Xilinx AI Video Analytics
Real-Time Analytics For A Smarter, Safer World
Xilinx is the Choice for Critical AI Video Analytics Applications
For critical AI video analytics applications that preserve human health, protect human life, and secure property, deterministic low latency performance is mandatory.
The Xilinx AI Video Analytics platform powers solutions that address the world’s most critical and complex inferencing applications.
Combining sub-100ms end-to-end pipeline latency with the massive parallel processing of Xilinx Alveo accelerators cards, Xilinx delivers the industry’s best performance at the absolute lowest hardware investment.
Featured Video
Low Latency Solutions for Your AI Video Analytics Needs
Featured Solutions
Ready-to-Deploy Analytics Solutions From our Ecosystem Partners
Smart Retail/City/Building
- Full video AI solutions at the edge
- Smart city, smart building, and smart retail
- High efficiency, low latency, and scalability
Migration and Acceleration
- Toolset delivering easy migration of existing AI applications
- High-performance plug-and-play AI inference accelerator
Edge AI Training
- AI training at the edge on FPGA with a 10x performance/cost advantage vs GPUs
- Support for Tensorflow, PyTorch, and Keras.
Powered by Alveo
Low Latency For The Most Complex Applications
Powered by Alveo™ data center accelerator cards, the Xilinx platform efficiently handles complex AI video applications on a single device.
- Optimized AI/ML performance
- Massively parallel to handle multiple models elegantly on minimal hardware
- Deterministic sub-100ms pipeline latency
Industry’s Lowest TCO and Lowest Deterministic Latency
Developers
Build Your Own AI Video Analytics Solution with VMSS
At the heart of the Xilinx AI Video Analytics platform is our Video Machine-learning Streaming Server (VMSS) framework. VMSS targets AI applications such as facial recognition, virtual fencing, crowd statistics, traffic monitoring, and object detection.
The VMSS Advantage
- Customizable, smart video processing
- Low latency, high throughput image processing engine
- Independently scalable workloads for optimal resource use
- Custom plugins for hardware acceleration and software processing
