Camera Network Topology for GPS-Free Object Tracking

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing surveillance systems that use camera networks for object tracking rely on GPS and GIS positioning information, which can be unreliable and insufficient for accurate tracking, especially when GPS/GIS techniques fail, and require cameras with built-in GPS/GIS devices.

Innovation Solution

A system that generates topological data for camera networks based on object motion information, allowing for object tracking and monitoring without relying on GPS/GIS data, by determining motion directions and neighboring cameras to relay tracking tasks across multiple cameras.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If GPS and GIS positioning information is used for object tracking, then tracking coverage can be extended, but tracking reliability deteriorates when GPS/GIS techniques fail

Engineering Contradiction:
Improvetracking coverageVSAvoidtracking reliability
Core Design Contradiction:
Area of stationary objectVSReliability

Solution Approach 1:

The patent introduces topological data as an intermediary between cameras and objects for tracking. Instead of relying on GPS/GIS positioning, the system uses topological relationships (neighborhood relationships) between cameras to track objects. The topological data includes camera identifiers, neighborhood relationships, and field of view information, which serve as a mediator to achieve reliable tracking without GPS dependency.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If cameras with built-in GPS/GIS devices are used, then positioning accuracy is improved, but device complexity increases

Engineering Contradiction:
Improvepositioning accuracyVSAvoidcamera system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts the positioning function from the camera hardware itself. Instead of having cameras with built-in GPS/GIS devices, the system separates positioning functionality into a independent topological data structure. The cameras only need to provide image data and basic identification information, while the topological relationships and positioning logic are handled externally through the generated topological data.

Inventive Principle:
Principle #2Taking out (Extraction)

3Reliability

If topological data generation is added to the system, then tracking reliability without GPS is improved, but system complexity increases

Engineering Contradiction:
ImproveGPS-free tracking reliabilityVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-generating and storing topological data before actual tracking operations. The topological data, including camera neighborhood relationships and field of view information, is prepared in advance and can be updated periodically or when changes occur. This preliminary preparation eliminates the need for complex real-time calculations during tracking, reducing operational complexity while maintaining high reliability.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11647163B2Methods and systems for object monitoring
Publication Date: 2023.05.09 ZHEJIANG DAHUA TECH CO LTD
  • US11647163B2 patent drawing
  • US11647163B2 patent drawing
  • US11647163B2 patent drawing

AI summary

According to various aspects of the present disclosure, methods, systems, and media for object tracking are provided. In some embodiments, the systems may include: at least one hardware processor to: detect a target object in first image data provided by a first camera; determine a first plurality of neighboring cameras of the first camera that have detected the target object; determine at least one of the first plurality of neighboring cameras as a next node of the first camera; and generate first topological data for the first camera and the next node of the first camera.