Mixtile Edge AI solution supports ONVIF cameras and leverages object detection, object classification, real-time analysis, and intelligent monitoring to create IoT video analytics applications across the security, transportation, logistics, retail, industry, and agriculture sectors.
The hardware is based on the time-tested Mixtile Edge 2 Kit IoT gateway powered by a Rockchip RK3568 SoC with a 1 TOPS NPU and 1080p60 VPU, or Mixtile Blade 3 SBC featuring the more powerful Rockchip RK3588 octa-core SoC with a 6 TOPS AI accelerator and an 8Kp60 VPU. The former can analyze up to 10 streams in real-time, and the latter up to a whopping 40 streams.
So the novelty here is on the software side that has been developed by Mixtile and works the following way: The ONVIF cameras transmit video streams to a Mixtile Edge AI Box over the network. The Edge AI Box then runs pre-trained AI models to analyze the streams in real-time and sends the analyzed data to third-party video management software (VMS) so that alarms can be triggered, recordings be started, and/or notifications sent to administrators’ mobile devices based on predefined rules. The diagram below summarizes how this all works.
Mixtile Edge AI solution supports four pre-trained models out of the box:
- Behavior Analysis detects whether a child, worker, or elder is falling, spots theft in stores, identifies fights, etc… to ensure safety and security.
- Face Recognition with support for identifying attributes such as gender, hairstyle, and clothing. It’s useful for airport security, office attendance management, and community access control.
- Quantity Statistics leverages the Mixtile Edge AI Box to count visitor entries and exits at museums or art galleries, monitoring engagement levels efficiently. It can also be used in parking lots to assess occupancy levels, and in the agriculture field, to estimate orchard yields.
- Object Classification identifies pedestrians and vehicles on the road to enhance the safety of automatic driving vehicles, analyzes customers’ behavior to optimize sales for Smart Retail, monitors forest fires and analyzes air pollution emissions, etc…
Customized models can also be trained with support for TensorFlow, Caffe, TFLite, PyTorch, ONNX NN, and Android NN. Workloads run at low power with the Mixtile Edge 2 Kit consuming around 4W, and the Blade 3 about 9 Watts.
Mixtile supports its customers by responding to all technical inquiries for each project within 48 hours, and comprehensive documentation with the SDK, development docs, user manuals, and tutorials are also available. You can find out more about Mixtile Edge AI boxes and solutions on the relevant page on the Mixtile website, and contact the company if you are interested in its video analytics solution.
![cnxsoft-logo-square](https://www.cnx-software.com/wp-content/uploads/2018/03/cnxsoft-logo-square.jpg)
This account is for paid-for, sponsored posts. We do not collect any commission on sales, and content is usually provided by the advertisers themselves, although we sometimes write it for our clients.
Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress