This version of DetectorPack is compatible with Axxon One 2.0 and later versions.
Added Meta-detector
Added standard sub-detector Track masking
Supported neural models generated via the neural model training service—Train It Yourself (TYI) (*.annext)
Added Fight detector VL
Added VI detectors:
Supported Nvidia GPUs with Ada Lovelace micro-architecture for License plate recognition IV.
Added the following features in βeta mode:
Face attributes recognition βeta parameter in Face detector TV
For Linux OS: if a detector pack 3.7.4 version and earlier that includes all analytics tools is installed (not divided into plugins), then before updating, it is necessary to remove the installed package without using purge (complete package deletion) by running the following command:
sudo dpkg --remove --force-depends axxon-detector-pack |
and then install the necessary plugins.
Updated the SDK of the VI detectors. Changed licensing from Sentinel to Guardant. When you update to this version of DetectorPack, you must contact the manager from whom the original dongle was purchased to get a new dongle.
People masking sub-detector of the Human pose detector is no longer supported.
In Smoke detector, the Ignore black and white image parameter only functions if CPU value is selected in the Decoder mode parameter.
Meta-detector requires at least 8 GB of video memory to operate. It is recommended to set GPU value for both the Decoder mode and Detection mode parameters.