Trw Limited

Trw Automotive U.S. LLC

Trw Vehicle Safety Systems Inc.

Jon Kelly Wallace

Farid Khairallah

Yun Luo

Russell Joseph Lynch

Stephen R W Cooper

Nicholas Michael Zayan

Scott E Kolassa

Keith R Miciuda

Roger A McCurdy

Robert Dziadula

Dale Walter Karolak

Charles E Steffens, Jr

Chek-Peng Foo

John Joseph Berenz

Barry Dunbridge

Raymond J David

Todd Alan Witters

Russell J Lynch

A system for classifying image data includes a vision system () for continuously imaging an area () of interest and providing an image signals. A classifier () determines an image class corresponding to each image signal, determines a confidence level for each determined image class, determines a time period for the confidence level, and establishes an image classification in response thereto. Switching between image classifications is in response to the confidence level and time period of the confidence level. When used in a vehicle restraining system (), other monitor vehicle parameters () can be used to adjust the confidence levels and time periods needed to switch between image classifications.

Method and apparatus for controlling classification and classification switching in a vision system

A system () for generating training images for a pattern recognition classifier () from three-dimensional image data representing an output class comprises a model constructor () that constructs an image model in a standard coordinate domain from the three-dimensional image data. A model transformer () manipulates the image model in the standard coordinate domain to produce at least one manipulated image model. An image restorer () maps the at least one manipulated image model from the standard coordinate domain to a coordinate domain associated with an image source utilized during the run-time operation of the pattern recognition classifier.

Method and apparatus for producing classifier training images via construction and manipulation of a three-dimensional image model

Systems and methods are provided for producing a stereo disparity map representing an imaged subject. A plurality of sensors (and) are operative to produce a plurality of images. Each image has an associated exposure according to an exposure level of an associated sensor. A system control () determines exposure levels for the plurality of sensors according to an exposure selection algorithm. A disparity processing component () is operative to generate a stereo disparity map from a plurality of images. An image merger () is operative to merge a plurality of images to produce a composite image having an increased dynamic range.

Method and apparatus for enhancing the dynamic range of a stereo vision system

Systems and methods are provided for identifying a position of a head of a vehicle occupant from a plurality of images of a vehicle interior. Image data is translated from the plurality of images to produce a virtual side view image of the vehicle interior (). A largest grouping of pixels in the side view image having values within a desired range is identified (). The grouping includes a plurality of pixel columns. A contour including uppermost pixels of each pixel column is produced and peaks are located within the contour (, and). The contour peaks are analyzed according to a heuristic voting algorithm to identify a peak location associated with the head of the vehicle occupant ().

Method and apparatus for locating an object of interest within an image

A system () for classifying an input image into one of a plurality of output classes includes a plurality of pattern recognition classifiers (). Each of the plurality of pattern recognition classifiers determines a candidate output class and at least one rejected output class for the input image from an associated subset of the plurality of output classes. Each classifier generates a confidence value associated with the classifier based on the determination. An arbitrator () selects a classifier having the best associated confidence value and eliminates the at least one rejected class determined at the selected classifier from consideration as the associated class for the input image.

Method and apparatus for arbitrating outputs from multiple pattern recognition classifiers

An apparatus () for determining a location of a person's head () includes stereo vision system () for imaging an area of interest such as the interior of a vehicle (). The vision system provides an image signal of the area of interest. An analyzer () analyzes the image signal to identify head candidates () in the area of interest and provides data regarding any identified head candidates in the area of interest. A processor () processes the provided data regarding identified head candidates to locate the person's head. In an air bag restraining system (), a controller () monitors the location of the person's head and controls an air bag () in response to a sensed crash condition () and the location of the person's head.

Method and apparatus for determining an occupant's head location in an actuatable occupant restraining system

Systems and methods are provided for editing an image of a vehicle interior to isolate the occupant of a vehicle seat. An image generator () generates an image of a vehicle interior. A contour generator () produces a contour image from the generated image. A model selector () selects a contour model from a plurality of contour models according to the similarity of the contour model to a portion of the contour image. An image editor () removes a portion of the generated image representing at least a portion of the vehicle seat according to the selected contour model to produce an image of an occupant of the vehicle seat.

Method and apparatus for determining the position of a vehicle seat

Systems and methods are provided for identifying a position of a head of a vehicle occupant from a plurality of images of a vehicle interior. Image data is translated from the plurality of images to produce a virtual side view image of the vehicle interior (). A largest grouping of pixels in the side view image having values within a desired range is identified (). The grouping includes a plurality of pixel columns. A contour including uppermost pixels of each pixel column is produced and peaks are located within the contour (). The contour peaks are analyzed according to a heuristic voting algorithm to identify a peak location associated with the head of the vehicle occupant ().

