Patent №
US 9,025,876
Granted
2015-05-05
Filed 2013
Owner
THOMSON LICENSING
Lab
—
AI components
4
ml · vision · kr · hardware
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
13786347
A method and an apparatus for multi-label segmentation of an image are described. First an energy function is determined for the image. Then for a homogeneous region of the image variables of the energy function are grouped to a single variable. Subsequently the energy function is minimized and labels are assigned to regions of the image based on the minimized energy function.
Machine learningVisionKnowledge representationAI hardwareG06T 7/11G06F 18/24G06T 7/162G06T 2207/20072
AI classification
Vision1.00
AI hardware0.99
Machine learning0.96
Knowledge representation0.72
Speech0.22
Evolutionary computation0.04
Natural language0.01
Planning0.01
Ownership
THOMSON LICENSING
assignment · 299320764
Assignors
SCHLOSSER, MARKUS, SCHEUERMANN, BJOERN, ROSENHAHN, BODO
On an employer assignment, the assignors are typically the inventors.
From the same owner
METHOD FOR RECOGNIZING AT LEAST ONE NATURALLY EMITTED SOUND PRODUCED BY A REAL-LIFE SOUND SOURCE IN AN ENVIRONMENT COMPRISING AT LEAST ONE ARTIFICIAL SOUND SOURCE, CORRESPONDING APPARATUS, COMPUTER PROGRAM PRODUCT AND COMPUTER-READABLE CARRIER MEDIUM.US 11,930,332 · 2024METHODS AND APPARATUS FOR DECODING A COMPRESSED HOA SIGNALUS 11,830,504 · 2023REDUCING REDUNDANCY BETWEEN TREE TYPESUS 11,818,349 · 2023METHOD AND A DEVICE FOR PICTURE ENCODING AND DECODINGUS 11,811,975 · 2023METHOD AND DEVICE FOR DEBLOCKING FILTERING A BOUNDARY WITHIN AN INTRA PREDICTED BLOCKUS 11,812,060 · 2023METHODS, DEVICES AND STREAM TO ENCODE GLOBAL ROTATION MOTION COMPENSATED IMAGESUS 11,812,066 · 2023METHOD FOR GENERATING LAYERED DEPTH DATA OF A SCENEUS 11,803,980 · 2023METHOD FOR ENCODING AND/OR DECODING IMAGES ON MACROBLOCK LEVEL USING INTRA-PREDICTIONUS 11,792,427 · 2023