Signals on a BIM model

NBU Medical Clinic, a two-floor outpatient clinic from the public NIBS Common BIM Files set (IFC 2x3, Revit). Every area, wall and door below was read from the file. Only the camera is a model.

Open floor measured
1,250 m²
2 floors, 59 open spaces
Cameras in the plan
32
16 on the first floor, 16 on the second floor
Private rooms
74
68 door-line counters, no camera inside
Set-up walk on site
0
camera-to-floor mapping comes from the model

From the model to the measured floor

1
Model

BIMstream delivers the building as an IFC: every wall, door, room name and area, in real dimensions.

2
Plan

Signals computes the camera plan from the model: where each camera goes, what it sees, what is behind a wall, and how many pixels land on each square meter of floor. Rooms are classed before anyone visits: measured, counted at the door, or out.

3
Train

The same model and camera plan render labeled footage of this building from the planned camera positions, so the detector and counter are tuned to this site's rooms, angles and light before a camera is mounted.

4
Install

Existing cameras go in first, the plan fills the gaps. Each camera's picture is mapped to floor coordinates from the model, not from a calibration walk.

5
Run

Every count Signals reports lands in a named room with an exact area: people per square meter, queue length at a counter, minutes a booked room sits empty. Accuracy is measured per room against the precision floor set in the plan.

Where the precision comes from

Three things are known before install that are normally discovered after it. Pixel density: the plan states, for every square meter, whether a camera can count people there or only tell that someone is present, so the customer is promised counts only where the geometry supports them. Occlusion: walls and columns are in the model, so a blind spot is a computed fact, not a surprise on day one. Ground truth: the floor plane and room boundaries come from the model, so a count is attributed to a room by geometry rather than by a hand-drawn zone, and a detection that lands inside a wall is caught as an error rather than counted.

What the model gives the training run

A building model with a camera plan is a complete description of a scene: camera position, lens and mount height, the floor plane, every occluder, and a name for every room. That is what a renderer needs to produce footage of this building with people in it, and because the people are placed by the renderer, every frame comes with exact boxes, floor positions and per-room counts at no labeling cost. The detector and tracker are fine-tuned on that footage for this site, then checked against real footage once cameras are up. The working plan is to render from the planned camera positions first, install, then keep the real footage and its corrected counts as the site's own training set.

Across sites the same thing compounds. Every BIM model that goes through this process adds a building type, a camera geometry and a labeled set to the corpus, and the retraining pipeline runs the same way on all of it. That corpus and the pipeline are the durable asset; the base models underneath are swappable. This run is not done yet: the renders and the fine-tuning are the next step, and the numbers on this page are geometry only.

The camera plan, floor by floor

Measured floor area
857 m²
35 open spaces
Count quality with the plan
75%
16 cameras; 90% needs more, or the room list narrowed
Corridor-only layout sees
24%
4 cameras, entrance and corridor
Private rooms, counted at the door
49
no camera inside any of them
Signals plan
Signals plan. Green: count quality (63 px/m and up). Amber: presence only (25 to 63 px/m). Red: not seen. Navy dots are cameras with their field of view; amber squares are door-line counters on private rooms. Black lines are walls and columns sectioned at 1.5 m from the IFC.

Coverage by space

SpaceCount qualityPresence
Corridor1556%75%
Corridor3093%93%
TEAM INTERACTION2381%89%
GROUP IS1886%86%
Corridor1487%91%
Corridor1998%98%
Corridor90%0%
Waiting17894%96%
Corridor3049%50%
Waiting13794%94%
Corridor618%56%
GROUP IS1889%89%
Corridor656%56%
Corridor1991%91%
Lounge100%0%
Corridor1483%87%
Reception93%21%
Waiting12100%100%
Corridor60%0%
Corridor1267%67%
Corridor4277%79%
Staff lounge140%0%
Corridor84%4%
Corridor874%74%
Corridor2786%86%
Staff lounge90%0%
Corridor5181%97%
Corridor4085%95%
Waiting120%0%
Corridor50%4%
Corridor70%0%
Corridor1192%92%
Reception9100%100%
Corridor80%0%
Reception2227%27%

