Mobile Visual Media Identification via Quadrilateral Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current technologies face challenges in efficiently identifying and capturing visual media content using camera-enabled mobile devices, particularly due to complications in orientation and extraneous images within the field of view, limiting convenient access and retrieval of media content on the go.

Innovation Solution

A method and system that utilize a camera-enabled mobile device to detect a quadrilateral representing an external display, capture and analyze visual media content, and identify it against a database, allowing for seamless retrieval and continuation of media consumption on the mobile device, employing techniques like histogram analysis, corner detection, and Scale Invariant Feature Transform (SIFT) for accurate recognition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If automated vision recognition is performed on media content using a mobile device camera, then users can capture and identify visual media content on the go, but the process becomes complicated by orientation issues and extraneous images within the field of view

Engineering Contradiction:
Improveconvenience of capturing and retrieving media contentVSAvoidcomplexity of image processing and identification
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent segments the captured image into multiple regions of interest (ROIs) based on detected features such as text, logos, or visual elements. By dividing the complex image processing task into smaller regional analyses, the system simplifies the overall complexity while maintaining ease of operation for content identification.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts specific regions of interest from the captured image that contain the media content, separating them from extraneous background elements. This extraction process removes distracting elements and focuses processing on relevant content, reducing complexity while improving operational ease.

Inventive Principle:
Principle #2Taking out (Extraction)

2Measurement precision

If high fidelity sampling and analysis of video content is performed, then accurate identification of media content is achieved, but the processing requires high processing capacity and is not suitable for mobile devices

Engineering Contradiction:
Improveaccuracy of media content identificationVSAvoidprocessing capacity requirement
Core Design Contradiction:
Measurement precisionVSPower

Solution Approach 1:

The patent applies local quality by performing high-precision analysis only on specific regions of interest within the captured image, rather than processing the entire image at high fidelity. This allows accurate identification of media content while reducing overall processing requirements to levels suitable for mobile devices.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent performs partial action by selectively processing only the portions of the image that contain media content indicators (such as text regions, logos, or key visual elements) rather than analyzing the entire image. This partial processing maintains identification accuracy while significantly reducing power requirements.

Inventive Principle:
Principle #16Partial or excessive action

3Reliability

If the entire captured image is analyzed for media content identification, then comprehensive recognition is achieved, but extraneous images and orientation issues complicate the process

Engineering Contradiction:
Improvecompleteness of media content recognitionVSAvoiddifficulty of identifying relevant content amid extraneous images
Core Design Contradiction:
ReliabilityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent performs preliminary action by pre-processing the captured image to detect and mark regions of interest before the main identification process. This preliminary step organizes the image data, identifies potential media content areas, and prepares the image for more efficient analysis, reducing the difficulty of detecting relevant content among extraneous elements.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary processing step that acts as a mediator between the captured image and the final identification process. This intermediary layer detects and extracts regions of interest, effectively filtering out extraneous images and orienting relevant content, thereby simplifying the detection process while maintaining comprehensive recognition.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP2601616B1Identifying visual media content captured by camera-enabled mobile device
Publication Date: 2020.06.03 QUALCOMM INC
  • EP2601616B1 patent drawingFigure 1
  • EP2601616B1 patent drawingFigure 2
  • EP2601616B1 patent drawingFigure 3A

AI summary

Automatic identification of media content is at least partially based upon visually capturing a still or video image of media content being presented to a user via another device. The media content can be further refined by determining location of the user, capturing an audio portion of the media content, date and time of the capture, or profile/behavioral characteristics of the user. Identifying the media content can require (1) distinguishing a rectangular illumination the corresponds to a video display; (2) decoding a watermark presented within the displayed image/video; (3) characterizing the presentation sufficiently for determining a particular time stamp or portion of a program; and (4) determining user setting preferences for viewing the program (e.g., close captioning, aspect ratio, language). Thus identified, the media content appropriately formatted can be received for continued presentation on a user interface of the mobile device.