Documentation for Axxon One 2.0. Documentation for other versions of Axxon One is available too.

Previous page DetectorPack 3.12.1 Release Notes  Hidden Pages Next page

Compatibility

This version of DetectorPack is compatible with Axxon One 2.0 Beta and later versions. 

What's new:

  1. Added Barcode detector.
  2. Added Face detector VA.
  3. Added Audio classification IV.
  4. Added Abandoned object detector VI and Abandoned object detector (Street) VI.
  5. Added new countries for the License plate recognition IV
  6. Added new countries for the License plate recognition VT
  7. Added new countries for the License plate recognition RR

Optimization

  1. Added the possibility of quantizing all embedded models for Neural tracker 

  2. Unified class numbers for embedded models

  3. Added the possibility of using object classes in standard sub-detectors (child detectors): Motion in area, Entrance in area, Exit from area.

  4. Updated integration of the Abandoned object detector VI—Windows version is now available.

  5. Added a new type of vehicle—"motorcycle" for the Vehicle recognition RR and License plate recognition RR.

  6. Improved the quality of speed detection for the License plate recognition RR

  7. Support for NVIDIA JetPack 5.1.2 (Nvidia Jetson Orin devices) in the Neuro Pack is available.
  8. Added general models for Atlas300i NPU.
  9. Normalized load by cores on Xeon processors.
  10. Improved the speed of the Image noise detector.

Update recommendations

  1. 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.

  2. For Face masking to work during export, it is necessary to have the Neuro Pack installed.

Update limitations

  1. 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.
  2. To start and correctly run the basic Face detector on GPU, you must first create a cache
  3. Discontinued the support for the Intel HDDL (Mustang-v-100) devices.
  4. The mechanisms for launching neural network models have changed, which is why some of the custom models (trained specifically for the object) can work incorrectly. If you encounter any difficulties, please contact technical support.
  5. In this version of DetectorPack, you cannot filter objects by color when using sub-detectors (child detectors).
  6. Replaced Face detector TV with Face detector VA. Discontinued the support for Face detector TV. Face detector TV and Face detector VA are incompatible.
  • No labels