Ghost detections in people-counting sensors

Meet Butlr

Discover what spatial intelligence can do for you.

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

What are ghost detections?

Ghost detections are spurious sensor readings that an algorithm interprets as a person or movement when no actual person exists. They can be single false counts, persistent phantom tracks, or intermittent noise that inflates occupancy metrics.

Why they matter:

They distort analytics and downstream decisions, such as HVAC scheduling or retail conversion metrics.
They erode trust in sensor systems and increase operational overhead to investigate anomalies.
They can trigger unnecessary interventions, like alerts or building-system adjustments.

Common causes by sensor type

Radar (mmWave) sensors

Multipath reflections from walls, glass, or metallic surfaces creating delayed echoes that appear as phantom objects.
Side-lobe and secondary reflections producing false angle or distance estimates.
Environmental motion (fans, curtains, HVAC) generating Doppler signatures misinterpreted as people.

Depth cameras and stereo vision

Reflections and specular surfaces producing erroneous depth readings.
Occlusion and silhouette artifacts from partial views creating fragmented depth blobs that confuse tracking.
Lighting variations and IR interference introducing noise in structured-light systems.

Thermal / heat-based sensors

Thermal reflections and hot reflective surfaces creating misleading heat signatures.
Ambient temperature gradients from HVAC vents or sunlight producing ghost hotspots.
Low resolution merging nearby people into single blobs or creating spurious small hot spots.

Vision cameras (RGB)

Shadows and lighting changes mistaken for motion.
Reflections in glass or polished floors multiplying apparent people.
Background motion from screens or dynamic displays introducing false motion.

Wireless/BLE/Wi‑Fi sensing

Multipath and RF signal fluctuation creating perceived motion.
Lingering MAC addresses or probe traffic interpreted as device presence.

Detection and mitigation strategies

Robust solutions combine hardware choices, installation practices, and software filtering. Multiple layers of mitigation address both transient noise and systematic false positives.

Hardware and installation best practices

Mounting and orientation: place sensors to minimize direct views of reflective surfaces and discourage multipath; adjust elevation and angle to remove common reflection paths.
Coverage planning: avoid locations near HVAC vents, rotating equipment, or screens that cause repeated environmental motion.
Choose the right sensor: match technology strengths to space challenges; anonymous heat-based sensors can avoid optical issues affecting cameras and depth sensors.

Signal preprocessing

Background subtraction: maintain a slowly updating static-scene model to filter out persistent non-human heat or motion sources.
Elevation gating: discard detections outside expected human height ranges for sensors with elevation data.
Temporal filtering: require minimum duration or continuity to debounce short spikes.

Tracking and model-based filters

Multi-frame tracking: validate tracks over time and discard short-lived tracks lacking human-like motion.
Motion and trajectory heuristics: apply speed and acceleration thresholds consistent with human movement.
Confidence scoring: combine size, persistence, and motion pattern into a confidence score with environment-tuned thresholds.

Sensor fusion

Combine complementary sensors (thermal + radar, depth + PIR) to leverage modality strengths and reduce modality-specific ghosts.
Cross-validation: require corroboration from two independent sensors in sensitive applications.

Regular calibration and monitoring

Periodic recalibration after layout or seasonal changes to prevent new ghost sources.
Health checks and analytics to detect sudden baseline shifts and investigate drift or environmental changes.

Case study: reducing ghost targets in an open-office deployment

A mid-size office experienced persistent false counts near a glazed partition and an HVAC diffuser. The following steps were taken:

Site survey: identified multipath-prone geometry with glass and a low ceiling over the diffuser.
Hardware adjustment: remounted sensors higher and angled them to reduce direct reflections into the field of view.
Software tuning: applied elevation gating and required a 2-second continuity threshold for detections.
Background update: enabled adaptive background modeling to learn the diffuser's thermal signature.

Results: false positives dropped by over 85% and event logs showed improved correlation with badge entries and manual head counts. Combining installation changes, software filters, and adaptive models produced reliable reduction without sacrificing sensitivity to genuine occupancy.

Why sensor choice matters for privacy and reliability

Sensor selection affects both accuracy and privacy. Camera systems deliver high granularity but raise privacy concerns and are susceptible to optical artifacts. Radar offers strong motion sensitivity but can suffer multipath ghosts. Heat-based sensing provides anonymous occupancy detection using thermal signatures rather than identifiable images.

Heat-based, anonymous sensors tend to:

Reduce privacy risk by not capturing facial or identifiable visual imagery.
Be less sensitive to lighting and reflections that affect cameras.
Produce lower false positives in some reflective or visually noisy environments, while requiring careful handling of thermal gradients.

No single technology is perfect; matching sensor strengths to installation challenges and combining modalities often yields the best outcome.

Deployment checklist to minimize ghost detections

Conduct a site survey to identify reflective surfaces, HVAC outlets, and moving equipment.
Choose sensor mounting height and angle to avoid direct reflections and limit sightlines to noisy areas.
Apply elevation gating and minimum-duration thresholds in software configuration.
Enable background subtraction and adaptive models that learn static environmental signatures.
Use multi-sensor fusion in high-criticality areas where false positives have high operational cost.
Schedule regular recalibration after layout or seasonal changes.
Monitor baseline metrics for sudden shifts and investigate promptly.

FAQs

How can I tell a ghost detection from a real person?

Ghost detections are often short-lived, lack coherent motion, repeat at fixed locations, or correlate with environmental events like HVAC cycles. Cross-checking with other sensors or manual observation helps confirm.

Can firmware or software fixes eliminate ghosts completely?

They can dramatically reduce ghosts but may not eliminate all, especially those caused by complex multipath or physical reflections. Combining installation, preprocessing, tracking, and fusion provides the best results.

Which sensor types are most susceptible to ghost detections?

Depth cameras and optical systems are sensitive to reflections and lighting; radar is prone to multipath. Thermal systems and wireless sensors have unique causes but often offer privacy and environment-specific advantages.

Should I use multiple sensor types?

For critical spaces requiring high accuracy, combining sensor types and applying fusion strategies typically yields the most reliable outcome.

Final recommendations

Begin deployments with a thorough site assessment and tune hardware and software to the environment. Favor layered mitigation: good mounting and coverage planning, robust preprocessing, tracking heuristics, and sensor fusion when needed. For privacy-sensitive or reflection-prone spaces, consider anonymous heat-based sensing as a strong option that balances reliability and anonymity.

If ghost detections affect analytics or operations, schedule a diagnostic assessment with a sensor specialist. A focused investigation usually identifies a few actionable changes that deliver large improvements in accuracy and trust.

Conclusion

Ghost detections are a common challenge across sensing modalities but can be effectively managed by combining careful installation, preprocessing, tracking, sensor fusion, and regular calibration. Selecting the right sensor technology for the environment and applying layered mitigation reduces false positives while protecting privacy and preserving sensitivity to real occupancy.

Ghost Detections in People‑Counting Sensors: Causes, Mitigation, and Best Practices