With the rising concentration of people in buildings and in transit, the need for better security is more urgent than ever. Avnet can meet this demand with its advanced facial recognition camera.
Based on Xilinx SOC chip and Xilinx AI solutions, this camera uses advanced neural network deep compression technology to run a powerful neural network cost-effectively. As a result, large-scale neural networks training based on a huge face database can be effectively implemented. Video preview and parameter setting are made possible with its support of 4K@30fps and 1080p@30fps, H.264 encoding as well as webserver function. Faces can be detected at up to 30fps at 30x30 pixels while facial features can be extracted at up to 20 faces/second. With powerful performances like these, Avnet’s advanced facial recognition camera is perfect for deployment in smart surveillance, new retail and smart transportation applications.
- Asymmetric SOC architecture: IP Camera + Xilinx SOC, powerful and professional.
- Large-scale neural networks training on large-scale face database.
- Using Xilinx's exclusive Deep Compression technology makes it possible to run a powerful neural network firstly on Xilinx's cost-effective FPGAs.
- Support face detection, tracing, quality filtering and face feature extraction, comparison.
- Face detection performance up to 30fps. Minimum detectable face: 30x30pixels.
- Face feature extraction performance up to 20 faces/second.
- Up to 1:30000/1:100000 face pictures match
- Built-in supercap helps to protect data integrity on TF card
- Smart AE based on face detection
- Smart community
- New retail
- Access control
- Smart shop