From Aetina’s products, there is a series of SoM embedded platform built with Nvidia Jetson modules, which is the first pick of edge AI computing device nowadays. Aetina knows the requirements from the customers, and they put Nvidia Jetson AGX Xavier edge computing platform into the experiment to compare with RTX 2080 graphics card. In the test, they try to find the advantages of the SoM platform and Aetina Xavier edge AI computing platform to provide the most suitable product for the customers.

The hardware of pose estimation used Aetina Jetson AGX Xavier AI computing platform, which has 512 CUDA computing cores and 11 TFLOPS of AI computing inference. Compared to Nvidia RTX 2080 high-performance graphics card. Even RTX 2080 provides 20.14 TFLOPS computing performance, but it needs 225W for operation. However, with the Xavier platform, it only cost 30W for operation, bringing 0.367 TFLOPS/W, got four times better AI performance efficiency compared to RTX 2080's 0.09 TFLOPS/W.

In the meanwhile, the Xavier platform supports various I/O extension, external high-speed Net card, and flexible match with different camera modules. As an SoM platform, the Aetina Xavier platform is easy to deploy at any edge position in the embedded IoT environment, lower the AI latency, and bring a perfect AIoT chain at the edge.

With the software, Aetina R&D team optimized the Openpose algorithm, detect humans by the bone point, which can capture several people in real-time. With the data from the skeleton, it can define the pose with action, execute a higher-level application.

With Aetina Jetson AGX Xavier edge AI computing platform, high-performance with low power consumption can realize AI application of collapse detection in the intelligent medical area, also customer behavior analysis in the smart retail area. Aetina Jetson AGX Xavier edge AI computing platform should be a beneficial product for AI application developers.