DetectorPack 3.13.1 Release Notes

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

Optimized the use of Nvidia GPU. As a result, it improved the performance of the Stopped object detector.
Improved the Handrail holding sub-detector
Added new countries for the License plate recognition IV: Hong Kong, Macau, Belgium, Luxembourg, Portugal
Added new countries for the License plate recognition RR and Vehicle recognition RR: Tunisia, Chile, Sri Lanka. Also added vehicle class recognition for the USA and Mexico, with classes including Van, SUV, and Sedan
Added a Skip area parameter for the following detectors:
- Standard sub-detectors:
  - Line crossing
  - Loitering in area
  - Stop in area
  - Abandoned object
  - Motion in area
  - Entrance in area
  - Exit from area
  - Multiple objects
- Stopped object detector
- Barcode detector
Added a Detection area parameter for the following detectors:
- Motion detector
- Object tracker
- Equipment detector VL
- Privacy masking

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.
Changed the licensing procedure for the following detectors:
- Face detector VL: Windows OS , Linux OS
- Fight detector VL: Windows OS , Linux OS
- Human tracker VL: Windows OS , Linux OS
- Equipment detector VL: Windows OS , Linux OS
In upcoming versions of Axxon One, the interface of the Detectors tab will be updated. Detector configuration and the creation of Automatic rules macros will be separated into two tabs.

When you update Face Recognition Pack add-ons (see Installing DetectorPack add-ons), the results of the previously recognized persons will become unavailable. If you want to keep the previously recognized persons, do not update the analytics package.
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.

Page tree