Yi H Lu

US Patent:

7952353, May 31, 2011

Filed:

May 6, 2009

Appl. No.:

12/436689

Inventors:

Wenmiao Lu - Nanyang Heights, SG
Yi Lu - Palo Alto CA, US

Assignee:

The Board of Trustees of The Leland Stanford Junior University - Palo Alto CA

International Classification:

G01V 3/00

US Classification:

324307, 324309

Abstract:

A method for estimating values of a field map to generate a magnetic resonance display image with species separation is provided. A set of MR images is acquired based on an applied magnetic resonance excitation. A set of feasible field map values for each pixel in a field map are determined from the set of MR images. Estimated values of the field map for each pixel are chosen from the set of feasible field map values using a combinatorial optimization algorithm that includes a smoothness constraint. The combinatorial optimization algorithm includes iteratively communicating, between neighboring pixels in the field map, sum-product belief messages that include likelihoods for feasible field map values. Field map values are fixed to most likely field map values if the pixel satisfies the smoothness constraint with its neighboring pixels. A magnetic resonance display image with species separation is generated using the estimated field map.

US Patent:

20210274064, Sep 2, 2021

Filed:

Mar 11, 2021

Appl. No.:

17/199271

Inventors:

- San Francisco CA, US
Forrest Samuel Briggs - Palo Alto CA, US
George James Hansel - Redwood City CA, US
James Allen-White Hoffacker - San Carlos CA, US
Dhruv Lamba - San Mateo CA, US
Chi Hoon Lee - San Francisco CA, US
Yi Lu - San Jose CA, US
Brian Thomas McGinn - Burlingame CA, US
Phillip Sawbridge - Los Altos CA, US

International Classification:

H04N 5/06
H04N 5/232
H04N 5/247

Abstract:

In one embodiment, a method includes, by a computing device of a first sensor receiving synchronization information from a controller. The synchronization information being generated based on a clock of the controller. The method also includes determining, based on the synchronization information, a first offset between a first clock of the first sensor and the clock of the controller; storing the first offset; and synchronizing, based on the stored first offset and the first clock of the first sensor, a first data capture by the first sensor with a second data capture by a second sensor. The first data capture and the second data capture being requested by the controller.

US Patent:

20190322288, Oct 24, 2019

Filed:

Jun 24, 2019

Appl. No.:

16/450561

Inventors:

- San Francisco CA, US
James Allen-White Hoffacker - San Carlos CA, US
Yi Lu - San Jose CA, US
Helen Ruth Lurie - San Francisco CA, US

International Classification:

B60W 50/06
G05D 1/00
B60W 50/04
G05D 1/02

Abstract:

In one embodiment, a computing system receives sensor data from one or more sensors of a vehicle. The computing system determines a metric associated with the vehicle based on the received sensor data. The computing system determines, based on the metric, a length of a transmission cycle of a communication network of the vehicle. The transmission cycle comprises one or more scheduled time periods dedicated for transmitting data from respective first nodes in the communication network. The computing system configures the communication network of the vehicle based at least in part on the length of the transmission cycle to adjust respective occurrence frequencies of the scheduled time periods over multiple instances of the transmission cycle.

US Patent:

20190287024, Sep 19, 2019

Filed:

Mar 11, 2019

Appl. No.:

16/298851

Inventors:

- San Francisco CA, US
James Allen-White Hoffacker - San Carlos CA, US
Dhruv Lamba - San Mateo CA, US
Yi Lu - San Jose CA, US
Phillip Sawbridge - Los Altos CA, US

International Classification:

G06N 20/20
H04N 19/105
G05D 1/00
G06T 5/00

Abstract:

In one embodiment, a computing system may receive an uncompressed image from a camera. The computing system may generate a compressed image by performing a compression process on the uncompressed image, wherein a decompressed image may be generated as a byproduct during the compression process. The computing system may send the decompressed image to a machine-learning model that was trained using decompressed images. The computing system may generate, by the machine-learning model, an output based on the decompressed image. The computing system may provide operational instructions to a vehicle based on the output.

US Patent:

20190289172, Sep 19, 2019

Filed:

Mar 11, 2019

Appl. No.:

16/298503

Inventors:

- San Francisco CA, US
Forrest Samuel Briggs - Palo Alto CA, US
George James Hansel - Redwood City CA, US
James Allen-White Hoffacker - San Carlos CA, US
Dhruv Lamba - San Mateo CA, US
Chi Hoon Lee - San Francisco CA, US
Yi Lu - San Jose CA, US
Brian Thomas McGinn - Burlingame CA, US
Phillip Sawbridge - Los Altos CA, US

International Classification:

H04N 5/06
H04N 5/247
H04N 5/232

Abstract:

In one embodiment, a method includes, by a computing device of a first sensor receiving synchronization information from a controller. The synchronization information being generated based on a clock of the controller. The method also includes determining, based on the synchronization information, a first offset between a first clock of the first sensor and the clock of the controller; storing the first offset; and synchronizing, based on the stored first offset and the first clock of the first sensor, a first data capture by the first sensor with a second data capture by a second sensor. The first data capture and the second data capture being requested by the controller.