Cameras added one at a time

CamerasCount qualityPresence
116%24%
223%34%
331%41%
436%48%
543%49%
648%52%
752%56%
856%59%
959%63%
1062%66%
1165%69%
1268%71%
1370%73%
1472%75%
1574%77%
1675%79%

Camera list

IdLensHeading
C01std (85° lens)-151°
C02wide (105° lens)-38°
C03std (85° lens)-42°
C04wide (105° lens)124°
C05wide (105° lens)128°
C06wide (105° lens)-37°
C07wide (105° lens)-48°
C08std (85° lens)60°
C09wide (105° lens)126°
C10wide (105° lens)-33°
C11wide (105° lens)-143°
C12wide (105° lens)29°
C13wide (105° lens)-125°
C14wide (105° lens)148°
C15wide (105° lens)-148°
C16wide (105° lens)54°

Door-line counters

IdRoom
D01RECORDS
D02APPMTS
D03INTERACTION STATION
D04PROVIDER CUBICLES
D05INTERACTION STATION
D06INTERACTION STATION
D07OPT. EXAM / OFF.
D08INTERACTION STATION
D09TRICARE OFFICE
D10TRICARE OFFICE
D11PROVIDER CUBICLES
D12INTERACTION STATION
D13OPT. EXAM / OFF.
D14INTERACTION STATION
D15PHARM. OFFICE
D16WTS & MEAS. ROOM
D17INTERACTION STATION
D18CONF. LIBRARY
D19PEDIATRIC WTS & MSRS
D20INTERACTION STATION
D21COUNSELING
D22PES ADMIN. OFFICE
D23INTERACTION STATION
D24TRICARE OFFICE
D25ADMIN WORK STATN.
D26HK BREAK ROOM
D27FAC. MGR. OFFICE
D28CHIEF LOG OFFICE
D29BIOMED MAINT. ADMIN.
D30TRICARE OFFICE
D31SUPER
D32INTERACTION STATION
D33LAB OFFICE
D34HK. SUPV. OFFICE
D35WORK ROOM
D36INTERACTION STATION
D37TRICARE OFFICE
D38TECH. WORK STATION
D39TECH. WORK ROOM
D40ISOLATION INTERACTION STATION
D41INTERACTION STATION
D42BMET WORK STATION
D43CLEAN SUP. & EQUIP.
Measured floor area
393 m²
24 open spaces
Count quality with the plan
89%
16 cameras; 90% needs more, or the room list narrowed
Corridor-only layout sees
37%
4 cameras, entrance and corridor
Private rooms, counted at the door
25
no camera inside any of them
Signals plan
Signals plan. Green: count quality (63 px/m and up). Amber: presence only (25 to 63 px/m). Red: not seen. Navy dots are cameras with their field of view; amber squares are door-line counters on private rooms. Black lines are walls and columns sectioned at 1.5 m from the IFC.

Coverage by space

SpaceCount qualityPresence
Reception1484%84%
Corridor1294%94%
Corridor2894%94%
Corridor12100%100%
Corridor1076%89%
Waiting1087%87%
Corridor2894%94%
Corridor2189%89%
Corridor877%77%
Corridor20100%100%
Lounge1083%83%
Corridor2593%93%
Corridor3999%99%
Vestibule20%0%
Corridor70%56%
Corridor1254%100%
Corridor16100%100%
Dental waiting3296%96%
Corridor1498%99%
Corridor2697%97%
Corridor13100%100%
Dental waiting78%17%
Corridor1791%97%
Corridor874%74%

Cameras added one at a time

CamerasCount qualityPresence
112%14%
221%29%
329%40%
437%48%
544%55%
652%63%
758%69%
865%71%
969%76%
1074%78%
1177%81%
1280%83%
1383%86%
1485%88%
1587%90%
1689%92%

