Go to documentation repository
Page History
...
This version of DetectorPack is compatible with Axxon One 2.0 Beta and later versions.
What's new:
- Added Barcode detection tooldetector.
- Added Face recognition detector VA.
- Added Audio analyticsclassification IV.
- Added Abandoned Objects Detection object detector VI and Abandoned Objects Detection object detector (Street) VI.
- Added new countries for the License plate recognition ( IV )
- Added new countries for the License plate recognition ( VT )
- Added new countries for the License plate recognition ( RR )
Optimization
Added the possibility of quantizing all embedded models for Neurotracker Neural tracker
- Unified class numbers for embedded models
Added the possibility of using object classes in classical standard sub-tools detectors (child detection toolsdetectors): Motion in area, Appearance in Entrance in area, Disappearance in Exit from area.
Updated the integration of the Abandoned object detector VI—Windows version is now available.
- Added a new type of vehicle—"motorcycle" for the Vehicle recognition RR vehicles recognition and License plate recognition ( RR).
Improved the quality of speed detection for the License plate recognition ( RR )
- Support for NVIDIA JetPack 5.1.2 (Nvidia Jetson Orin devices) in the Neuro Pack is available.
- Added general models for Atlas300i NPU.
- Normalized load by cores on Xeon processors.
- Improved the speed of the Image noise detectiondetector.
Update recommendations
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:
Code Block sudo dpkg --remove --force-depends axxon-detector-pack
and then install the necessary plugins.
- For Face masking to work during export, it is necessary to have the Neuro Pack installed.
...
- When you update the Face Recognition Pack, 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.
- To start and correctly run the basic Face Detectiondetector on GPU, you must first create a cache
- Discontinued the support for the Intel HDDL (Mustang-v-100) devices.
- The mechanisms for launching neural network models have changed, that which is why some of the custom models (trained specifically for the object) may not can work correctlyincorrectly. If you encounter any difficulties, please contact technical support.
- In this version of DetectorPack, you cannot filter objects by color when using sub-tools detectors (child detection toolsdetectors).
- Replaced Face Detection detector TV with Face Detection detector VA. Discontinued the support for Face Detection detector TV. Face Detection detector TV and Face Detection detector VA are incompatible.