SenseCraft AI: Upgrade Any Camera with YOLOv8 in A No-Code Way!
Extracting valuable, real-time insight from large quantities of video data requires inference from the edge to the cloud. Leveraging the NVIDIA TensorRT and DeepStream SDK, we can maximize the performance of inferencing YOLOv8 models on NVIDIA Jetson.
Step further, we are introducing SenseCraft AI, a new suite of applications including an open-source inference server and web UI to deploy any YOLOv8 to NVIDIA Jetson Orin devices and visualize captured streams, without any line of code. Step to the repository 👉 github.com/Seeed-Studio/SenseCraft-AI
- Experiment with a YOLOv8 model trained on the Microsoft COCO;
- Supporting object detection, segmentation, and pose estimation tasks;
- Click-to-deploy applications for industries such as people counting, vehicle detection, and helmet detection;
- Custom YOLOv8 model and fast performance testing(coming soon).
How to start?
- Prepare an NVIDIA Jetson Orin device with Jetpack 5.0.1 and above; Connect Jetson to a display and power on it;
Don’t have one? Check out Seeed’s reComputer of Orin Nano/Orin NX series, edge AI box with production-grade Orin module and carrier board, and built-in Jetpack system.
2. Quickstart in one-line script!
bash ./script/edge-ai-setup.sh
Build your own model (BYOM)!
Datasets
If you have a specific AI application and want to bring your own AI model that is suitable for your application, you can collect your own dataset, label them, and then train using YOLOv8.
If you do not want to collect data by yourself, you can also choose public datasets which are readily available. You can download a number of publically available datasets such as the COCO dataset, Pascal VOC dataset, and much more. Roboflow Universe is a recommended platform that provides a wide range of datasets and it has 90,000+ datasets with 66+ million images available for building computer vision models. Also, you can simply search open-source datasets on Google and choose from a variety of datasets available.
Follow up our wiki with clear steps for training!
If you have any specific requirements for the AI model used in the application, you can also bring your own model here, collect your own dataset, label it, and then train the model using YOLOv8.
Here we have three recommended methods for training a model:
You can easily integrate Roboflow into Ultralytics HUB so that all your Roboflow projects will be readily available for training. Here it offers a Google Colab notebook to start the training process easily and also view the training progress in real-time.
2. Use a Google Colab workspace created by us.
Here we use Roboflow API to download the dataset from the Roboflow project. Click here to open an already prepared Google Colab workspace and go through the steps mentioned in the workspace.
3. Use a local PC for the training process.
Here you need to make sure you have a powerful enough GPU and also need to download the dataset manually.
Have a try now! Time to upgrade any legacy camera with the state of art computer vision!
Seeed NVIDIA Jetson Ecosystem
Seeed is an Elite partner for edge AI in the NVIDIA Partner Network. Explore more carrier boards, full system devices, customization services, use cases, and developer tools on Seeed’s NVIDIA Jetson ecosystem page.
Partner with us!
Join the forefront of AI innovation with us! Harness the power of cutting-edge hardware and technology to revolutionize the deployment of machine learning in the real world across industries. Be a part of our mission to provide developers and enterprises with the best ML solutions available. Check out our successful case study catalog to discover more edge AI possibilities!
Take the first step and send us an email at [email protected] to become a part of this exciting journey!
More Resources
- Jetson Orin NX Series and Jetson Orin Nano Series – Thermal Design Guide, by NVIDIA
- Seeed’s NVIDIA Jetson Platform to Be Manufactured in Vietnam
- Find everything about Seeed’s Jetson on the ecosystem page
- Download our latest Jetson Catalog to find one option that suits your projects.
- If you can’t find the off-the-shelf Jetson hardware solution for your needs, please check out our customization services, and submit a new product inquiry to us at [email protected] for evaluation.
- Find all useful developer tools at our wiki, we help you get started with AI projects easily!
About Author
rainbow obby, thanks for sharing that important tip! Having a powerful GPU is indeed crucial for smooth and efficient training when working with YOLOv8 and other computer vision models. It can significantly impact the speed and accuracy of your model’s training process. Make sure to choose the right hardware to get the best results.
you need to make sure you have a powerful enough