Cross-Camera Object Tracking Using Biometric Identifiers

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional tracking systems require cumbersome setup processes and high processing and memory requirements, especially with multiple cameras, making them inefficient for tracking objects across different video streams.

Innovation Solution

A video surveillance system that generates a unique biometric identifier for an object of interest, allowing seamless tracking across multiple video streams by comparing candidate identifiers and automatically switching the primary viewing stream to the object's current location.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional tracking systems are used with multiple cameras, then object tracking capability is provided, but setup complexity and processing requirements increase significantly

Engineering Contradiction:
Improveobject tracking capabilityVSAvoidsetup complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system segments the tracking task by assigning each camera its own video stream processing, extracting features independently at each camera location. This distributed approach reduces the complexity of coordinating multiple cameras while maintaining comprehensive object tracking capability across the entire environment.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system introduces a feature database as an intermediary that stores extracted features from each camera. This database acts as a mediator between cameras, enabling object tracking across multiple views without requiring direct coordination between cameras or complex pre-programming of movement vectors.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If conventional tracking systems process multiple video streams, then comprehensive object monitoring is achieved, but processing power and memory requirements increase

Engineering Contradiction:
Improvecomprehensive object monitoringVSAvoidprocessing power requirements
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system extracts only the essential features from each video stream (such as object appearance, position, and characteristics) rather than processing the entire video data. These extracted features are stored in a database and compared to identify tracked objects, significantly reducing processing power and memory requirements while maintaining reliable comprehensive monitoring.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs partial processing by extracting and storing only the necessary feature information from each camera stream rather than processing all video data in detail. This partial action approach reduces computational burden while sufficient for reliable object tracking across multiple cameras.

Inventive Principle:
Principle #16Partial or excessive action

3Area of stationary object

If cameras are positioned to cover all areas with minimal overlap, then comprehensive coverage is achieved, but system setup becomes cumbersome

Engineering Contradiction:
Improveenvironment coverageVSAvoidcamera placement complexity
Core Design Contradiction:
Area of stationary objectVSEase of manufacture

Solution Approach 1:

The system makes each camera multi-functional by enabling any camera to potentially capture the object of interest. Rather than requiring precise coordination and specific positioning, the system allows cameras to be placed more flexibly while still achieving comprehensive coverage through the feature extraction and database comparison mechanism that works across all camera views.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP4407569B1Systems and methods for tracking objects
Publication Date: 2025.12.24 JOHNSON CONTROLS TYCO IP HLDG LLP
  • EP4407569B1 patent drawingFigure 1
  • EP4407569B1 patent drawingFigure 2
  • EP4407569B1 patent drawingFigure 3

AI summary

Example implementations include a method, apparatus and computer-readable medium in a video surveillance system for tracking an of-interest (OI) object, comprising receiving, from a user interface, a request to track an object in a first video stream from a plurality of video streams captured from a first camera of a plurality of cameras installed in an environment. The implementations further include extracting at least one image of the object from the first video stream. Additionally, the implementations further include generating a unique biometric identifier of the object based on the at least one image. Additionally, the implementations further include detecting, using the unique biometric identifier, the object in a second video stream captured from a second camera of the plurality of cameras, and outputting, on the user interface, the second video stream in response to detecting the object in the second video stream.