Edge Artificial Intelligence
Faster, flexible, scalable AI deployment for everyone. We aim to cover all kinds of AI scenarios at our open-source platform to accelerate industries’ AI transformations.
We are looking forward to leveraging local and global resources to accelerate next-gen AI product together with you.Powered by reComputer - NVIDIA Jetson Series
Generative AI
| Speech Subtitle Generation on Nvidia Jetson | Deploy Whisper on NVIDIA Jetson Orin for Real time Speech to Text | How to Run a Local LLM Text-to-Image on reComputer |
|---|---|---|
 |  |  |
| In this wiki, we introduce you Speech Subtitle Generation on Jetson, which can offer real-time speech-to-subtitle services while avoiding information leakage on the internet. | In this wiki we introduce you Real Time Whisper on Jetson, this integration enables speech processing directly on the device, eliminating the need for constant network connectivity and enhancing privacy and security. | This wiki encompasses setting up and deploying local LLM-based text-to-image generation models on the Nvidia Jetson Orin NX 16GB |
Object Recognition
| Decision Support Systems | Object Detection with Lumeo | Object Detection with AlwaysAI |
|---|---|---|
 |  |  |
| CVEDIA-RT is a modular, cross-platform AI inference engine that provides the solid foundations for building decision support systems, designed from the ground-up with developers and integrators in mind. | Lumeo is a no-code video analytics platform that enables you to rapidly design, deploy, and monitor custom video analytics and other vision-AI enabled applications. | AlwaysAI is an essential Computer Vision development platform for creating and deploying machine learning applications on Edge devices such as NVIDIA® Jetson devices.. |
| Hard Hat Detection with EI | Object Detection with Yolov5 | Object Detection with Yolov8 |
|---|---|---|
 |  |  |
| Edge Impulse is a machine learning development platform that enables developers to create and deploy custom ML models to edge devices. Developers can easily build and deploy machine learning models on embedded devices. | YOLOv5 is one of the most famous object detection algorithms available. It only needs few samples for training, while providing faster training times and high accuracy. | YOLOv8 is one of the most famous object detection algorithms available. It only needs few samples for training, while providing faster training times and high accuracy. This is built with TensorRT. |
| Object Detection with Yolov8 | Object Detection with Scailable | Object Detection with Roboflow |
|---|---|---|
 |  |  |
| YOLOv8 is one of the most famous object detection algorithms available. It only needs few samples for training, while providing faster training times and high accuracy. This is built with DeepStream SDK. | Scailable provides a platform for creating and managing Edge AI solutions at scale. With Scailable, you can simply configure any supported edge device (such as a router, gateway, or IPC) to turn it into a "smart" device. | Roboflow Inference is the easiest way to use and deploy computer vision models, providing an HTTP Roboflow API used for running inference. |
| Mask Detection | Knife Detection(X-ray) | Warehouse Detection with no code |
|---|---|---|
 |  |  |
| MaskCam is developed by Berkeley Design Technology, Inc. (BDTI) and Tryolabs S.A., with development funded by NVIDIA. | Yanlu Wei and Renshuai Tao et al provides and we introduces this fundamental project that we are going to deploy a Deep Learning model on reComputer J1010 that could detect prohibited items (knives). | Seeed Studio provides the experience of no code achieving the quick and easy object recognition, working with node-red. |
| Farm Guards with no code |
|---|
 |
| Farm Guards with no code |
Sound Recognition
 |
| Cochl.Sense is an Machine Learning regarding listening development platform for deploying deep learning applications on edge devices such as NVIDIA® Jetson devices. |
Enhance Deep Learning Model
| Utilize Deci Platform | Train and Deploy YOLOv8 Models | OTA Update with Allxon |
|---|---|---|
 |  |  |
| Deci platform enables you to manage, optimize, deploy and serve models in your production environment with ease. You can continue using popular DL frameworks, such as TensorFlow, PyTorch, Keras and ONNX. | This wiki will guide you to train and deploy a object detection model for traffic scenes on the reComputer and use the YOLOv8 object detection algorithm as an example | Allxon can assist you to deliver the OTA Payload Package to the Jetson devices via the Allxon DMS Portal. For users or manufactures who are in charge of generating the OTA Payload Package, it's very easy to upload the OTA Payload Package. |
Powered by reTerminal & reTerminal DM - Raspberry Pi CM4
Object Recognition
| Color Detection on reTerminal with OpenCV | Face Detection on reTerminal with OpenCV | Object Detection on reTerminal with OpenCV |
|---|---|---|
 |  |  |
| OpenCV is a powerful and open-source computer vision library designed for real-time computer vision tasks. It provides a comprehensive set of tools and functions that enable developers to work with images and videos, offering solutions for tasks like image processing, object detection, face recognition, and more. | In this guide, we'll explore Face Detection using the Haar Cascade method, a crucial technique in computer vision that utilizes a machine learning model to identify facial features. We'll specifically focus on implementing this on the reTerminal using the Raspberry Pi camera. | In this documentation, we will delve into using the Raspberry Pi camera and ReTerminal to detect approximately 100 images using a pre-trained EfficientNet model. |
| Object Tracking on reTerminal with OpenCV | Object Detection on reTerminal with TensorFlow Lite | Object detection on reTerminal with Edge Impulse |
|---|---|---|
 |  |  |
| Object tracking is the process of consistently locating a specific object across consecutive frames in a video. In the realm of single object trackers, the initial frame serves as a reference, with the target object marked by a bounding rectangle. | TensorFlow Lite is a set of tools that enables on-device machine learning by helping developers run their models on mobile, embedded, and IoT devices. The key features of TensorFlow Lite are optimized for on-device machine learning, with a focus on latency, privacy, connectivity, size, and power consumption. | In this wiki, we explore Object detection with Edge Impulse and reTerminal. Edge Impulse empowers developers to create and optimize embedded machine learning solutions using real-world data. Let's delve into the details. |
| Object Detection on reTerminal DM with Yolov5 | Object detection on reTerminal DM with Edge Impulse |
|---|---|
 |  |
| YOLOv5 is one of the most famous object detection algorithms available. It only needs few samples for training, while providing faster training times and high accuracy. | In this wiki, we explore Object detection with Edge Impulse and reTerminal DM. Edge Impulse empowers developers to create and optimize embedded machine learning solutions using real-world data. Let's delve into the details. |
✨ Contributor Program
- The Seeed Studio Contributor Program is a collaborative program designed to unite our friends from the community and co-build innovative solutions with us.
- We are really looking forward your contributions:
Tech Support & Product Discussion
Thank you for choosing our products! We are here to provide you with different support to ensure that your experience with our products is as smooth as possible. We offer several communication channels to cater to different preferences and needs.