Yelena M Rodin

7068302, Jun 27, 2006

Aug 15, 2002

10/064769

Samuel Edward Ebenstein - Southfield MI, US
Gregory H. Smith - Ann Arbor MI, US
Yelena Mordechai Rodin - Southfield MI, US
David Bednarz - Pontiac MI, US
Thomas Meitzler - Troy MI, US

Ford Global Technologies, LLC - Dearborn MI

H04N 17/00

348187, 348188

A method for testing cameras includes positioning a camera such that an image of a target is displayed on a monitor within at least one default image parameter. The method further includes engaging a dimming condition of a light source from the camera, thereby generating a lighting condition signal. Subsequently the camera receives the lighting condition signal and displays it on the monitor. A group of observers then analyze the lighting condition signal. The method continues through engaging a second dimming condition of the light source from the first camera, thereby generating a second lighting condition signal, which is also displayed on the monitor. The group of observers then analyzes the second lighting condition signal.

7353088, Apr 1, 2008

Oct 25, 2004

10/904124

Charles Eagen - Ann Arbor MI, US
Lee Feldkamp - Plymouth MI, US
Sam Ebenstein - Southfield MI, US
Kwaku Prakah-Asante - Commerce Township MI, US
Yelena Rodin - Southfield MI, US
Greg Smith - Ann Arbor MI, US

Ford Global Technologies, LLC - Dearborn MI

B60R 21/015
G08B 23/00
G06F 19/00

701 1, 701 35, 701 45, 706 15, 706 30, 702 56

A system for detecting the presence of a human in a vehicle is provided. The system includes a vibration sensor that is configured to detect vibrations of the vehicle, and to output signals related to the sensed vibrations. A processor is configured to receive the signals output from the vibration sensor. The processor also operates a neural network that has a plurality of nodes, at least some of which are recurrent. The use of the recurrent nodes allows the output of a recurrent node to be fed back into itself, or another node. In addition, the output that is fed back can be combined with other inputs entering the node. In this way, the neural network can quickly learn to distinguish between various conditions, including an occupied state and an unoccupied state of the vehicle. The neural network provides an output indicating whether the vehicle is occupied.

8194920, Jun 5, 2012

Feb 16, 2007

11/675799

Samuel Ebenstein - Southfield MI, US
Gregory Smith - Ann Arbor MI, US
Kwaku Prakah-Asante - Commerce Township MI, US
Yelena Rodin - Southfield MI, US
Nicholas Zorka - Clarkston MI, US

Ford Global Technologies, LLC - Dearborn MI

G06K 9/00
G06K 9/34
G06K 9/46
G06K 9/38

382103, 382100, 382104, 382173, 382190, 382270

An object detection system is disclosed in at least one embodiment. The system includes a far IR sensor operable to sense thermal radiation of objects and surroundings in a field of view and to generate a far IR image in response thereto, and an image processing device operable to receive and process the far IR image to detect the presence of one or more objects in the field of view. The image processing device can be configured to process the far IR image by generating an initial threshold image based on the far IR image and an initial threshold value, iteratively obtaining a number of successive threshold images based on the far IR image and a number of successively increased threshold values, and determining the presence of one or more objects in the field of view based on the threshold images and threshold values.

20030076981, Apr 24, 2003

Oct 18, 2001

09/682777

Gregory Smith - Ann Arbor MI, US
James Rankin - Novi MI, US
Samuel Ebenstein - Southfield MI, US
Yelena Rodin - Southfield MI, US

B60R021/32
G06K009/00

382/104000, 280/735000, 382/106000

A pre-crash system () has a controller () coupled to an object sensor (). Object sensor () has a vision system () that includes image sensors to detect an impact and in particular, a side impact. The image sensors provide a high frame rate to a video-processing chip () which in turn is coupled to a general purpose controller (). The general-purpose controller 34 determines whether an object is an impending threat and controls the deployment of an airbag through an airbag controller () or other counter-measure. The high frame rate used in the present invention allows not only the distance to the object but the velocity of the object as well as the acceleration of the object to be determined and factored into the deployment decision.

20050225635, Oct 13, 2005

Apr 9, 2004

10/828525

Thomas Meitzler - Troy MI, US
Samuel Ebenstein - Southfield MI, US
Gregory Smith - Ann Arbor MI, US
James Rankin - Novi MI, US
Yelena Rodin - Southfield MI, US

The United States of America as represented by the Secretary of the Army - Washington DC

H04N007/18

348148000, 348143000

A video surveillance system for vehicle interiors that has a plurality of video cameras positioned throughout the vehicle connected to a multiplexer to route the signals to an image processing system. The system will build a high resolution image and display the image real-time for review.

20070216768, Sep 20, 2007

Mar 14, 2006

11/308248

Gregory Smith - Ann Arbor MI, US
Nicholas Zorka - Clarkston MI, US
Kwaku Prakah-Asante - Commerce Twp. MI, US
Samuel Ebenstein - Southfield MI, US
Patrick Canfield - Dearborn MI, US
Yelena Rodin - Southfield MI, US

FORD GLOBAL TECHNOLOGIES, LLC - Dearborn MI

H04N 7/18

348118000

A system for mounting a camera within a vehicle is illustrated. The camera may be positioned behind an IR transmissible window within the vehicle and within a housing within the vehicle. The camera is thus placed between the windshield and the housing so that the field of view of the camera is through the window . A notch shape or hole may be formed within the windshield so that the IR transmissive portion may be inserted therein.

20090016571, Jan 15, 2009

Mar 30, 2007

11/731354

Louis Tijerina - Dearborn MI, US
Samuel Edward Ebenstein - Southfield MI, US
Kwaku O. Prakah-Asante - Commerce Township MI, US
Yelena Mordechai Rodin - Southfield MI, US

G06K 9/00
G06K 9/40

382104, 382264

The present invention relates to a night vision system human machine interface and particularly to an HMI display that provides enhanced road scene imagery from low resolution cameras.

62818066, Aug 28, 2001

Oct 12, 2000

9/689411

Gregory Hugh Smith - Ann Arbor MI
Samuel Edward Ebenstein - Southfield MI
Yelena Mordechai Rodin - Southfield MI

Ford Global Technologies, Inc. - Dearborn MI

G08G 100

340901

A vision enhancement system 10 which aids the driver in visually identifying a sensed object 16 without diverting his/her attention from the road ahead. One or more sensors 20 used to collect information about the vehicle's environment are operatively coupled with a controlled source of illumination 38. A processor 24 receives input from the sensors and intelligently determines whether a particular object sensed in or near the current path of the vehicle requires alerting the driver. If so, the processor outputs a control signal 30 to effect illumination of the sensed object. The source of illumination is controlled so as to continuously direct light onto the identified object, even as the vehicle and/or object move simultaneously with respect to one another.