Depth-Based Visual Search Area for Lower-Cost Image Extraction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Extracting information from entire images using electronic devices with cameras is computationally expensive.

Innovation Solution

Selecting a portion of the image based on the user's gaze location and distance to an object in the physical environment for processing, reducing computational load.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If information extraction is performed on the entire image, then comprehensive information can be obtained, but computational cost increases significantly

Engineering Contradiction:
Improveinformation extraction completenessVSAvoidcomputational cost
Core Design Contradiction:
Loss of informationVSUse of energy by moving object

Solution Approach 1:

The patent divides the image processing task into two segments: first processing a depth map to identify a search area, then processing only that specific region in the color image. This segmentation reduces the amount of data requiring intensive computational processing while ensuring relevant information is extracted.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies different processing quality and intensity to different regions of the image. The identified search area receives full processing attention for information extraction, while the rest of the image receives minimal or no processing, optimizing computational resource allocation based on local importance.

Inventive Principle:
Principle #3Local quality

2Loss of information

If the entire image is processed for information extraction, then all potential information is captured, but processing time increases

Engineering Contradiction:
Improveinformation extraction completenessVSAvoidprocessing time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The patent segments the processing workflow into rapid depth map analysis followed by targeted color image processing of only the relevant search area. This approach significantly reduces total processing time compared to analyzing the entire color image, while maintaining information extraction completeness within the area of interest.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary processing of the depth map to identify the search area before processing the color image. This preliminary action enables subsequent focused processing, reducing overall processing time while ensuring no relevant information is missed in the final extraction phase.

Inventive Principle:
Principle #10Preliminary action

3Device complexity

If a fixed search area is used, then processing is simplified, but adaptability to different scenarios is reduced

Engineering Contradiction:
Improveprocessing complexityVSAvoidsearch area adaptability
Core Design Contradiction:
Device complexityVSAdaptability or versatility

Solution Approach 1:

The patent implements a dynamic search area determination mechanism that adapts to different scenarios. The system calculates the search area based on depth information and adjusts its boundaries according to the specific context, maintaining low complexity through algorithmic adaptability rather than multiple fixed configurations.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the parameters defining the search area (position, size, shape) based on depth map analysis and scene characteristics. This allows the system to adapt to different scenarios by modifying search area parameters dynamically, balancing processing simplicity with scenario-specific adaptability.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS12469246B1Depth-based visual search area
Publication Date: 2025.11.11 APPLE INC
  • US12469246B1 patent drawing
  • US12469246B1 patent drawing
  • US12469246B1 patent drawing

AI summary

In one implementation, a method of extracting information from a physical environment is performed at a device including an image sensor, one or more processors, and non-transitory memory. The method includes determining a gaze location and a distance to an object in a physical environment at the gaze location. The method includes selecting a field-of-view of the physical environment based on the gaze location and the distance to the object. The method includes obtaining, using the image sensor, an image corresponding to the field-of-view of the physical environment. The method includes extracting information from the image.