Object Tracking via Segmented Image Tiles and Ellipse Models

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional approaches for object tracking in computing devices, such as head tracking, are resource-intensive and prone to false positives due to the need to analyze full-resolution images, which can drain battery power and reduce accuracy.

Innovation Solution

A method using a two-dimensional model, like an ellipse, to approximate objects of interest in images, combined with distance information from stereoscopic or proximity sensors to segment foreground from background, allowing for efficient object tracking by processing only relevant image segments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If full resolution images are analyzed for object tracking, then tracking accuracy is improved, but processing load and battery consumption increase

Engineering Contradiction:
Improvetracking accuracyVSAvoidbattery consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent segments the image processing task by dividing the full-resolution image into multiple lower-resolution tiles or regions. Each tile is processed independently for object tracking, allowing the system to maintain acceptable tracking accuracy while significantly reducing the computational load and energy consumption associated with processing the entire high-resolution image at once.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies partial action by processing only a subset of image data at full resolution - specifically, once objects are detected in lower-resolution tiles, full-resolution analysis is applied only to those specific regions containing detected objects, rather than analyzing the entire image at full resolution. This selective approach maintains accuracy for relevant objects while minimizing overall processing requirements.

Inventive Principle:
Principle #16Partial or excessive action

2Measurement precision

If full resolution images are analyzed for object tracking, then tracking accuracy is improved, but processing speed decreases

Engineering Contradiction:
Improvetracking accuracyVSAvoidprocessing speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent segments the image processing task by dividing the full-resolution image into multiple lower-resolution tiles or regions. Each tile is processed independently for object tracking, allowing the system to maintain acceptable tracking accuracy while significantly reducing the computational load and energy consumption associated with processing the entire high-resolution image at once.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies partial action by processing only a subset of image data at full resolution - specifically, once objects are detected in lower-resolution tiles, full-resolution analysis is applied only to those specific regions containing detected objects, rather than analyzing the entire image at full resolution. This selective approach maintains accuracy for relevant objects while minimizing overall processing requirements.

Inventive Principle:
Principle #16Partial or excessive action

3Use of energy by moving object

If lower resolution cameras and algorithms are used, then processing load is reduced, but false positives increase and accuracy decreases

Engineering Contradiction:
Improveprocessing loadVSAvoidfalse positive rate
Core Design Contradiction:
Use of energy by moving objectVSReliability

Solution Approach 1:

The patent segments the image processing task by dividing the full-resolution image into multiple lower-resolution tiles or regions. Each tile is processed independently for object tracking, allowing the system to maintain acceptable tracking accuracy while significantly reducing the computational load and energy consumption associated with processing the entire high-resolution image at once.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent merges the results from multiple lower-resolution tile analyses with selective full-resolution verification. By combining the broad coverage of low-resolution processing with targeted high-resolution validation of detected objects, the system achieves both low processing load and low false positive rates.

Inventive Principle:
Principle #5Merging (Combining)

4Measurement precision

If full resolution images are continuously analyzed, then tracking precision is improved, but battery life decreases

Engineering Contradiction:
Improvetracking precisionVSAvoidbattery life
Core Design Contradiction:
Measurement precisionVSDuration of action of stationary object

Solution Approach 1:

The patent segments the image processing task by dividing the full-resolution image into multiple lower-resolution tiles or regions. Each tile is processed independently for object tracking, allowing the system to maintain acceptable tracking accuracy while significantly reducing the computational load and energy consumption associated with processing the entire high-resolution image at once.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies partial action by processing only a subset of image data at full resolution - specifically, once objects are detected in lower-resolution tiles, full-resolution analysis is applied only to those specific regions containing detected objects, rather than analyzing the entire image at full resolution. This selective approach maintains accuracy for relevant objects while minimizing overall processing requirements.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS9792491B1Approaches for object tracking
Publication Date: 2017.10.17 AMAZON TECH INC
  • US9792491B1 patent drawing
  • US9792491B1 patent drawing
  • US9792491B1 patent drawing

AI summary

The location of a user's head, for purposes such as head tracking or motion input, can be determined using a two-step process. In a first step, at least one image is captured including a representation of at least a portion of the person, such as a head portion of the person. In a second step, a contour of the head portion can be determined, and a two-dimensional model, for example, an ellipse or other similar shape can be used to approximate the head portion of the person represented in the image. The ellipse, for example, can be modeled using a number of shapes, such as rectangles, and the portion of the person can be tracked by locating an ellipse that bounds a maximum intensity gradient of pixel values in each one of a series of images.