Gm Global Technolgoy Operations, Inc.

Carnegie Mellon University

Guangyu J Zou

Upali Priyantha Mudalige

Jinsong Wang

Andrew W Averhart

Fan Bai

Shuqing Zeng

Sai Vishnu Aluru

Soheil Samii

Joseph G Machak

Lawrence A Bush

Brent Navin Roger Bacchus

Michael A Losh

Vijayakumar Bhagavatula

David A Craig

Unmesh Dutta Bordoloi

Ismail Hamieh

Aravindhan Mani

Indranil Palit

Yang Zou

A self-cleaning sensor system of a motor vehicle includes an object sensor having a lens surface facing a region located external to the motor vehicle. The object sensor generates a signal associated with an image or a video of the region. The system further includes multiple lens treatment devices for applying remedies for removing an obscurity formed on the lens surface. The system further includes a computer having one or more processors and a computer readable medium storing instructions. The processor is programmed to determine a classification of the obscurity, in response to the processor receiving the signal from the object sensor. The processor is further programmed to generate an actuation signal, and the associated lens treatment device applies the remedy, in response to the associated lens treatment device receiving the actuation signal from the processor.

Self-cleaning sensor system of a motor vehicle

A scene creation system for an autonomous vehicle includes one or more controllers executing instructions to receive perception data and map data of a roadway the autonomous vehicle is traveling along, and identify a plurality of lane segments of the roadway that the autonomous vehicle travels along based on the perception data and the map data. The one or more controllers connect the plurality of lane segments together based on a spatial relationship between the plurality of lane segments to create a lane graph. The one or more controllers classify each of the plurality of lane segments of the lane graph to one or more lane attributes and reassemble the plurality of lane segments to create a representation of the roadway. The one or more controllers recreate a scene of an environment surrounding the autonomous vehicle based on the representation of the lanes that are part of the roadway.

Scene creation system for an autonomous vehicle

Systems and methods of detecting a traffic object outside of a vehicle and controlling the vehicle. The systems and methods receive perception data from a sensor system included in the vehicle, determine a focused Region Of Interest (ROI) in the perception data, scale the perception data of the at least one focused ROI, process the scaled perception data of the focused ROI using a neural network (NN)-based traffic object detection algorithm to provide traffic object detection data, and control at least one vehicle feature based, in part, on the traffic object detection data.

Systems and methods for detecting traffic objects

A system for analyzing images includes a processing device including a receiving module configured to receive an image associated with a target domain, and a domain adaptation module configured to characterize one or more features represented in the received image based on a domain adaptation model. The domain adaptation model is generated using a machine learning algorithm to train the domain adaptation model, and the machine learning algorithm is configured to train the domain adaptation model based on one or more source domain images associated with a source domain, one or more previously acquired images associated with the target domain, and acquired characterization data associated with the target domain. The system also includes an output module configured to output the received image with characterization data identifying one or more features characterized by the domain adaptation module.

Domain adaptation for analysis of images

An attention-based imaging system is described, including a camera that can adjust its field of view (FOV) and resolution and a control routine that can determine one or more regions of interest (ROI) within the FOV to prioritize camera resources. The camera includes an image sensor, an internal lens, a steerable mirror, an external lens, and a controller. The external lens is disposed to monitor a viewable region, and the steerable mirror is interposed between the internal lenses and the external lenses. The steerable mirrors are arranged to project the viewable region from the external lens onto the image sensor via the internal lens. The steerable mirror modifies the viewable region that is projected onto the image sensor and controls the image sensor to capture an image. The associated control routine can be deployed either inside the camera or in a separate external processor.

On-vehicle imaging system

An automotive vehicle includes a sensor configured to detect features external to the vehicle, an HMI configured to signal an alert to an operator of the vehicle, and a controller. The controller is in communication with the sensor and the HMI, and is in communication with a non-transient computer-readable storage medium provided with a road furniture database. The road furniture database includes a plurality of items of road furniture having associated road furniture geolocations and road furniture classifications. The controller is configured to, in response to the vehicle being proximate a respective road furniture geolocation for a respective item of road furniture and the sensor not detecting the respective item of road furniture, control the HMI to signal an alert.

System and method for displaying information in a vehicle

A system and method for object detection and classification includes receiving by a controller a first data of a scene, wherein the data reflects the scene at a first time, and performing a first classification of at least one object within the scene based on the data. The method includes determining a projected location of the at least one object corresponding to an estimated location at a second time. The method includes receiving a second data of the scene reflecting the scene at the second time. The method includes determining whether the projected location of the object corresponds to the location of the object as reflected by the second data. The method includes determining whether performing a second classification of the object is necessary based on the determination of whether the projected location corresponds to the location of the object reflected by the second data.

Method and system for improving object detection and object classification

Systems and method are provided for controlling a vehicle. In one embodiment, a method of controlling a vehicle, includes receiving, via at least one processor, image data from each of plural cameras mounted on the vehicle. The method includes assembling, via the at least one processor, the image data from each of the plural cameras to form assembled image data. The method includes classifying and localizing lane features using an artificial neural network based on the assembled image data, to produce classified and localized lane data. The method includes performing, via the at least one processor, a data fusion process based on the classified and localized lane data, thereby producing fused lane feature data. The method includes controlling, via the at least one processor, the vehicle based, in part, on the fused lane feature data.

Artificial neural network for lane feature classification and localization

Systems and methods are provided for detecting features from multi-modal image-like data representations. The system includes a wavelet transformer configured to, via at least one processor, receive image data and to wavelet transform the image data, thereby providing decomposed image data divided into frequency sub-bands. The system further includes an artificial neural network configured to receive and process at least one sub-band of the decomposed image data to detect image features based thereon, the artificial neural network configured to output the detected image features.

Detecting features from multi-modal images

Techniques for road scene primitive detection using a vehicle camera system are disclosed. In one example implementation, a computer-implemented method includes receiving, by a processing device having at least two parallel processing cores, at least one image from a camera associated with a vehicle on a road. The processing device generates a plurality of views from the at least one image that include a feature primitive. The feature primitive is indicative of a vehicle or other road scene entities of interest. Using each of the parallel processing cores, a set of primitives are identified from one or more of the plurality of views. The feature primitives are identified using one or more of machine learning and classic computer vision techniques. The processing device outputs, based on the plurality of views, result primitives based on the plurality of identified primitives from multiple views based on the plurality of identified entities.

Growing community of inventors

Warren, MI, United States of America

Guangyu J Zou