To manage privacy concerns, Samsara can blur most uploaded and saved footage for all license plates and individuals (drivers, passengers, and pedestrians). Blurring can be applied to videos in the dashboard (safety event videos and video retrievals), downloaded videos, and trip stills.
There are three different Identity Blurring features that you can enable separately or together through the Feature Management page:
-
Exterior Identity Blurring (dual and front-facing dash cams with AI capabilities)
-
Driver Identity Blurring (dual-facing dash cams)
-
HD NVR Blurring (HD NVR system)
As soon as you enable your preferred Identity Blurring features, Samsara applies the settings to any future image and video captures.
Note
Samsara does not retroactively blur images and videos captured before the feature is enabled.
Identify Blurring also has the following exceptions and usage notes:
-
If you have Live Streaming enabled, using Take New Still will capture unblurred images and videos, however, only users with explicit live streaming permissions can initiate live streams.
-
Certain overlays for AI events, such as those for Distracted Driving and Forward Collision warning, will not display on blurred images and videos.
-
In the event that you need to retrieve unblurred footage such as to exonerate a driver or as requested by law enforcement, Dashboard admins can download unblurred images and videos. For more information, see Download Unblurred Footage.
Our blurring algorithm relies on AI object detection models to detect human heads and vehicles as objects. The following factors can impact its performance:
-
Object size: Proximity to the camera affects detection. Objects too close or far might not register.
-
Object variation: Human faces and vehicles vary, leading to potential misidentifications. Images with multiple instances of these objects may confuse the algorithm.
-
Image orientation: Object detection is often more successful when certain facial features or certain vehicle characteristics like headlights are in frame. For human heads, these include shape, size, facial features, and accessories. For vehicles, identifiers like headlights and position relative to the road are essential. However, objects at angles to the camera may not be detected due to missing identifiers.
-
Object placement: Unconventional positions can cause detection errors. For instance, Samsara's algorithm is trained to recognize typical adult head locations. Therefore, the relative positioning of a child's head compared to an adult's head, which deviates from the standard seat location, may not be accurately detected.
-
Illumination and lighting: Poor or excessive lighting, such as bright daylight or glare, can hinder detection.
-
Occlusion: Partially obscured objects may escape detection.
-
Blur: Blurriness reduces detectability, with image quality and resolution further impacting performance.
-
Motion (in video): Rapid movement between frames can lower object detection accuracy.
Comments
0 comments
Please sign in to leave a comment.