Piotr Dollar

US Patent:

20190228259, Jul 25, 2019

Filed:

Mar 29, 2019

Appl. No.:

16/370491

Inventors:

- Menlo Park CA, US
Ronan Stéfan Collobert - Mountain View CA, US
Piotr Dollar - San Mateo CA, US

International Classification:

G06K 9/62
G06N 20/00
G06N 3/04
G06N 5/04
G06K 9/00
G06K 9/46
G06N 3/08

Abstract:

In one embodiment, a plurality of patches of an image are processed using a first-pass of a first deep-learning model to generate object-level information for each of the patches. Each patch includes one or more pixels of the image. Using a second-pass of the first deep-learning model, a respective object proposal is generated for each of the plurality of patches of the image. The second-pass takes as input the first-pass output, and the generated respective object proposals comprise pixel-level information for each of the patches. Using a second deep-learning model, a respective score is computed for each object proposal. The second deep-learning model takes as input the first-pass output, and the object score includes a likelihood that the respective patch of the object proposal contains an entire object.

US Patent:

20180285686, Oct 4, 2018

Filed:

Dec 22, 2017

Appl. No.:

15/853290

Inventors:

- Menlo Park CA, US
Ronan Stéfan Collobert - Mountain View CA, US
Piotr Dollar - San Mateo CA, US

International Classification:

G06K 9/62
G06K 9/68
G06N 3/04
G06N 3/08
G06F 15/18

Abstract:

In one embodiment a plurality of patches of an image are processed, using a first set of layers of a convolutional neural network, to output a plurality of object proposals associated with the plurality of patches of the image. Each patch includes one or more pixels of the image. Each object proposal includes a prediction as to a location of an object in the respective patch. Using a second set of layers of the convolutional neural network, the plurality of object proposals outputted by the first set of layers are processed to generate a plurality of refined object proposals. Each refined object proposal includes pixel-level information for the respective patch of the image. The first layer in the second set of layers of the convolutional neural network takes as input the plurality of object proposals outputted by the first set of layers. Each layer after the first layer in the second set of layers takes as input the output of a preceding layer in the second set of layers combined with the output of a respective layer of the first set of layers.

US Patent:

20180197047, Jul 12, 2018

Filed:

Mar 6, 2018

Appl. No.:

15/913118

Inventors:

- Redmond WA, US
Piotr Dollar - Redmond WA, US
Wolf Kienzle - Bellevue WA, US
Mladen Radojevic - Valjevo, RS
Matthew S. Ashman - Seattle WA, US
Ivan Stojiljkovic - Belgrade, RS
Magdalena Vukosavljevic - Bellevue WA, US

Assignee:

Microsoft Technology Licensing, LLC - Redmond WA

International Classification:

G06K 9/62
G06K 9/00
G06T 7/73
G06F 3/01

Abstract:

A method of object detection includes receiving a first image taken from a first perspective by a first camera and receiving a second image taken from a second perspective, different from the first perspective, by a second camera. Each pixel in the first image is offset relative to a corresponding pixel in the second image by a predetermined offset distance resulting in offset first and second images. A particular pixel of the offset first image depicts a same object locus as a corresponding pixel in the offset second image only if the object locus is at an expected object-detection distance from the first and second cameras. The method includes recognizing that a target object is imaged by the particular pixel of the offset first image and the corresponding pixel of the offset second image.

US Patent:

20180189935, Jul 5, 2018

Filed:

Dec 20, 2017

Appl. No.:

15/849379

Inventors:

- Menlo Park CA, US
Michael F. Cohen - Seattle WA, US
Johannes Peter Kopf - Seattle WA, US
Piotr Dollar - San Mateo CA, US

International Classification:

G06T 5/00
G06N 99/00
G06T 7/13
G06T 5/20

Abstract:

Systems, methods, and non-transitory computer-readable media can generate an initial alpha mask for an image based on machine learning techniques. A plurality of uncertain pixels is defined in the initial alpha mask. For each uncertain pixel in the plurality of uncertain pixels, a binary value is assigned based on a nearest certain neighbor determination.

