Repeating Object Controller for Media Stream Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing media stream identification and segmentation technologies rely on preexisting databases of pre-identified media objects, and they struggle with efficiently identifying and controlling repeating objects in noisy and distorted media streams, such as radio or television broadcasts, where objects are frequently corrupted by noise, foreshortened, or intentionally distorted.

Innovation Solution

A system and method that uses a 'repeating object controller' (ROC) in conjunction with an 'object extractor' to identify and segment repeating media objects within a media stream without a preexisting database, by comparing sections of the stream to locate matching portions, employing object-dependent algorithms, and computing fingerprints to determine object endpoints, allowing for real-time user control and interaction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional audio fingerprinting schemes are used to identify media objects, then identification accuracy is improved, but the system requires a preexisting database of pre-identified media objects which increases system complexity and limits adaptability to new or unknown objects

Engineering Contradiction:

Improveidentification accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs self-learning by automatically extracting features from media objects as they are encountered in the stream, building its own reference database without requiring preexisting external databases. The object identification module learns object characteristics in real-time through feature extraction and comparison, enabling it to identify both known and novel objects autonomously

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary feature extraction and database construction as media objects are encountered during stream processing. By continuously learning and storing object features in the reference database during normal operation, the system prepares identification capabilities in advance without requiring complex preconfigured databases

Inventive Principle:

Principle #10Preliminary action

2Reliability

If media stream sampling is performed over extended periods to improve identification accuracy, then object identification reliability is improved, but the time required to identify objects increases significantly

Engineering Contradiction:

Improveidentification reliabilityVSAvoididentification time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system extracts and compares only the most discriminative features from media objects rather than processing the entire stream uniformly. By selecting key acoustic features and using efficient comparison algorithms, the system achieves reliable identification with reduced computational time and faster response

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system dynamically adjusts the sampling rate and feature extraction intensity based on the current stream context and identification needs. The object identification module can operate in different modes, adapting the depth of analysis to balance between speed and accuracy based on real-time requirements

Inventive Principle:

Principle #15Dynamics

3Adaptability or versatility

If the system provides comprehensive user control options for repeating objects, then user interaction capability is improved, but the interface complexity and ease of operation deteriorates

Engineering Contradiction:

Improveuser control capabilityVSAvoidinterface ease of use

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system extracts and presents only the essential control functions for repeating objects, separating useful operations from unnecessary complexity. The user interface focuses on core capabilities like skipping, repeating, and controlling specific objects, removing extraneous features to maintain simplicity while providing targeted functionality

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system creates simplified representations of media objects through their acoustic fingerprints and key features, allowing users to identify and control objects based on these condensed representations rather than processing the complete complex stream data. This abstraction layer simplifies user interaction while maintaining full control capability

Inventive Principle:

Principle #26Copying

Data Source

PatentUS7523474B2System and method for providing user control over repeating objects embedded in a stream

Publication Date: 2009.04.21 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

Many media streams contain “objects” that repeat. Repeating objects in a media stream are defined as any section of non-negligible duration, i.e., a song, video, advertisement, jingle, etc., which would be considered to be a logical unit by a human listener or viewer. An “object controller” identifies such repeating objects as they occur, and provides an interactive user interface for allowing users to specify how individual repeating objects are to be handled either in real time, or upon subsequent occurrences of particular repeating objects. In general, the object controller includes a mechanism for identifying repeating objects, a mechanism for identifying temporal endpoints of those objects, a user interface for specifying actions to be taken when a particular object repeats within a media stream, and, in one embodiment, a buffer having sufficient length to allow for real-time deletion of objects from the media stream without obvious interruption in the stream.