Table of Contents
SentiVeillance 8.x SDK
February 22, 2023
- 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
- 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.
- Maximize video view on double click in SurveillanceSample.
- Limit what subject information is shown in SurveillanceSample.
September 16, 2022
- Improved license plate origin country prediction.
- Improved license plate deduplication when identical plates are present in same frame.
- Different parameters can now be set for each NSurveillanceSource and NSurveillanceEngine task.
- VideoTimeStamp property allows to obtain event time in a video.
- 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, 2022Product revision number: 20220721 Product revision hash: 1d9fe2dcc356ae8e09f771f0690f0fcd1f44cc64 Algorithms-related changes:
- Improved country codes prediction from license plates.
- Fixed a number of bugs and issues.
June 22, 2022Product 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.
- Added camera capturing optimizations to reduce CPU usage.
February 21, 2022Product revision number: 20220221 Product revision hash: 529f1712893f685032e10231f284725b6cb09f12 Fixes:
- Fixed NSurveillanceEngine processing error.
February 2, 2022Product 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.
- Fixed a memory leak when using NSurveillanceEngine.
- Fixed several minor bugs and issues.
- Updated biometric components to the MegaMatcher 12.3 line.
November 25, 2021Product 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 Java sample: surveillance-sample.
- Fixed a number of minor bugs, crashes and issues.
May 12, 2021Product 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.
- Fixed a number of bugs and issues.
- Multiple minor improvements.
January 19, 2021Product 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.
- Face modality can now be combined with the vehicle-human modality.
- FacesThermalSampleCS and SurveillanceThermalFacesSampleCS added.
- SurveillanceImagesSampleCS and SurveillanceImagesSampleVB added.