EVA SDK includes a no-code graphical user interface (GUI) and support for 10+ types of cameras, field-ready plugins, ONNX runtime, TensorRT and OpenVINO for fast AI inference validation. Its integrated development environment (IDE) is currently built into ADLINK's NEON series AI smart cameras and EOS series AI vision systems for AI-enabled machine vision project development.
“EVA SDK is a one-API framework that lets users build edge AI vision applications with low coding efforts,” said Chia-Wei Yang, Head of Edge Vision Business Center, ADLINK. “Even without prior, or deep AI knowledge or expertise, users can develop an edge AI POC with the ready-to-use plugins and reference codes using the drag-and-drop GUI, which ultimately speeds up deployment and time to market.”
Benefits of EVA SDK:
- Allows developers to select from more than 10 cameras, with no effort required to learn camera APIs
- Simplifies integration with drag-and-drop GUI, allowing easy switching of image sources, image processing adjustment, and AI models, shortening the development time
- Supports review function of each step from image capturing, image pre-processing to AI inference, so that users can easily verify and debug if necessary, shorting the time to deployment
- Guarantees the quality of edge AI vision solutions with ADLINK-verified open-source plugins
- Enables flexible, optimized configuration for higher cost efficiency.
Using EVA SDK, developers will be able to build an AI vision application quickly without AI expertise. Currently, EVA SDK benefits applications ranging from safety AI, behaviour analysis for SOP compliance, object detection and object classification, which are all tasks typically required by smart factories, such as in semiconductor, electronics, and automobile manufacturing.
EVA SDK will continue to release more reference codes to support more edge AI applications.