Camera list

IdLensHeading
C01wide (105° lens)58°
C02wide (105° lens)-132°
C03wide (105° lens)54°
C04wide (105° lens)143°
C05wide (105° lens)135°
C06wide (105° lens)34°
C07wide (105° lens)50°
C08wide (105° lens)30°
C09wide (105° lens)-38°
C10wide (105° lens)50°
C11wide (105° lens)47°
C12wide (105° lens)142°
C13wide (105° lens)46°
C14wide (105° lens)132°
C15wide (105° lens)-58°
C16wide (105° lens)-29°

Door-line counters

IdRoom
D01TECH. OFFICE
D02OFFICE / EXAM
D03PH TECH
D04CONF. ROOM
D05READINESS NCOIC OFFICE
D06TECH OFFICE
D07TECH OFFICE
D08CONF. / GROUP THERAPY
D09LIBRARY / CLASSROOM
D10DIPC CLEAN
D11OFFICE
D12CMDR OFFICE
D13LIBRARY / CONF. ROOM
D14SYS. ANALYST
D15ADMIN
D16SUPER
D17PH SUPER
D18SUPER OFFICE
D19ADMIN OFFICE
D20COPY / FILE
D21CONSULT.
D22OFFICE
D23DENTAL SURGEON OFFICE
D24PH TECH
D25SEC. OFFICE

How the camera is modeled

One camera type throughout: a 4 MP sensor, 2688 pixels wide, mounted at 2.8 m, with either a 105° or an 85° lens chosen per position. Pixel density on the floor falls with distance; the two thresholds are the IEC 62676-4 tiers for detection (25 px/m, presence) and observation (63 px/m, enough to count people and read posture). Identification tiers are not used anywhere in the plan. A 105° lens holds count quality to 16.4 m and presence to 41.3 m; the 85° lens holds count quality to 23.3 m.

Walls, columns and curtain wall panels are sectioned at 1.5 m above each floor and block the line of sight. Placement runs a greedy search over the corners of every open space, adding the camera that gains the most count-quality floor each round, and stops when a camera would add less than 6 m². The corridor-only layout is the same search restricted to the entrance and corridor, four cameras, which is where a conventional security install puts them.

What this building would report

Waiting rooms and reception: people waiting, time from arrival to being called, and the hour the room fills. Corridors and lobby: flow between departments and after-hours presence. Staff lounge: use by hour. Offices, provider cubicles and conference rooms: occupied or not, from a counter on the door line, with no camera inside. Exam rooms, labs, toilets, dressing rooms and plant rooms are out of scope by policy, so patient care spaces never carry a camera.

Caveats. The IFC records every interior partition as a wall; glass partitions would not block a camera the way the model assumes, so real coverage in glazed offices is higher than shown. Furniture, monitors and people are not in the model and will occlude at floor level; count quality assumes the camera sees heads and shoulders at 2.8 m. Camera counts here are an upper bound for the layout, not a bill of materials. Room names in this model are abbreviated and were classified by keyword: corridors, waiting rooms, reception, lobbies and lounges are measured; offices, work stations and conference rooms are counted at the door; every clinical room is out. A handful may sit in the wrong class and should be checked room by room before anything goes to a customer. The site's own cameras were not modeled because the file has none; on a BIMstream job the existing cameras would be placed first and only the gaps filled.

Where this goes with BIMstream

BIMstream delivers the model and the install. Signals turns the model into a camera plan, a coverage map, a room-by-room list of what will be measured and a training set for the site, all before anyone visits. The customer sees which rooms get counts, which get presence, and which are left out on purpose, with the pixel density behind every promise. After install the same model is the coordinate frame for every number Signals reports. Sold together: model, plan, train, install, measured floor.

Source model: NBU_MedicalClinic_Arch-Optimized.ifc, IFC 2x3, from the NIBS Common BIM Files, public sample. Computed 15 Sep 2026 with ifcopenshell 0.8.5. Confidential. Internal to YYZdata Inc. Not for distribution, in whole or in part, without written consent.