Controller system for a vehicle occupant protection device

A method and apparatus () for testing an occupant position sensing system () of a vehicle () includes a motor () having a stationary portion () and a movable portion (). A test object () is fixed relative to the movable portion () of the motor (). A motor position sensor () senses a position of the movable portion () of the motor () relative to the stationary portion () and for providing a motor position signal indicative thereof. Motor drive electronics () are responsive to the motor position signal for controlling the motor () for moving the test object (). A data recorder () is adapted to receive and record data from the occupant position sensing system () and is adapted to receive and record the motor position signal provided by the motor position sensor ().

Apparatus and method for testing and occupant position sensing system of a vehicle

A method for helping to control a vehicle occupant protection device () includes taking an image of the vehicle interior with a digital imager () having an array of pixels (). A contiguous portion of the image less than the entire image is selected. At least one image enhancement technique is applied to the selected image portion. The enhanced image portion is combined with the other portions of the image to make an enhanced image. The enhanced image is analyzed to detect at least one of features and characteristics of the enhanced image. Alternatively, a selected non-contiguous group of the pixels () of the imager () are read out, as representative of the entire image, to estimate the illumination levels across the entire array of pixels. In one aspect, the imager shutter () speed may be controlled to enhance the image.

Enhancement of vehicle interior digital images

A method and apparatus () for recognizing and determining a location of an object () in an area of interest () comprises an imaging device () for obtaining an image of the area of interest. At least three identifying marks () are located at predetermined positions in the area of interest (). The apparatus () also comprises a memory () in which the predetermined positions of the at least three identifying marks () are stored. A controller () determines whether the imaging device () is calibrated properly by analyzing the image obtained by the imaging device to determine whether positions of the at least three identifying marks () in the obtained image correspond to the predetermined positions stored in the memory (). The controller () is also adapted to determine whether a view of the area of interest () from the imaging device () is obstructed.

Method and apparatus for self-diagnostics of a vision system

An apparatus () and associated method determine a vehicle occupant characteristic. An imager () collects a first image of an occupant location while the occupant location is subject to a first lighting condition. A light source () provides light onto the occupant location. The imager () collects a second image of the occupant location while the occupant location is subject to the first lighting condition and the provided light. A subtractor device () generates a third image of the occupant location indicative of the difference between the first and second images. An image processing device () processes the third image to determine the vehicle occupant characteristic.

Apparatus and method for determining vehicle occupant characteristic utilizing imaging with provided light

A vehicle intrusion detection system () for detecting an intrusion condition of a vehicle () having an occupant compartment () partially defined by an outer structure () of the vehicle, comprises an actuatable illuminator () mounted in the vehicle and having a limited field of illumination () extending within the vehicle occupant compartment adjacent the vehicle outer structure. A linear imager () mounted in the vehicle () has a field of view () that substantially coincides with the field of illumination () of the illuminator (). A controller () compares a first image taken by the imager () when the illuminator () is actuated and a second image taken by the imager when the illuminator is unactuated to help determine the existence of an intrusion condition of the vehicle.

Intrusion detection system using linear imaging

An occupant sensing system ( ) and an associated method provide for the sensing of an occupant ( ). An illuminating element ( ) of the system ( )selectively illuminates the interior of a vehicle ( ). An image sensor ( ) acquires a first image of the interior of the vehicle ( ) when the interior of the vehicle is illuminated by ambient sources only and acquires a second image of the interior of the vehicle when the interior of the vehicle is illuminated by ambient sources and the illuminating element ( ). A controller ( ) removes the effect of ambient sources by comparing the first and second images to produce a third image of the interior of the vehicle ( ) as illuminated by the illuminating element ( ) only. The controller ( ) determines the presence of an occupant ( ) by comparing the third image to a produced map of the interior of the vehicle ( ).

Occupant sensing system and method via imaging

An apparatus ( ) for determining the location of a vehicle occupant ( ) in a vehicle interior includes a light source ( ) for projecting at least one structured light beam ( ) onto an area of interest ( ) to form a light pattern on the area of interest. A beam divergence control device ( ) alters the apparent location of the light source ( ) with respect to the area of interest ( ). An imager ( ) detects the light reflected from the area of interest ( ). A characteristic of the reflected light is measured, and the distance between the imager ( ) and the area of interest ( ) is measured, based on the measured characteristic of the reflected light.

Growing community of inventors

Redford, MI, United States of America

Jon Kelly Wallace