SDK for facial identification and movement tracking integration into surveillance (CCTV) software applications, with rich features.
- SentiVeillance SDK
- License :Trial
- OS:Windows All
SentiVeillance SDK Description
Formerly known as VeriLook Surveillance SDK, SentiVeillance SDK is a tool that can be integrated into your software projects to facilitate biometric face identification via webcam as well as a movement tracker for a single object or a group of objects. It’s dedicated for passive identification and can be used within law enforcement, traffic monitoring, and other fields.
How it works is that the system detects faces in real time and matches them against all entries within a database which was previously created using a watchlist. It can monitor and detect the faces of multiple people or objects at the same time as well as classify them to tell apart people from vehicles.
People can be profiled based on gender, age, glasses, facial hair, and facial expressions (e.g. smile, open mouth, closed eyes, wink). It’s also possible to load data from video files. Events are automatically saved within logs for your later examination.|
However, natural events such as rain, snow or trees swayed by wind are ignored. Moreover, SentiVeillance SDK can be instructed to auto-add unknown faces to the watchlist. Up to ten cameras can be connected to one computer, and data can be seamlessly synced across all machines in the network.
The tool supports a facial extractor that’s capable of creating face templates using face images. It’s a separate component from the package that allows usage with still images when video content is not possible. In addition to Windows, SentiVeillance SDK supports Linux. It supports multiple programming languages.
- 3GHz or better processor with 4 processor cores is recommended for systems with 1 or 2 cameras connected to the same PC or server. Systems with more cameras will need a graphical processing unit
- SSE2 (Streaming SIMD Extensions 2) support
- At least 2 processor cores are required to process surveillance data from one camera with several faces in a frame. If there are more than 2 cameras in a surveillance system, several networked PCs or a multi-processor server will be required to process da
- If large number of faces in a frame is expected, more processor cores, more powerful processor or even multi-processor server may be required to process surveillance data and keep the acceptable performance.
- A graphical processing unit (GPU) is needed for surveillance system with more than 2 cameras connected to the same PC or server.
- NVIDIA GeForce GTX 1080 GPU or better is recommended for systems with up to 10 cameras.
- At least 8GB RAM
- A high-resolution digital camera. The camera resolution may vary depending on the actual application. The recommended resolution is about 2 MegaPixel, as processing video from cameras with higher resolution will require more free RAM and more powerful pro
- .NET framework 3.5 or newer
- DirectX 9.0 or later
- Visual Studio 2012 or newer (for application development under C/C++, C#, Visual Basic .NET)
- or Java 1.6 SDK or later
Limitations in the unregistered version
- 30 days trial