2019 R1
Pre-release
Pre-release
This release is a collection of GStreamer* plugins (GVA plugins / GStreamer* Video Analytics plugins) to enable video analytics applications on Intel hardware. The complete solution leverages
- Open source GStreamer* framework for pipeline management
- GStreamer* plugins for input and output such as media files and real-time streaming from camera or network
- Video decode and encode plugins, either CPU optimized plugins or GPU-accelerated plugins based on VAAPI
and additionally, installs the following Deep Learning specific plugins from this repository:
- Inference plugins based on Intel® OpenVINO™ Toolkit for CNN models inference targeting various computer vision tasks such as object detection, recognition, tracking, classification and others;
- either model converted from training frameworks TensorFlow*, Caffe*, etc or model from Open Model Zoo.
- Visualization of computer vision results (such as bounding boxes and labels of detected objects) on top of video stream;
- Flexible configuration of inference pre-processing and post-processing;
- Inference acceleration on Intel hardware supported by Intel® OpenVINO™ Toolkit, including CPU, GPU, VPU.
This release is targeting the following platforms:
- Server platforms with Intel® Xeon™ CPU starting from BDW with Linux* OS
- Desktop platforms with Intel® Core™ CPU and integrated graphics starting from BDW with Linux* OS
* Other names and brands may be claimed as the property of others.