Bernd Heisele

US Patent:

7734071, Jun 8, 2010

Filed:

Jun 30, 2004

Appl. No.:

10/882981

Inventors:

Bernd Heisele - Cambridge MA, US

Assignee:

Honda Motor Co., Ltd. - Tokyo

International Classification:

G06K 9/00

US Classification:

382118, 382155, 382227

Abstract:

Systems and methods are presented that determine components to use as examples to train a component-based face recognition system. In one embodiment, an initial component shape and size is determined, a training set is built, a component recognition classifier is trained, and the accuracy of the classifier is estimated. The component is then temporarily grown in each of four directions (up, down, left, and right) and the effect on the classifier's accuracy is determined. The component is then grown in the direction that maximizes the classifier's accuracy. The process can be performed multiple times in order to maximize the classifier's accuracy.

US Patent:

7783082, Aug 24, 2010

Filed:

Jun 30, 2004

Appl. No.:

10/561256

Inventors:

Takamasa Koshizen - Wako, JP
Bernd Heisele - Cambridge MA, US
Hiroshi Tsujino - Wako, JP

Assignee:

Honda Motor Co., Ltd. - Tokyo

International Classification:

G06K 9/00

US Classification:

382118, 382115, 382116, 382155, 382159

Abstract:

A face recognition system includes a component learning/extraction module, component classifier training module, knowledge base for component classification (KBCC), component extraction module (CEM), object identification training module (OITM), knowledge base for face identification (KBFI), and object identification module (OIM). The CEM receives image data of faces at various viewpoints and extracts outputs of classification of the component data, using the results of classifier training of the component data, stored in the KBCC. The OITM receives the outputs of classification of the component data and determines indicator component for each person by Bayesian estimation so that posterior probability of a predetermined attention class is maximized under the outputs of classification of the component data at various viewpoints. The KBFI stores indicator components for the individuals. The OIM receives the outputs of classification of the component data and identifies faces using the indicator components stored in the KBFI.

US Patent:

8422797, Apr 16, 2013

Filed:

Jun 30, 2010

Appl. No.:

12/827185

Inventors:

Bernd Heisele - Mountain View CA, US
Gunhee Kim - Pittsburgh PA, US
Andrew J. Meyer - Cambridge MA, US

Assignee:

Honda Motor Co., Ltd. - Tokyo

International Classification:

G06K 9/62

US Classification:

382224, 382159

Abstract:

An “active learning” method trains a compact classifier for view-based object recognition. The method actively generates its own training data. Specifically, the generation of synthetic training images is controlled within an iterative training process. Valuable and/or informative object views are found in a low-dimensional rendering space and then added iteratively to the training set. In each iteration, new views are generated. A sparse training set is iteratively generated by searching for local minima of a classifier's output in a low-dimensional space of rendering parameters. An initial training set is generated. The classifier is trained using the training set. Local minima are found of the classifier's output in the low-dimensional rendering space. Images are rendered at the local minima. The newly-rendered images are added to the training set.

US Patent:

20060210125, Sep 21, 2006

Filed:

Mar 16, 2006

Appl. No.:

11/376895

Inventors:

Bernd Heisele - Cambridge MA, US

International Classification:

G05B 19/00
G06K 9/00
H04K 1/00

US Classification:

382118000, 340005520, 340005530, 713186000

Abstract:

A method is disclosed which matches a description of a face with face images in a database. A service/system for dating/matchmaking is disclosed in which a partner profiles comprises a description of a face and a member profile comprises one or multiple image/s of a face. The matching between partner and member profiles comprises a method which matches the description of a face in the partner profile with the face images in the member profiles.

US Patent:

20070179918, Aug 2, 2007

Filed:

Feb 2, 2006

Appl. No.:

11/347422

Inventors:

Bernd Heisele - Cambridge MA, US
Yoav Sharon - Rehovot, IL

International Classification:

G06N 3/12

US Classification:

706013000

Abstract:

Object recognition techniques are disclosed that provide both accuracy and speed. One embodiment of the present invention is an identification system. The system is capable of locating objects in images by searching for local features of an object. The system can operate in real-time. The system is trained from a set of images of an object or objects. The system computes interest points in the training images, and then extracts local image features (tokens) around these interest points. The set of tokens from the training images is then used to build a hierarchical model structure. During identification/detection, the system, computes interest points from incoming target images. The system matches tokens around these interest points with the tokens in the hierarchical model. Each successfully matched image token votes for an object hypothesis at a certain scale, location, and orientation in the target image. Object hypotheses that receive insufficient votes are rejected.

US Patent:

20100121794, May 13, 2010

Filed:

Jan 22, 2010

Appl. No.:

12/692475

Inventors:

Bernd Heisele - Cambridge MA, US
Yoav Sharon - Rehovot, IL

Assignee:

Honda Motor Co., Ltd. - Tokyo

International Classification:

G06N 7/00

US Classification:

706 13, 706 20, 706 12

Abstract:

Object recognition techniques are disclosed that provide both accuracy and speed. One embodiment of the present invention is an identification system. The system is capable of locating objects in images by searching for local features of an object. The system can operate in real-time. The system is trained from a set of images of an object or objects. The system computes interest points in the training images, and then extracts local image features (tokens) around these interest points. The set of tokens from the training images is then used to build a hierarchical model structure. During identification/detection, the system computes interest points from incoming target images. The system matches tokens around these interest points with the tokens in the hierarchical model. Each successfully matched image token votes for an object hypothesis at a certain scale, location, and orientation in the target image. Object hypotheses that receive insufficient votes are rejected.

US Patent:

20180336697, Nov 22, 2018

Filed:

May 22, 2017

Appl. No.:

15/601638

Inventors:

- Tokyo, JP
Jiawei Huang - Raymond OH, US
Yi-Ting Chen - Sunnyvale CA, US
Bernd Heisele - Mountain View CA, US

International Classification:

G06T 7/73
G01S 17/89

Abstract:

The present disclosure relates to methods and systems for monocular localization in urban environments. The method may generate an image from a camera at a pose. The method may receive a pre-generated map, and determine features from the generated image based on edge detection. The method may predict a pose of the camera based on at least the pre-generated map, and determine features from the predicted camera pose. Further, the method may determine a Chamfer distance based upon the determined features from the image and the predicted camera pose, optimize the determined Chamfer distance based upon odometry information and epipolar geometry. Upon optimization, the method may determine an estimated camera pose.

US Patent:

20180005025, Jan 4, 2018

Filed:

Aug 30, 2017

Appl. No.:

15/690394

Inventors:

- Tokyo, JP
Kai-Chi Chan - West Lafayette IN, US
Bernd Heisele - Mountain View CA, US

International Classification:

G06K 9/00
G06K 9/46
G06K 9/62

Abstract:

A method for partially occluded object detection includes obtaining a response map for a detection window of an input image, the response map based on a trained model and including a root layer and a parts layer. The method includes determining visibility flags for each root cell of the root layer and each part of the parts layer. The visibility flag is one of visible or occluded. The method includes determining an occlusion penalty for each root cell with a visibility flag of occluded and for each part with a visibility flag of occluded. The occlusion penalty is based on a location of the root cell or the part with respect to the detection window. The method determines a detection score for the detection window based on the visibility flags and the occlusion penalties and generates an estimated visibility map for object detection based on the detection score.