Duplicate Image Detection in Electronic Meetings Using Presence Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Hybrid electronic meetings often transmit unintended reflections and duplicate frames of participants due to ineffective zone-based field of view restrictions, leading to display clutter and increased processing.
Innovation Solution
Utilize a secondary sensor, such as a ToF, PIR, or LIDAR, to verify the physical presence of participants within a meeting area, correlating this information with camera images to exclude extraneous reflections and non-participant faces from the gallery view.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If zone-based field of view restrictions are used to limit camera capture area, then the field of view is restricted, but reflections and duplicate frames are still transmitted
Solution Approach 1:
The patent introduces a secondary sensor as an intermediary device to verify the physical presence of participants. This sensor independently detects actual participant locations and provides verification data that mediates between the camera's visual detection and the final determination of whether to include a detected face in the broadcast, thereby resolving the contradiction between field of view restriction and reliable participant identification
Solution Approach 2:
The system implements feedback by using the secondary sensor to continuously monitor and verify participant presence, then using this verification information to confirm or reject camera-detected faces. This feedback loop ensures that only verified participants are included in the broadcast, maintaining high reliability even when zone-based field of view restrictions are applied
2Quantity of substance
If width and depth boundaries are configured to capture individuals, then more participants are included, but reflections within the boundary are also captured
Solution Approach 1:
The secondary sensor serves as an intermediary verification mechanism that distinguishes between actual participants and reflections. By providing independent presence verification data, it enables the system to include more detected faces in the broadcast while filtering out duplicates and reflections, thus resolving the contradiction between capturing more participants and eliminating harmful duplicate frames
Solution Approach 2:
The system intentionally allows the camera to capture a broader area including potential reflections and duplicate frames (excessive action), then uses the secondary sensor verification to selectively include only the valid participant frames in the final broadcast. This approach ensures no legitimate participant is missed while still eliminating duplicates through subsequent verification
3Reliability
If all detected faces are transmitted to ensure completeness, then no participant is missed, but display clutter increases due to reflections
Solution Approach 1:
The secondary sensor acts as an intermediary filter that verifies which detected faces correspond to actual participants. This verification mechanism maintains completeness by ensuring all real participants are included while reducing display clutter by excluding reflections and duplicate frames through the sensor's presence verification data
Solution Approach 2:
The system extracts and removes duplicate frames and reflections from the set of camera-detected faces by using secondary sensor verification. This extraction process separates valid participant frames from harmful duplicate frames, maintaining broadcast completeness while reducing display clutter and processing requirements
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Effectively distinguishes real participants from reflections and non-participants, reducing display clutter and processing load by ensuring only verified, physically present individuals are included in the broadcast.
Implementation Method 1
A first device includes a camera to capture an image of a meeting area and a time of flight sensor to identify a depth distance to a face in the image
Implementation Method 2
A first device includes a camera to capture an image of a meeting area and an infrared sensor to identify a location of a participant in the meeting area
Implementation Method 3
A first device includes a camera to capture an image of a meeting area and a light detection and ranging sensor to identify a location of a participant in the meeting area
Data Source
AI summary
A computer implemented method includes receiving an image of a meeting area from a first camera during an electronic conference call, detecting multiple faces in the image using a facial recognition model, receiving information from a secondary sensor to identify locations of participants in the meeting area, correlating the detected faces with the locations of participants, and generating a set of images of the participants that excludes detected faces that do not correspond to the locations of participants.