Release notes

Table of Contents

SentiVeillance 10.0 SDK

Subscribe for newsletters to get notifications about the releases.

March 19, 2025

  • Algorithms-related changes:
    • Now uses improved face recognition algorithms from MegaMatcher SDK 2025.1.
    • Improved ALPR OCR confidence evaluation algorithm.
    • Improved rejection of invalid object detection and stationary subjects.
    • Added ALPR support for Togo, Nigeria, Burkina Faso, Benin, Ivory Coast, Ghana and Mali.
    • Improved OCR accuracy for Argentinian license plates.
    • Added option to prioritize Arabic version of license plate when plate contains both Arabic and Latin versions.
    • Added Saudi Arabia plate type recognition by color.
    • Improved license plate template matching for Saudi Arabia plates.
    • Removed character reversion for Saudi Arabian plates.
    • Fixed tripwire distance evaluation for noisy event rejection.
    • Improved face modality performance in high load scenarios.
    • Fixed excessive ALPR modality compute requirements in some scenarios.
  • SDK-related changes:
    • NEW: Returns confidence for plate origin estimation.
    • On x86 platform, AVX2 instruction support is now required.
    • .NET minimal version upgraded 4.5 -> 4.8.
    • Java minimal version upgraded 8 -> 11.
  • Samples:
    • Image service sample now enables trial based on TrialFlag configuration file.

SentiVeillance 9.1 SDK

January 22, 2025

  • SDK-related changes:
    • Vehicle-Human functionality now is also unlocked with Faces or License Plate Recognition license.

November 8, 2024

  • SDK-related changes:
    • Fixed a rare memory leak when using Vehicle-Human and License Plate Recognition algorithms.
  • Samples:
    • Added SurveillanceImageServiceSampleCS sample which allows processing images by using REST API.
    • Updated SurveillanceSampleCS to allow exporting each subject as single image.
    • DetectFromImage tutorials now only obtains required license based on selected modality.

September 17, 2024

  • Algorithms’-related changes:
    • Added template matching support for Mexico, Vietnam, Singapore, Malaysia and Indonesia license plates.
    • Added recognition of Ä, Ö, Ü characters.
  • SDK-related changes:
    • Added analytic triggers (Tripwires and Regions), allowing to generate events if subjects cross specified lines; enters, exits or dwells inside a region for specific time.
  • Samples:
    • Updated SurveillanceSampleCS to support analytic triggers.
    • Updated SurveillanceSampleCS to remember recently opened samples and selected modalities.

May 28, 2024

  • Algorithms’-related changes:
    • Improved face quality estimation.
    • Added license plate occlusion estimation.
    • Added template matching support for New Zealand, Sri Lanka.

April 5, 2024

  • Algorithms’-related changes:
    • Biometric algorithms from MegaMatcher 13.1 product line are now used.
  • SDK-related changes:
    • Added support for processing using Intel GPUs/
  • Samples:
    • Fixed an issue in Java sample with showing mirrored images.

SentiVeillance 9.0 SDK

February 2, 2024

  • Algorithms’-related changes:
    • Improved License plate recognition accuracy.
    • Added template matching support for Oman, Kuwait, Jordan, Bahrain, Qatar.
  • SDK-related changes:
    • Allow to specify search areas when detecting from images with NSurveillanceEngine.
    • Fix NCamera now correctly returns whether it supports returning NVideoSample.
  • Samples:
    • Allow to search through priority countries in SurveillanceSampleCS.
    • Allow to export all events in SurveillanceSampleCS.
    • Allow to filter exported events by source in SurveillanceCS.
    • SurveillanceSampleCS now exports more information to CSV file: vehicle tags, if license plate from watchlist and its owner.
    • Tutorials now have option to enable GPU usage.
    • Small fixes in surveillance-web-sample.

December 14, 2023

  • Algorithms’-related changes:
    • Added support for Arabic license plates.
    • Added template matching support for Egypt, Morocco, Saudi Arabia license plates.
  • SDK-related changes:
    • Fix cases where best license plate has no assigned value.
    • NSurveillanceEngine now throws more descriptive exception if data files are missing.
  • Samples:
    • Added surveillance web sample using java and react framework.
    • Added license plate watchlist to SurveillanceSampleCS.
    • Added more event filters to SurveillanceSampleCS: in watchlist, not in watchlist, must have face, must have license plate.
    • Improved faces watchlist user interface in SurveillanceSampleCS.
    • Surveillance samples now has option to start all sources at startup if ‘–start’ command line argument is provided.
    • Fixed small issues in java surveillance-sample.

October 20, 2023

  • Fix serial number activation on nvidia jetson platform.
  • Fix high memory usage with video/camera streams.

October 3, 2023

  • Algorithms’-related changes:
    • Tuned default face algorithm properties for better operation.
  • Samples:
    • Removed thermal camera samples.
    • Fixed export functionality in SurveillanceSampleCS.
    • Fixed crash and functionality issues in Java surveillance-sample.

June 13, 2023

  • SDK-related changes:
    • Fixed incorrectl check if the object is in specified search area when CheckSearchAreaByObjectCenter parameter is set.
    • Fixed a bug with wrong object color returned when objects tracked for short duration.
  • Samples:
    • Fixed SurveillanceSampleCS events export error.
    • Fix surveillance-sample memory leaks and other minor issues.

