Axiomtek and NVIDIA
As a member of the NVIDIA Preferred Partner, Axiomtek has been in close collaboration with NVIDIA in driving AI innovation at the edge. Combining its strong edge computing expertise with NVIDIA’s AI and deep learning technologies, Axiomtek delivers a full portfolio of GPU-optimized hardware platforms and data communication solutions for deploying AI to the edge, helping customers speed up implementation of deep learning capabilities into their IoT devices and turn Artificial Intelligence of Things (AIoT) into reality. Axiomtek has rolled out a series of edge AI embedded systems specifically built around NVIDIA® Jetson Supercomputer-on-Modules, with integrated NVIDIA GPUs to deliver exceptional computing performance for processing AI data at the edge. These edge AI systems come bundled with NVIDIA JetPack SDK to provide convenient access to the most advanced tools, making it quick and easy to set up development environments for running AI and deep learning algorithms. Depending on what they wish to accomplish, developers and system integrators can utilize pre-trained inference models to build a variety of computer vision programs with their datasets, encompassing the tasks of image classification, object detection, facial recognition, surveillance video analytics, license plate recognition, vehicle tracking, industrial machine vision inspection, and so on.
The NVIDIA Jetson™ platform
NVIDIA’s Jetson™ embedded AI platform combines GPU-driven computation hardware and rich developer SDKs to deliver the performance and efficiency needed for accelerating AI deployment at the edge, where developers can quickly build and get deep learning models running for their AI projects.
NVIDIA® Jetson™ System-on-Modules (SoMs) come in three form factor series – NVIDIA® Jetson Nano™, NVIDIA® Jetson™ TX2, and NVIDIA® Jetson AGX Xavier™ – with specifications targeting particular AI performance needs. Each system is packed with a multi-core CUDA GPU with accelerated parallel processing, as well as a complete set of hardware components including CPU, DRAM and flash storage to save development time and cost. (Source: NVIDIA Autonomous Machines)
NVIDIA JetPack SDK is a unified software package supporting all Jetson series modules. It provides comprehensive software resources needed for deploying AI models to Jetson modules, including:
- Linux OS images
- Board support package (BSP)
- CUDA Developer Toolkit
- TensorRT deep learning inference accelerator
- CUDA libraries: CUDA® Deep Neural Network (cuDNN) library and computer vision libraries (VisionWorks, OpenCV)
- Multimedia APIs and samples
Through NVIDIA JetPack SDK, software architects and engineers can make full use of the GPU power to design and train their own neural network models on popular deep learning frameworks, meanwhile optimizing GPU-accelerated inference performance when running deep learning tasks across all Jetson platforms. (Source: NVIDIA JetPack)
Axiomtek’s Edge AI Solutions
Smart farming with eBOX560-900-FL
The customer has been developing a smart camera system that enables 24/7 cattle behavior monitoring and video data analysis to improve farming operations. Using Axiomtek’s eBOX560-900-FL to combine both computer vision and artificial intelligence capabilities, the camera system is able to identify animals with specific eating or drinking activities from video footage, discover health and feeding patterns, and assess how environmental changes/farming practices impact livestock. The camera system delivers daily event notifications to farmers through their phones, while also providing remote access to detailed analytics about their herd and farm operations, which is helpful for farmers to turn visual information into actionable insights and make data-driven decisions to maximize productivity and profitability.
Video-based traffic management with eBOX800-900-FL
The customer was initiating a traffic management program involving the implementation of an on-site video IoT solution with edge AI processing power to analyze live video feeds from street surveillance cameras. It aimed to provide timely traffic control via real-time video content analysis, meanwhile relieving the burden of transferring large video datasets back to the cloud for analysis. Axiomtek’s eBOX800-900-FL edge AI computing system, with its PoE camera connectivity, deep learning capability, as well as ruggedized design for harsh outdoor use, was deployed into the customer’s platform to facilitate traffic management by performing the tasks of computer vision-enabled video analytics:
- Traffic flow measurement: vehicle counting, vehicle speed detection, etc.
- Vehicle Tracking: vehicle type classification, driving line identification, and moving direction predictions (going straight; turning right or left).
The traffic and vehicle tracking analysis based on live video streams would help transportation authorities detect incidents and give them a better understanding of the actual traffic volume on the road, allowing them to precisely estimate potential traffic jam areas/periods and take prompt actions to eliminate congestion or help drivers avoid it. The results of real-time traffic analysis can also be integrated with other intelligent traffic systems such as traffic light control to direct vehicles to alternate routes with less traffic.