US Patent:

20170364771, Dec 21, 2017

Filed:

Jun 15, 2017

Appl. No.:

15/624643

Inventors:

Pedro Henrique Oliveira Pinheiro - Saint Sulpice, CH
Ronan Stéfan Collobert - Mountain View CA, US
Piotr Dollar - San Mateo CA, US

International Classification:

G06K 9/62
G06N 3/04
G06N 5/04
G06N 99/00

Abstract:

In one embodiment, a plurality of patches of an image are processed using a first deep-learning model to detect a plurality of features associated with the first patch of the image. Each patch includes one or more pixels of the image. Using a second deep-learning model, a respective object proposal is generated for each of the plurality of patches of the image. The second deep-learning model takes as input the plurality of detected features associated with the respective patch of the image, and each object proposal includes a prediction as to a location of an object in the patch. Using a third deep-learning model, a respective score is computed for each object proposal generated using the second deep-learning model. The third deep-learning model takes as input the plurality of detected features associated with the respective patch of the image, and the object score may include a likelihood that the patch contains an entire object.

US Patent:

20170132510, May 11, 2017

Filed:

Dec 28, 2015

Appl. No.:

14/981413

Inventors:

- Menlo Park CA, US
Oren Rippel - Brookline MA, US
Piotr Dollar - San Mateo CA, US
Lubomir Dimitrov Bourdev - Mountian View CA, US

International Classification:

G06N 3/08
H04L 29/08

Abstract:

In one embodiment, a method may include receiving a first content item. A first embedding of the first content item may be determined and may corresponds to a first point in an embedding space. The embedding space may include a plurality of second points corresponding to a plurality of second embeddings of second content items. The embeddings are determined using a deep-learning model. The points are located in one or more clusters in the embedding space, which are each associated with a class of content items. Locations of points within clusters may be based on one or more attributes of the respective corresponding content items. Second content items that are similar to the first content item may be identified based on the locations of the first point and the second points and on particular clusters that the second points corresponding to the identified second content items are located in.

US Patent:

20140376770, Dec 25, 2014

Filed:

Jun 25, 2013

Appl. No.:

13/926882

Inventors:

David Nister - Bellevue WA, US
Piotr Dollar - Redmond WA, US
Wolf Kienzle - Bellevue WA, US
Mladen Radojevic - Valjevo, RS
Matthew S. Ashman - Seattle WA, US
Ivan Stojiljkovic - Belgrade, RS
Magdalena Vukosavljevic - Bellevue WA, US

International Classification:

G06T 7/00
G06K 9/62
G06K 9/00

US Classification:

382103

Abstract:

A method of object detection includes receiving a first image taken by a first stereo camera, receiving a second image taken by a second stereo camera, and offsetting the first image relative to the second image by an offset distance selected such that each corresponding pixel of offset first and second images depict a same object locus if the object locus is at an assumed distance from the first and second stereo cameras. The method further includes locating a target object in the offset first and second images.

US Patent:

20140270489, Sep 18, 2014

Filed:

Mar 12, 2013

Appl. No.:

13/794857

Inventors:

- Redmond WA, US
Piotr Dollar - Redmond WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06K 9/62

US Classification:

382159

Abstract:

Various technologies described herein pertain to constructing mid-level sketch tokens for use in tasks, such as object detection and contour detection. Sketch patches can be extracted from binary images that comprise hand-drawn contours. The hand-drawn contours in the binary images can correspond to contours in training images. The sketch patches can be clustered to form sketch token classes. Moreover, color patches from the training images can be extracted and low-level features of the color patches can be computed. Further, a classifier that labels mid-level sketch tokens can be trained. Such training of the classifier can be through supervised learning of a mapping from the low-level features of the color patches to the sketch token classes.