Xilinx: Enabling Vision Guided Machine Learning Applications with reVISION™
- Today’s embedded vision systems have evolved to include vision guided machine learning applications that need to be highly responsive, flexible enough to keep up with latest networks and sensor technology, and have the ability to connect to any machine (IoT).
Xilinx® SoC and MPSoC devices uniquely address the requirements of today’s vision guided machine learning applications but traditionally have been hard to adopt for those without expert hardware or RTL-based design experience. The reVISION stack breaks through this barrier to adoption to include software defined development resources for platform, algorithm and application development.
- No Hardware Expertise Required
- Familiar eclipse-based development environment using C, C++ and/or OpenCL languages
- Accelerate development with ready to use OpenCV libraries
- Support for popular frameworks and neural networks
- Responsiveness – Lowest Latency From Sensor To Inference and Control
- Up to 6x better images/second/watt in machine learning
- 42x higher frames per second for computer vision processing
- 1/5 the latency (in milliseconds)
- Reconfigurability for Latest Networks and Sensors
- Only devices to offer ‘future-proof’ hardware reconfigurability to keep up with rapidly evolving neural networks and sensor evolution
- Any-to-Any Connectivity and Sensor Interfaces
- Up to 12x more bandwidth relative to alternative SoCs currently in the market, including support for native 8K and custom resolutions
- Significantly more high and low bandwidth sensor interfaces and channels, enabling highly differentiated combinations of sensors such as RADAR, LiDAR, accelerometers and force torque sensors
- Industry-leading support for the latest data transfer and storage interfaces, easily reconfigured for future standards
- Designers always wanted more flexibility in planning the circuit layout and achieve an overall PCB routing that is more manageable and straightforward.
- New designs are moving toward smaller, more robust solution. For optocoupler gate drivers, the trend is towards higher integration.
- Low-profile components are preferred over higher profile ones. For example, a low profile single transformer for each driver enables improved reliability and robustness compared to heavier, higher profile transformers that are more vulnerable to mechanical vibration.
Need Immediate Assistance?Call Toll Free 1-888-257-5027 or email us: firstname.lastname@example.org