Version History
Here you can find the changelog of SentiVeillance SDK Trial since it was posted on our website on 2018-02-02.
The latest version is 9.0.20231214 and it was updated on soft112.com on 27 March, 2024.
See below the changes in each version:
version 9.0.20231214
posted on 2023-12-14
Added support for Arabic license plates.
Added template matching support for Egypt, Morocco, Saudi Arabia license plates.
Fix cases where best license plate has no assigned value.
NSurveillanceEngine now throws more descriptive exception if data files are missing.
And more!
version 9.0
posted on 2023-06-13
Improved all modalities.
Added support for Kyrgyzstan, Tajikistan, El Salvador license plates. 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 VH modality.
version 9.0.20230613
posted on 2023-06-13
Fixed incorrect 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.
Fixed SurveillanceSampleCS events export error.
Fixed surveillance-sample memory leaks.
version 8.2.20230222
posted on 2023-02-22
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.
version 8.2.20221113
posted on 2022-11-13
Improved license plate origin country prediction for the United States, Canada and United Arab Emirates.
Added template matching support for the USA, Canada, Norway, Turkey and Uzbekistan license plates.
Greatly improved differentiation between zero and O letter O for license plate recognition.
version 8.2.20220916
posted on 2022-09-16
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.
version 8.2
posted on 2022-06-27
New color recognition model and new license plates symbol recognition algorithm, as well as camera capturing optimizations to reduce CPU usage.
version 8.1
posted on 2022-02-21
Updated face detection algorithm, working better with cropped faces, masked faces, bad pose faces.
Improved face blink, dark glasses, expression, gender, glasses, mouth open, beard, mustache, hat attribute detection.
Introduced heavy frame detection.
Fixed NSurveillanceEngine processing error.
version 8.0.2021.11.25
posted on 2021-11-25
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.
version 8.0.2021-05-12
posted on 2021-05-12
New features:
surveillance-images-sample - a new Java sample.
SurveillanceImagesSampleWX - a new C++ sample.
Added an API for easy selection of the best frame.
Added an API for retrieving subject information for all tracked frames.
Other improvements and bug fixes.
version 8.0.20210512
posted on 2021-05-12
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.
version 8.0
posted on 2021-01-18
New face detection and recognition of people who are wearing masks.
New algorithms that improve license plate detection and recognition speed and accuracy.
Vehicle make and model estimation.
Vehicle orientation angle estimation.
Cloth and gender estimations for pedestrians.
version 7.3.2020.11.30
posted on 2020-11-30
Fixed face medium template compatibility with MegaMatcher Accelerator.
Improved SurveillaceFacesThermalSampleCS.
Reduced GPU memory consumption for faces modality.
version 7.3.20200302
posted on 2020-03-02
Improved License plate recognition (ALPR) algorithms.
Fixed a number of bugs and issues.
Lots of improvements to SDK and samples.
version 7.3
posted on 2019-12-11
Improved Vehicle-Human and License plate recognition algorithms
Added functionality to use still images with Vehicle-Human and License plate recognition modes
Added SurveillanceImagesSampleCS and DetectFromImage tutorials
Fixed licensing related issues
Multiple GPUs (up to 8) now supported
version 7.2
posted on 2019-09-10
Improved facial recognition algorithm which provides even better accuracy.
Also a number of other minor improvements
version 7.1
posted on 2019-06-13
New improved vehicle-human and automatic license plate recognition algorithms.
Implemented region of interest property for video sources, allowing to specify where to detect vehicles, humans and license plates.
Added C++ tutorials.
Multiple minor improvements and bug fixes in the SDK and samples.
version 7.0.191272
posted on 2019-03-21
New features:
Added CPU mode for VH (Vehicle/Human) and ALPR modalities (previously only GPU mode was available).
Added a parameter for minimal IOD (interoccular distance).
Fixes and improvements.
version 6.0.183849
posted on 2018-10-10
New features:
Added Fujifilm camera support.
Fixes:
Fixed a number of minor bugs and issues.
Updates and improvements:
Improved processing scheduling.
Updated Nikon camera module to support latest devices.
version 6.0.178880
posted on 2018-05-30
Fixed issues with some activation dongles not working on Linux.
Fixed a number of minor bugs.
Updated Canon SDK to support newest devices.
version 6.0.176566
posted on 2018-03-23
Fixed issues with some media formats which were not properly converted under Windows Media framework.
Fixed a number of other minor bugs.
version 6.0.173737
posted on 2018-01-09
Fixed an issue with incorrect attribute confidences returned (Expression, Beard, Mustache).
Fixed a number of other minor bugs.