set. The compass provides a directional heading of the vehicle. The ECU determines the Sun's location relative to the vehicle and camera using an input data set, including the present location and directional heading. The ECU also detects a specular reflecting area or areas on the road surface using the polarimetric image data and Sun's location, with the specular reflecting area(s) forming an output data set. The ECU then executes a control action aboard the host vehicle in response to the output data set.

Automated detection of specular reflecting road surfaces using polarimetric image data

A system for a host vehicle operating on a road surface includes a polarimetric camera, a global positioning system ('GPS') receiver, a compass, and an electronic control unit (“ECU”). The camera collects polarimetric image data of a drive scene, including a potential driving path on the road surface. The ECU receives the polarimetric image data, estimates the Sun location using the GPS receiver and compass, and computes an ideal representation of the road surface using the Sun location. The ECU normalizes the polarimetric image data such that the road surface has a normalized representation in the drive scene, i.e., an angle of linear polarization (“AoLP”) and degree of linear polarization (“DoLP”) equal predetermined fixed values. The ECU executes a control action using the normalized representation.

Vehicle with polarimetric image normalization logic

A system in a vehicle includes an image sensor to obtain images in an image sensor coordinate system and a depth sensor to obtain point clouds in a depth sensor coordinate system. Processing circuitry implements a neural network to determine a validation state of a transformation matrix that transforms the point clouds in the depth sensor coordinate system to transformed point clouds in the image sensor coordinate system. The transformation matrix includes rotation parameters and translation parameters.

Alignment validation in vehicle-based sensors

A system includes a transmitter of a radar system to transmit transmitted signals, and a receiver of the radar system to receive received signals based on reflection of one or more of the transmitted signals by one or more objects. The system also includes a processor to train a neural network with reference data obtained by simulating a higher resolution radar system than the radar system to obtain a trained neural network. The trained neural network enhances detection of the one or more objects based on obtaining and processing the received signals in a vehicle. One or more operations of the vehicle are controlled based on the detection of the one or more objects.

High resolution radar simulation to train vehicle radar system neural network

A method of controlling a color display screen aboard a motor vehicle includes performing, via a host computer, a color calibration test of a user of the motor vehicle in which the user is subjected to a calibrated set of color-coded test information. The method includes receiving a color perception response of the user to the calibrated set of color-coded test information via the host computer. Additionally, the method includes mapping a reduced visual gamut of the user via the host computer using the color perception response, and then commanding adjustment of user-specific color settings of the motor vehicle using the reduced visual gamut to thereby accommodate a color perception deficiency of the user.

Vehicle display control for color-impaired viewers

A method for deblurring a blurred image includes dividing the blurred image into overlapping regions each having a size and an offset from neighboring overlapping regions along a first direction as determined by a period of a ringing artifact in the blurred image, or by obtained blur characteristics relating to the blurred image and/or attributable to the optical system, or by a detected cause capable of producing the blur characteristics, stacking the overlapping regions to produce a stacked output, wherein the overlapping regions are sequentially organized along the first direction, convolving the stacked output through a first convolutional neural network (CNN) to produce a first CNN output having reduced blur as compared to the stacked output, and assembling the first CNN output into a re-assembled image, and processing the re-assembled image through a second CNN to produce a deblurred image having reduced residual artifacts as compared to the re-assembled image.

Method and system for deblurring a blurred image

A system for analyzing images includes a processing device includes a receiving module configured to receive an image, and an analysis module configured to apply the received image to a machine learning network and classify one or more features in the received image, the machine learning network configured to propagate image data through a plurality of convolutional layers, each convolutional layer of the plurality of convolutional layers including a plurality of filter channels, the machine learning network including a bottleneck layer configured to recognize an image feature based on a shape of an image component, The system also includes an output module configured to output characterization data that includes a classification of the one or more features.

Shape-biased image classification using deep convolutional networks

A vehicle having an imaging sensor that is arranged to monitor a field-of-view (FOV) that includes a travel surface proximal to the vehicle is described. Detecting the travel lane includes capturing a FOV image of a viewable region of the travel surface. The FOV image is converted, via an artificial neural network, to a plurality of feature maps. The feature maps are projected, via an inverse perspective mapping algorithm, onto a BEV orthographic grid. The feature maps include travel lane segments and feature embeddings, and the travel lane segments are represented as line segments. The line segments are concatenated for the plurality of grid sections based upon the feature embeddings to form a predicted lane. The concatenation, or clustering is accomplished via the feature embeddings.

Method and apparatus for lane detection on a vehicle travel surface

A system and method to adjust an augmented reality (AR) image involve a front-facing camera in a vehicle. The camera obtains an image that includes a road surface ahead of the vehicle. The system also includes a processor to detect lane lines of the road surface in three dimensions, to perform interpolation using the lane lines to determine a ground plane of the road surface, and to adjust the AR image to obtain an adjusted AR image such that all points of the adjusted AR image correspond with points on the ground plane.

Dynamic adjustment of augmented reality image

Growing community of inventors

Kyriat Ono, Israel

Dan Levi