Movable Imaging Subject Tracking via Predictive Region of Interest

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing subject tracking systems for movable imaging platforms face challenges in accurately tracking subjects, especially when the operator is also the subject, and in ensuring safety and robust operation, particularly in dynamic environments where manual control is difficult and complex.

Innovation Solution

The system employs a movable imaging assembly with a camera and a controller connected via a wireless link, using motion models and sensors to predict subject location, define movement constraints, and implement voice command recognition, while limiting motion within predefined volumes to ensure safety and robust tracking.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual controls are used to provide tracking commands to the movable imaging platform, then the operator can control the imaging system, but the operation becomes too difficult and complex when the operator is also the subject to be tracked

Engineering Contradiction:

Improveease of operationVSAvoidcomplexity of manual controls

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The system automatically tracks the subject without requiring manual intervention. The movable imaging platform autonomously adjusts its position and orientation to keep the subject within the region of interest, eliminating the need for the operator to manually control the platform while also being the subject

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical control with an automated system that uses sensors, processors, and control algorithms to generate tracking commands. The system substitutes human-operated mechanical controls with an automated control loop that continuously adjusts the platform based on subject position detection

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If the tracking system operates over a large region to ensure robust tracking, then the tracking function is more reliable, but the safety of the user may be compromised

Engineering Contradiction:

Improverobustness of tracking systemVSAvoidsafety risks

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The operating space is divided into multiple defined volumes with different safety characteristics and operational permissions. The system segments the three-dimensional space into restricted zones, allowable zones, and target zones, enabling the platform to operate robustly within safe boundaries while maintaining reliable tracking functionality

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces defined volumes as intermediary spatial boundaries between the tracking target and the operator/safe zones. These volumetric boundaries act as mediators that constrain the platform's movement to safe regions while still allowing effective tracking, preventing direct proximity to the operator

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If the system searches the entire image frame to locate the subject, then the tracking is thorough, but the computational resources and time required increase significantly

Engineering Contradiction:

Improveaccuracy of subject locationVSAvoidtime to locate subject

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by predicting the subject's future position within a region of interest before actually searching for the subject in the current frame. This predictive approach pre-establishes the search area based on motion models and previous subject positions, eliminating the need to search the entire frame

Inventive Principle:

Principle #10Preliminary action

4Reliability

If the system uses a large search region to ensure the subject is found, then the tracking is reliable, but the computational resources and processing time increase

Engineering Contradiction:

Improvereliability of subject trackingVSAvoidcomputational efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system applies local quality by concentrating computational resources on a localized region of interest rather than uniformly processing the entire image frame. The region of interest is dynamically adjusted based on predicted subject position, allowing reliable tracking while minimizing computational workload to only the necessary local area

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS10636150B2Subject tracking systems for a movable imaging system

Publication Date: 2020.04.28 GOPRO INC

AI summary

A method for tracking a subject in successive image frames includes obtaining previous image frames with an imaging device, processing the previous image frames, obtaining motion information of the imaging device and a subject, determining a region of interest, obtaining a subsequent image frame, and processing the region of interest. The processing includes determining previous frame positions of the subject therein. The motion information is obtained with sensors physically associated with one or more of the imaging device and the subject. The region of interest is located in a predetermined spatial relationship relative to a predicted frame position of the subject.