IDENTIFYING SCENE BOUNDARIES USING GROUP SPARSITY ANALYSIS

Patent №

US 8,989,503

Granted

2015-03-24

Filed 2012

Owner

EASTMAN KODAK

Lab

AI components

4

ml · vision · kr · planning

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

13565919

A method for identifying a set of key video frames from a video sequence comprising extracting feature vectors for each video frame and applying a group sparsity algorithm to represent the feature vector for a particular video frame as a group sparse combination of the feature vectors for the other video frames. Weighting coefficients associated with the group sparse combination are analyzed to determine video frame clusters of temporally-contiguous, similar video frames. The video sequence is segmented into scenes by identifying scene boundaries based on the determined video frame clusters.

Machine learningVisionKnowledge representationPlanningG06V 20/47G06F 18/2136G06V 10/7715G06V 20/49G06V 10/513

AI classification

Vision1.00
Knowledge representation0.98
Planning0.82
Machine learning0.61
AI hardware0.02
Natural language0.00
Speech0.00
Evolutionary computation0.00

Ownership

EASTMAN KODAK

assignment · 289660915

Assignors

KUMAR, MRITYUNJAY, LOUI, ALEXANDER C., PILLMAN, BRUCE HAROLD

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC