Video Analytics actively monitors the customer's video stream for people, animals, and vehicles. For more information about how to create and customize Video Analytics recording rules, see Configure a Video Analytics rule.
When a Video Analytics rule is set up correctly, it can detect objects moving across a threshold or into an area of interest and ignore objects that are unimportant.
Video Analytics camera setup
Video Analytics operates by tracking a target’s feet or a vehicle’s wheels. Verify that the camera is clearly facing the ground or floor of the area being monitored.
Camera placement
Position |
Position the camera 8-16 feet above the ground. When the camera is repositioned, recreate all of the rules and recalibrate the camera if the camera supports calibration. For more information about which cameras must be calibrated, see Calibrate a device for Video Analytics. |
---|---|
Angle |
Angle the camera downward between 30°-60° and keep the horizon line level. This angle provides an ideal field of view while avoiding clouds and trees. Video Analytics is designed to work with an angled-down perspective; not horizontal, and not top-down. Video Analytics scans the frames where the bottom of the screen is the ground and the top of the screen is the area above the ground (e.g., ceiling, sky). Video Analytics performs best when the camera's sideways tilt is no more than approximately 10 degrees.
|
Distance |
Targets should be closer than 25 feet from the camera (15 feet at night). The entire target should be visible inside the camera’s field of view. |
Camera location
Video Analytics detects objects and classifies them as people, animals, and vehicles. Position the camera with a view that can see important activity from people, animals, and/or vehicles.
Recommended |
|
---|---|
Not recommended |
|
Lighting
Be aware of any bright lights (i.e., motion-triggered floodlights) near the camera that may attract insects or affect exposure and IR settings. Mount the camera in such a way that a vehicle’s headlights do not shine directly into the camera.
Avoid reflective surfaces (i.e. overhangs/eaves, walls, etc) that will reflect IR lights at night and make it difficult to see objects further away as reflective surfaces become overexposed.
Video Analytics rules
Video Analytics can be configured to detect when an object lingers in a specific area or when an object passes through a specific point.
When to use a Ground Zone rule
Use a Ground Zone rule when the object to be recorded lingers in a specific place for too long.
Verify that the Ground Zone is fitted to the ground or floor where the object's feet will be. For more information about configuring a Ground Zone rule, see Configure rule - Ground Zone.
When to use a Tripwire rule
Use a Tripwire rule when the object to be recorded passes through a specific place.
Verify that the Tripwire is placed where the object's feet or wheels will cross the threshold. For more information about configuring a Tripwire rule, see Configure rule - Tripwire.
To ensure rule accuracy
- Avoid intersecting tripwires or overlapping ground zones with objects that are prone to movements, such as trees, bushes, or other objects that move in the wind.
- Only draw the rule where the feet or wheels of an object should cross.
- Do not increase the size of the loiter zone or tripwire to cover the whole of the target.
- Do not include furniture, walls, trees, or other structures in the rule/selection.
- After observing what the rule detects over a few days, consider adjusting either the Minimum Object Detection Size slider or recalibrating the camera.
- When adjusting the Minimum Object Detection Size slider:
- Increasing the minimum object size can reduce false detection.
- Decreasing the minimum object size can detect smaller targets.
- When adjusting the Minimum Object Detection Size slider:
Video Analytics recordings
Notifications
When configuring the Notify Recipients section, keep in mind that the camera records all objects it detects even if the customer deselects a specific object type (i.e., a person, animal, vehicle, or other).
Example: The customer only chooses to be notified of recordings of people. If an animal triggers a recording, the recording will be saved, but no notification will be sent to the customer.
For more information about how clips are classified, see How does a Video Analytics clip get classified as Other?.
Accessing saved video clips
Recorded clips designated as Other by the camera are saved to the customer account but hidden by default on the Saved Video page. Verify that Other is selected as a filter on the Saved Video page when searching for Video Analytics recordings that appear to be missing.
To view video clips filtered to Other using the Customer Website:
- Log into the Customer Website.
- Click Video.
- Click Saved Video Clips.
- Using the video device dropdown menu, select the desired video device.
- Using the Object Detection dropdown menu, select Other.
- Click Search.
To view video clips filtered to Other using the Customer app:
- Log into the Customer app.
- Tap .
- Tap Video.
- Tap Saved.
- In Show, tap to select the desired date and time.
- In Object Detection, tap to select Other.
- Tap Apply.