Video Object Annotation System for Interactive Content

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for creating interactive video content are cumbersome and require significant manual configuration, limiting their production and distribution, especially in non-interactive platforms like televisions, where embedded interactivity has not become commonplace.

Innovation Solution

A video streaming system that includes an object annotation component to receive and aggregate user input for developing video content with annotated object features, enabling interactive object recognition and tracking across multiple frames, and integrating this functionality into video streaming sessions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If manual configuration and planning are used to create interactive video content, then the precision and control of interactive features can be improved, but the complexity and time required for production increases significantly

Engineering Contradiction:

Improveprecision of interactive featuresVSAvoidcomplexity of content production process

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system enables automated annotation of objects in video content using computer vision and machine learning algorithms. The system self-identifies and tags objects without requiring manual configuration, thereby maintaining precision while reducing production complexity and time

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Manual mechanical annotation processes are replaced with automated computational systems. The patent uses image recognition algorithms and AI models to automatically detect, track, and annotate objects in video frames, substituting human manual work with automated computational mechanisms

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Manufacturing precision

If manual configuration is used for interactive video content, then the quality and accuracy of object annotation can be improved, but the productivity and distribution speed decrease

Engineering Contradiction:

Improveaccuracy of object annotationVSAvoidproductivity of video content production

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The automated annotation system performs object identification and tagging autonomously using machine learning models, eliminating the need for manual annotation while maintaining high accuracy through trained algorithms and continuous learning

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system changes the operational parameters from manual human annotation to automated computational annotation. By adjusting the complexity and training of AI models, the system achieves high annotation accuracy while dramatically increasing production speed and throughput

Inventive Principle:

Principle #35Parameter changes

3Reliability

If extensive manual configuration is required, then the reliability and quality of interactive features can be improved, but the ease of operation and accessibility worsen

Engineering Contradiction:

Improvereliability of interactive featuresVSAvoidease of content creation

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system performs reliable object annotation automatically without requiring operators to manually configure each interactive feature. The automated system handles object detection, tracking, and tagging, making the process accessible to users without specialized knowledge while maintaining reliability through robust algorithms

Inventive Principle:

Principle #25Self-service

4Productivity

If automated object annotation is implemented, then the productivity and ease of operation can be improved, but the measurement precision and accuracy of object identification may worsen

Engineering Contradiction:

Improveproductivity of annotation processVSAvoidprecision of object identification

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

Manual annotation is replaced with automated computer vision systems that use trained machine learning models to identify and track objects. The system substitutes human visual inspection with computational image analysis, achieving both high productivity and maintained precision through algorithmic object recognition

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system adjusts parameters such as model complexity, training data quality, and detection thresholds to optimize the balance between processing speed and identification accuracy. By tuning these parameters, the system achieves high productivity while maintaining measurement precision

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS9118886B2Annotating general objects in video

Publication Date: 2015.08.25 HULU LLC

AI summary

A method for annotating general objects contained in video content is provided. The method sends video data to a client device and receives a first annotation from the client device defining a boundary around a portion of a first frame of the video data. Then, the first annotation is tracked through multiple frames of the video content. Other annotations determined to be associated with annotation that match the first annotation within a threshold are determined where the other annotations are received from other client devices and located in the first frame or other frames from the first frame. The method combines the other annotations and the first annotation into an object track and associates a tag with the object track. The tag is input by at least one of the client devices.