.. _new:

What's New in FindFace Multi 2.1
===================================


.. rubric:: New Features:

* :ref:`line_crossing`: monitor the intersection of a predetermined virtual line by an individual or a vehicle.
* :ref:`alarm_monitor`: get notifications about alarming events into a separate desktop application or its web version.
* :ref:`bi_analytics`: data visualization and exploration tool.
* :ref:`Router URL <video_processing_parameters>` in camera settings: send detects to the external processing units.
* :ref:`Counter health monitoring <counter-operation>`: filter counters to find out the ones with technical issues. 

.. rubric:: Technical Changes:

* Integration with Annex.

  See :ref:`alarm_monitor`

* :ref:`hot_cold_storage`: hot-cold storage to smooth out system peaks.

.. rubric:: Enhanced Algorithms, UI, UX:

* :ref:`Webhooks configurator <webhooks>`: in the web interface, create and configure a webhook, either in a visual or code mode.
* VMS cleanup improved functionality.
 
  See:

  * :ref:`vms_cleanup`
  * :ref:`global_vms_cleanup` 
  * :ref:`Custom VMS Cleanup Settings <custom_vms_cleanup>`

* :ref:`Enrich a record with a photo <enrich-record>` of the detected object directly from the event.
* New and updated neural networks with enhanced characteristics. 
  
  See :ref:`neural_networks`



.. rubric:: Fresh Neural Networks:


* Vehicle detection: an updated version ``car.gustav_accurate.006`` and a new model ``car.gustav_normal.004`` with better accuracy in vehicle detection.

* Body detection: brand-new body detection models ``body.gustav_accurate.019`` with enhanced characteristics and ``body.jasmine_fast_nomany.018`` (GPU only), used for body detection when there is a small number (10-20) of objects in a frame.

* Face recognition: brand-new ``nectarine_xs_320`` and ``nectarine_m_160`` face recognition models, much faster and more accurate than preceding models.

* Vehicle recognition: a brand-new ``bottas`` neural network model with better accuracy in vehicle recognition.

* Body recognition: a brand-new ``pedrec.durga`` body recognition model with significantly improved quality of recognition for various retail scenarios (stores and malls).

* Face attribute recognition: an updated version ``headpose.v3``, more accurate and faster.