Computer Vision Gimbal Tracking for GPS Obstruction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional GPS-enabled tracking systems for capturing dynamic subjects in three-dimensional spaces face limitations, such as dependency on GPS signals, obstructions, and the need for the subject to carry a tracking device, leading to inaccuracies and difficulties in capturing movements in complex environments.

Innovation Solution

A system comprising a pivoting device (gimbal) with a camera, a main computing system, and a gimbal stabilizer controller, which uses computer vision algorithms and object detection methods to track subjects in 3D spaces, allowing for real-time adjustments and stabilization of the camera's position and orientation, independent of the cameraperson's expertise.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If GPS-enabled tracking system is used, then location tracking is enabled, but accuracy deteriorates due to obstructions and multipath errors in three-dimensional spaces

Engineering Contradiction:
Improvetracking reliabilityVSAvoidlocation accuracy
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent replaces GPS-based tracking with a computer vision-based tracking system. Instead of relying on satellite signals and GPS receivers, the system uses cameras to capture images and computer vision algorithms to detect and track the target's position and orientation in three-dimensional space, eliminating GPS-related accuracy issues in obstructed environments

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces computer vision algorithms as an intermediary between the camera and the tracking system. The algorithms process camera images to extract target position and orientation data, serving as a mediator that enables accurate tracking without direct GPS signal dependency

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If subject carries tracking device, then tracking capability is enabled, but ease of operation deteriorates due to complexity of setup and operation

Engineering Contradiction:
Improvetracking capabilityVSAvoidoperation simplicity
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent inverts the traditional tracking approach by placing the camera on the tracking device (camera mount) rather than requiring the subject to carry a GPS receiver or tracking device. The camera-mounted system passively observes and tracks the subject, eliminating the need for subject involvement in the tracking process

Inventive Principle:
Principle #13The other way round (Inversion)

Solution Approach 2:

The computer vision system automatically detects, identifies, and tracks the target without requiring manual intervention or subject cooperation. The system self-adjusts to maintain target acquisition, performing the tracking function autonomously once the camera is positioned

Inventive Principle:
Principle #25Self-service

3Reliability

If conventional camera tracking is used, then capturing capability is enabled, but productivity deteriorates due to need for expert cameraperson

Engineering Contradiction:
Improvecapturing capabilityVSAvoidoperational efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The camera mount system with computer vision algorithms performs automatic target tracking and positioning without requiring skilled operation. The system autonomously adjusts camera orientation to follow the target, eliminating the need for expert camerapersons and enabling untrained users to achieve professional-quality tracking shots

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces manual camera operation with automated computer vision-based control. Instead of relying on a cameraperson's expertise to manually track and frame the subject, the system uses image processing algorithms to automatically determine and execute the optimal camera positioning and orientation

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10095942B2Vision based real-time object tracking system for robotic gimbal control
Publication Date: 2018.10.09 REFLEX ROBOTICS
  • US10095942B2 patent drawing
  • US10095942B2 patent drawing
  • US10095942B2 patent drawing

AI summary

Using various embodiments, methods, systems, and apparatuses for controlling a camera pivoting device (e.g., mechanical gimbal) are described. In one embodiment, the system comprises a main computing device, a gimbal stabilizer controller, and a computer vision camera, and/or a user camera. The system is able to track a target object using the computer vision camera even while the target object is moving, the base of the pivoting device is moving (e.g., when a user controlling the camera moves), or a combination of thereof. The camera pivoting device of the embodiments disclosed herein can be mounted on to any number of devices/objects that can provide mobility and/or transportation.