Video Occupancy Mapping for Desk-Level Room Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current occupancy detection systems only provide general metrics on room occupancy, such as the presence or number of people, without specifically identifying the occupancy status of points of interest like desks or seats within a room.
Innovation Solution
The system uses a camera to receive a video feed, employs an AI model to detect individuals, and maps their locations from the video feed to a floor plan, indicating occupancy of specific points of interest if the person remains at that location for a threshold period.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If general occupancy detection is used to detect presence or number of people in a room, then occupancy information can be obtained, but specific occupancy status of points of interest like desks or seats cannot be identified
Solution Approach 1:
The patent segments the room into multiple points of interest (desks, seats, workstations) on a floor plan, allowing occupancy detection to be performed at each specific location rather than just general room occupancy. This enables precise tracking of which specific desks or seats are occupied while using the same video feed infrastructure.
Solution Approach 2:
The patent maps two-dimensional video feed coordinates to a two-dimensional floor plan, creating a spatial correspondence that enables location-specific occupancy detection. By establishing coordinate transformations between the video feed space and floor plan space, the system can identify which specific points of interest are occupied based on person locations in the video.
2Loss of information
If video feed analysis is used to track person locations, then specific point of interest occupancy can be identified, but processing complexity and computational requirements increase
Solution Approach 1:
The patent pre-processes the floor plan to identify and mark points of interest (desks, seats, workstations) before occupancy detection begins. This preliminary segmentation and coordinate system establishment reduces real-time processing complexity by having the spatial mapping framework ready in advance, allowing the system to simply map detected person locations to the pre-defined points of interest.
Solution Approach 2:
The patent creates a digital copy of the room layout as a floor plan with coordinate systems that corresponds to the physical space. This virtual representation allows the system to track occupancy by mapping video feed coordinates to the floor plan copy, avoiding the need for complex real-time analysis of the actual physical environment while maintaining complete occupancy information.
3Productivity
If real-time occupancy tracking at specific locations is implemented, then hot desking and energy optimization can be enabled, but threshold period requirements may reduce responsiveness
Solution Approach 1:
The patent implements a dynamic threshold period mechanism that can adjust the time requirement for confirming occupancy at a point of interest. This allows the system to balance between false positive occupancy detection and responsiveness, adapting the threshold based on contextual factors such as time of day, room type, and usage patterns to optimize both hot desking efficiency and detection responsiveness.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Systems and methods are disclosed for indicating occupancy of a point of interest in a room. A video feed from a camera located in the room can be received, and a person in the video feed can be detected by using an artificial intelligence (AI) model. A location of the person on a floor plan of the room can be identified based on a video feed location of the person detected in the video feed, and where the location of the person on the floor plan is at the point of interest for at least a threshold period of time, the point of interest can be indicated as being occupied.