Compatibility

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

What's new:

1. Supported Nvidia GPUs with Ada Lovelace micro-architecture for:

   • Neural tracker
   • Neural counter
   • Human pose detector
   • Equipment detector
   • Fire detector
   • Smoke detector
   • Neural classifier
   • Barcode detector
   • Water level detector
   • Stopped object detector
   • Privacy masking
   • Person-based privacy masking
   • Face detector VA
   • Crowd Estimation VA
   • Abandoned object detector VI
   • Abandoned object detector VI (Street)
   • License plate recognition RR
   • License plate recognition VT

2. Added Stopped object detector

3. Added Human tracker VL

4. Added Glow detector

5. Added Vehicle Recognition XR Windows OS .
6. Added new countries for the License plate recognition IV
7. Added new countries for the License plate recognition RR 

8. Added new countries for the License plate recognition VT 

9. It is now possible to hide the license plate number completely or partially using the GDPR Policy feature.

10. It is now possible to create events based on unrecognized license plates for detectors:

    • Configuring the License plate recognition RR

    • Configuring License plate recognition RR—Parking

11. Added the Biometric data parameter for:
    • Face detector TV
    • Face detector VA
    • Face detector VL

Optimization

1. Optimized the Nvidia GPU utilization so it can be used more efficiently, which increased the performance of the detectors:

   • Neural tracker
   • Fire detector
   • Neural classifier
   • Smoke detector
   • Neural counter

2. Added a new embedded neural network for the Human (top-down view) for detectors:

   • Neural tracker
   • Stopped object detector
   • Neural counter

3. Added the possibility of using object classes in standard sub-detectors

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

5. Added demo license for the detectors:

   • Face detector VL
   • Equipment detector VL
   • Human tracker VL

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.

3. By default, the GDPR Policy feature for detectors created before the update will be disabled. To enable it, it is necessary to delete the field values ​​and then re-enter '-' or specify the required filter.

Update limitations

1. When you update the Face detector TV, Face detector VA, or Face detector VL (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.
2. To start and correctly run the basic Face detector and Face detector VA on GPU, you must first create a cache
3. Replaced Face detector TV with Face detector VA. Discontinued the support for Face detector TV. Face detector TV and Face detector VA are incompatible.
4. Discontinued the support for the Intel HDDL (Mustang-v-100) devices.
5. The mechanisms for launching neural network models have changed, which is why some of the custom models (trained specifically for the object, see Data collection requirements for neural network training) can work incorrectly. If you encounter any difficulties, please contact technical support.
6. In this version of DetectorPack, you cannot filter objects by color when using sub-detectors (child detectors).
7. When working with Fire detector and Smoke detector in scanning mode (see Configuring the scanning mode), it is strongly recommended to set the polygon detection areas if you need to analyze only part of the frame.