Multi-angle Video Object Detection and Angle Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing video recording technologies do not effectively allow users to seamlessly switch between multiple angles of the same event, limiting user control and customization in viewing experiences.

Innovation Solution

A method and system that identify objects-of-interest in multiple videos captured from different angles and allow users to select and switch between these angles dynamically, providing optimal presentation and alternative viewing options based on user selection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple video angles are recorded and stored, then viewing options and user control are improved, but system complexity and data management burden increase

Engineering Contradiction:

Improveviewing optionsVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system segments the multi-angle video content by identifying and separating objects-of-interest from different video sources. Each object is tagged with metadata indicating which video angles contain it, allowing the system to serve specific video segments based on user selection rather than managing complete multi-angle video files.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary layer of object-based metadata and selection logic between the stored video files and the user interface. This intermediary layer processes user selections and automatically determines which video angle to display, simplifying the user interaction while managing the complexity of multiple video sources.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Ease of operation

If automatic video angle selection is implemented, then user interaction simplicity is improved, but loss of user control and customization decreases

Engineering Contradiction:

Improveuser interaction simplicityVSAvoiduser control

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The system provides feedback to users by displaying information about available video angles and objects-of-interest. Users can see what objects are detected and which angles are available, then make informed selections. The system responds to user selections by automatically switching to the appropriate video angle, combining automation with user control.

Inventive Principle:

Principle #23Feedback

3Loss of information

If real-time object identification and video switching is implemented, then viewing experience relevance is improved, but processing time and computational resources increase

Engineering Contradiction:

Improveviewing experience relevanceVSAvoidprocessing time

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The system performs preliminary action by pre-identifying and tagging objects-of-interest in video content before user viewing. Metadata about objects and their locations in different video angles is prepared in advance, allowing rapid retrieval and switching when users make selections without requiring real-time analysis during viewing.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS8805158B2Video viewing angle selection

Publication Date: 2014.08.12 NOKIA TECHNOLOGIES OY

AI summary

A method including identifying a plurality of common objects-of-interest in each of a plurality of videos, where each of the plurality of videos has a different viewing angle of the plurality of objects-of-interest; and automatically selecting a first one of the videos to send to a user based, at least partially, upon a selection by the user of one of the objects-of-interest.