Topics included in this article:
- Overview
- AI Confidence Thresholds
- Adjusting AI Confidence
- Environmental Impacts to AI Performance
- Troubleshooting AI
- Helpful Links
- Contact Support or Sales
Overview
AI confidence thresholds determine how certain a Rhombus camera must be before identifying a person, face, vehicle, or license plate. Adjusting these thresholds can help balance missed detections and false positives based on the camera's environment and positioning. This article explains how AI confidence thresholds work, how to adjust them, and how to troubleshoot common AI detection issues.
AI Confidence Thresholds
In AI detection models, confidence refers to the AI's certainty that an identification is correct. Confidence thresholds determine how certain the AI must be before identifying an object as a human or vehicle. Adjusting these thresholds can help balance false positives and false negatives.
- High Confidence: The model uses a stricter threshold when identifying humans or vehicles, reducing incorrect identifications but increasing the risk of missing valid targets.
- Low Confidence: The model uses a less strict threshold when identifying humans or vehicles, reducing the risk of missing valid targets but increasing the risk of incorrect identifications.
High Confidence Setting
When the confidence threshold is set high, the model requires a higher level of certainty before identifying a human or vehicle. Setting the threshold too high can result in missed detections when the model does not have enough information to confidently make an identification.
Example: Imagine a security camera is configured to detect humans with a confidence threshold of 95%. The system will only identify a person if it is at least 95% confident that the detected movement matches its model for human movement. If the person is partially obscured or the image quality is poor, the model may not reach the required confidence threshold, resulting in a missed detection.
Low Confidence Setting
When the confidence threshold is set low, the model requires less certainty before identifying a human or vehicle. Setting the threshold too low can result in false positives because the model may make an identification without enough information to accurately classify the detected object.
Example: Imagine a security camera is configured to detect humans with a confidence threshold of 50%. The system will identify a person if it is at least 50% confident that the detected movement matches its model for human movement. Because the required confidence is lower, objects such as moving tree branches or birds may be incorrectly identified as people, resulting in more false detections and alerts.
Adjusting AI Confidence
Finding the appropriate confidence threshold for a device may require some adjustment. While changing the confidence threshold can improve AI detection performance, external factors such as ambient lighting, camera positioning, and camera angle can also significantly impact detection accuracy.
AI confidence thresholds can be adjusted for the following event types:
- Human Detections
- Face Detections
- Vehicle Detections
- License Plate Detections
Note: For the AI model to identify a face, it must first identify a human in the frame. Similarly, the model must first identify a vehicle before it can identify a license plate.
Increasing Confidence
Increasing the confidence threshold requires the AI model to have greater certainty before making an identification, which can reduce false positives. However, setting the threshold too high can cause the model to filter out valid event detections.
| 1. Navigate to the "Devices" tab, then select the device for which you want to adjust the AI confidence thresholds. |
| 2. Hover over the ellipsis button in the upper-right corner of the video feed, then click "Settings." |
|
|
| 3. Click "Edit" beside "AI Confidence." |
|
|
| 4. Move the slider to a higher value to increase the AI confidence threshold for the selected event type. To restore the default value, click "Revert to default." Click "Save" when finished. |
|
|
Note: The slider moves in increments of 1%. We recommend initially adjusting the confidence threshold in increments of 2-3% to find the appropriate balance for your device. Changes may take some time to affect detection results. Monitor the device's behavior for 24-48 hours before making additional adjustments. |
Face Detection and License Plate Recognition require an Enterprise license and must be enabled before their AI confidence thresholds can be adjusted. |
Decreasing Confidence
Decreasing the confidence threshold requires the AI model to have less certainty before making an identification, which can reduce missed detections. However, setting the threshold too low can increase false positives.
| 1. Navigate to the "Devices" tab, then select the device for which you want to adjust the AI confidence thresholds. |
| 2. Hover over the ellipsis button in the upper-right corner of the video feed, then click "Settings." |
|
|
| 3. Click "Edit" beside "AI Confidence." |
|
|
| 4. Move the slider to a lower value to decrease the AI confidence threshold for the selected event type. To restore the default value, click "Revert to default." Click "Save" when finished. |
|
|
| Note: The slider moves in increments of 1%. We recommend initially adjusting the confidence threshold in increments of 2-3% to find the appropriate balance for your device. Changes may take some time to affect detection results. Monitor the device's behavior for 24-48 hours before making additional adjustments. |
| Face Detection and License Plate Recognition require an Enterprise license and must be enabled before their AI confidence thresholds can be adjusted. |
Environmental Impacts to AI Performance
Accurate AI event detection depends on proper camera placement and environmental conditions. Factors such as lighting, mounting height, and camera angle can impact detection accuracy, and optimal conditions may vary depending on the detection type.
Adequate lighting is essential for accurately identifying humans, faces, vehicles, and license plates. Insufficient lighting can reduce detection accuracy or prevent the AI model from identifying these objects. Camera mounting height and angle can also affect how reliably the AI model detects and identifies objects.
Troubleshooting AI
| Issue | Solution |
The AI model is generating false positives for a specific event type. |
The confidence threshold for the affected event type may be set too low, resulting in false positives. Increase the confidence threshold in increments of 2–3% and monitor the device's detection accuracy to determine whether the issue improves. |
The camera is not detecting Human Movement events. |
If environmental conditions and camera placement are optimized, decrease the Human Movement confidence threshold in increments of 2–3% until the camera begins detecting Human Movement events. |
The camera is not detecting faces. |
If environmental conditions and camera placement are optimized, confirm that the camera is detecting Human Movement events. If Human Movement is being detected, decrease the Facial Recognition confidence threshold in increments of 2–3% and monitor for an increase in face detections. |
The camera is not detecting Vehicle Movement events. |
If environmental conditions and camera placement are optimized, decrease the Vehicle Movement confidence threshold in increments of 2–3% until the camera begins detecting Vehicle Movement events. |
The camera is not detecting license plates (LPR). |
If environmental conditions and camera placement are optimized, confirm that the camera is detecting Vehicle Movement events. If Vehicle Movement is being detected, decrease the License Plate confidence threshold in increments of 2–3% and monitor for an increase in license plate detections. |
Helpful Links
- Best Practices for AI
- Enable AI Bounding Boxes
- Console Features & Licensing
- Optics and Object Distances for Analytics
- Managing Facial Recognition
- Managing License Plate Recognition (LPR)
- People and Vehicle Counting
Contact Support or Sales
Have more questions? Contact Rhombus Support at +1 (877) 746-6797 option 2 or support@rhombus.com.
Interested in learning more? Contact Rhombus Sales at +1 (877) 746-6797 option 1 or sales@rhombus.com.
Comments
0 comments
Please sign in to leave a comment.