May 30, 2023

  • Algorithms’-related changes:
    • Face recognition algorithm updated to the one used in VeriLook/MegaMatcher 13.0 SDK.
    • Improved object tracking algorithm.
    • Improved ALPR algorithm.
    • Vehicle model recognition algorithm updated with newer models and improved accuracy.
    • Added feature to recognize person’s age group (Child, Teenager, Adult, Senior) when using vehicle-human modality.
    • Added template matching support for Kyrgyzstan, Tajikistan, El Salvador license plates.
  • SDK-related changes:
    • Model optimization can now return progress.
    • Region of Interest is replaced with search areas, allowing for more precise configuration for selecting analyzed area.
    • Added feature to return formatted license plate value.
    • Changed frame decoding to only decode frames, which will be used in further processing, please update your applications if you are using ImageCaptured callback.
    • Add support for NVIDIA Jetson devices (Requires JetPack 5.1.1).
  • Samples:
    • Updated samples to include new features.
    • Removed VB.NET samples and tutorials.

SentiVeillance 8.x SDK

February 22, 2023

Algorithms-related changes:

  • Improved license plate recognition accuracy.
  • Added template matching support for Argentina, Bolivia, Brazil, Chile, Colombia, Ecuador, Paraguay, Peru, Uruguay, Venezuela, Cyprus, Ireland, Liechtenstein, Slovenia, Denmark, Andorra, Malta, Australia, Kazakhstan license plates.

November 13, 2022

Algorithms-related changes:

  • Improved license plate origin country prediction for the United States, Canada and United Arab Emirates..
  • Added template matching support for the United States, Canada, Norway, Turkey and Uzbekistan license plates..
  • Greatly improved differentiation between 0 (zero) and O (letter O) for license plate recognition.

New features:

  • Maximize video view on double click in SurveillanceSample.
  • Limit what subject information is shown in SurveillanceSample.

September 16, 2022

Algorithms-related changes:

  • Improved license plate origin country prediction.
  • Improved license plate deduplication when identical plates are present in same frame.

New features:

  • Different parameters can now be set for each NSurveillanceSource and NSurveillanceEngine task.
  • VideoTimeStamp property allows to obtain event time in a video.

Fixes:

  • Fixed incorrect default configuration for license plate algorithm.
  • Fixed issues with United Kingdom license plate recognition.
  • Fixed an issue with incorrect matching results if matching threshold of 0 was used.
  • Fixed a bug when Previous matching details were shown after using Next/Previous buttons in SurveillanceSample.
  • Fixed a bug when the “default settings” button in the SurveillanceSample caused unrelated configuration reset.

Updates and improvements:

  • Added support for United Arab Emirates license plates.
  • Updated surveillance samples to allow using different parameter sets for each video source.

July 21, 2022

Product revision number: 20220721

Product revision hash: 1d9fe2dcc356ae8e09f771f0690f0fcd1f44cc64

Algorithms-related changes:

  • Improved country codes prediction from license plates.
Fixes:
  • Fixed a number of bugs and issues.

June 22, 2022

Product revision number: 20220622

Product revision hash: 1d6dc6655b876822cf052851086708af83caa958

The first release of SentiVeillance 8.2 SDK.

Algorithms-related changes:

  • New color recognition model.
  • New license plates symbol recognition.

Updates and improvements:

  • Added camera capturing optimizations to reduce CPU usage.

February 21, 2022

Product revision number: 20220221

Product revision hash: 529f1712893f685032e10231f284725b6cb09f12

Fixes:

  • Fixed NSurveillanceEngine processing error.

February 2, 2022

Product revision number: 20220202

Product revision hash: 1134bc94481a4b6b83301a67c3de01d8e6e95ab4

The first release of SentiVeillance 8.1 SDK.

Algorithms-related changes:

  • Updated face detection algorithm, working better with cropped faces, masked faces, bad pose faces (profile).
  • Greatly improved face blink, dark glasses, expression, gender, glasses, mouth open, beard, mustache, hat attribute detection. Introduced heavy frame detection.

Fixes:

  • Fixed a memory leak when using NSurveillanceEngine.
  • Fixed several minor bugs and issues.

Updates and improvements:

  • Updated biometric components to the MegaMatcher 12.3 line.

November 25, 2021

Product revision number: 20211125

Product revision hash: 2fc3b955e721a36b25fd74b74d3fdd05275d7666

Algorithms-related changes:

  • Clothing details now also determines clothes by body parts: headwear, torso, arms, legs, feet.
  • Improved vehicle model prediction.

New features:

  • New Java sample: surveillance-sample.

Fixes:

  • Fixed a number of minor bugs, crashes and issues.

May 12, 2021

Product revision number: 20210512

Product revision hash: bd63b6a59be30849e9a42ecf278219074596696b

New features:

  • API for easy selection of the best frame added.
  • API for retrieving subject information for all tracked frames added.
  • New Java sample: surveillance-images-sample.
  • New C++ sample: SurveillanceImagesSampleWX.

Fixes:

  • Fixed a number of bugs and issues.

Updates and improvements:

  • Multiple minor improvements.

January 19, 2021

Product revision number: 20210119

Product revision hash: 0a93df68fdebe4f2c9c725d5dd1cc132f67acddb

The first release of SentiVeillance 8.0 SDK.

Algorithms-related changes:

  • Vehicle type, model/make and orientation estimation added.
  • Person’s clothing estimation added.
  • Improved faces, vehicle-human and license plate recognition algorithms.

New features:

  • Face modality can now be combined with the vehicle-human modality.
  • FacesThermalSampleCS and SurveillanceThermalFacesSampleCS added.
  • SurveillanceImagesSampleCS and SurveillanceImagesSampleVB added.