Occupancy Detection Using Camera Visual Field Overlap

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Multiple image sensors with overlapping fields of vision often miscount occupants due to counting the same individual, leading to inaccurate occupancy detection in areas.

Innovation Solution

A system and method that determine whether multiple luminaire-integrated cameras have a common visual field, allowing for accurate identification of shared or distinct occupants by processing visual data and comparing movement directions and pixel mappings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If multiple image sensors are used to monitor the same area, then the coverage area is improved, but the measurement precision deteriorates due to duplicate counting of the same occupant

Engineering Contradiction:
Improvecoverage areaVSAvoidoccupant count accuracy
Core Design Contradiction:
Area of stationary objectVSMeasurement precision

Solution Approach 1:

The system segments the monitoring area into distinct visual fields for each camera and assigns unique identifiers to each camera's field of view. This segmentation allows the system to track which occupant has been counted by which camera, preventing duplicate counting while maintaining comprehensive coverage across multiple overlapping areas.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system implements a feedback mechanism where each camera reports detected occupants to a central processor, which then checks whether the same occupant has already been counted by another camera in the overlapping region. This feedback loop ensures that duplicate detections are identified and excluded from the final occupant count, maintaining measurement precision across the expanded coverage area.

Inventive Principle:
Principle #23Feedback

2Device complexity

If a single image sensor is used, then the device complexity is reduced, but the measurement precision deteriorates due to incomplete coverage of the monitored area

Engineering Contradiction:
Improvesensor system complexityVSAvoidoccupant count accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The monitoring area is divided into multiple visual field segments, each covered by a separate camera. Each camera is responsible for detecting occupants within its specific segment, and the system integrates results from all segments to provide complete area coverage while maintaining manageable device complexity through modular camera units.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system merges the detection results from multiple cameras by combining their visual field data and coordinating their counting operations. This merging process allows the system to achieve complete area coverage equivalent to a single large sensor while using multiple smaller, simpler camera units that can be independently manufactured and positioned.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3387625B1Occupancy detection
Publication Date: 2023.07.26 SIGNIFY HOLDING BV
  • EP3387625B1 patent drawingFigure 1
  • EP3387625B1 patent drawingFigure 2
  • EP3387625B1 patent drawingFigure 3

AI summary

A system for determining occupancy includes a first luminaire having a first camera to detect a first occupant and a second luminaire having a second camera to detect a second occupant. The system further includes a processor to determine whether the first camera and the second camera have a common visual field and to determine whether the first occupant and the second occupant are the same occupant in response to determining that the first camera and the second camera have a common visual field.