object detection and tracking on android Yolov8 about ultralytics

[github-actions]

👋 Hello @aamir0011, thank you for your interest in Ultralytics YOLOv8 🚀! We recommend a visit to the Docs for new users where you can find many Python and CLI usage examples and where many of the most common questions may already be answered.

If this is a 🐛 Bug Report, please provide a minimum reproducible example to help us debug it.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset image examples and training logs, and verify you are following our Tips for Best Training Results.

Join the vibrant Ultralytics Discord 🎧 community for real-time conversations and collaborations. This platform offers a perfect space to inquire, showcase your work, and connect with fellow Ultralytics users.

Install

Pip install the ultralytics package including all requirements in a Python>=3.8 environment with PyTorch>=1.8.

pip install ultralytics

Environments

YOLOv8 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all Ultralytics CI tests are currently passing. CI tests verify correct operation of all YOLOv8 Modes and Tasks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@aamir0011 hello! It's great to hear you've successfully deployed YOLOv8 for object detection on Android. 😊 For object tracking, you can consider exporting the YOLO model to ONNX and using it with an Android-compatible inference framework like OpenCV DNN, which recently added support for ONNX models. Here's a simplified guide:

1. Export YOLOv8 model to ONNX format:

   yolo export model=yolov8n.pt format=onnx

2. Integrate the ONNX model with OpenCV in your Android app. You'd need OpenCV Android SDK installed in your project. Here's a rough snippet on how you might load and use the model for inference:

   // Load the ONNX model using OpenCV DNN
   String modelPath = "path_to_your_model.onnx";
   Net net = Dnn.readNetFromONNX(modelPath);
   
   // Assuming 'frame' is your input image
   Mat blob = Dnn.blobFromImage(frame, 1.0 / 255, new Size(640, 640), new Scalar(0, 0, 0), true, false);
   net.setInput(blob);
   
   // Forward pass
   Mat detections = net.forward();

3. For tracking, post-process the detection outputs to maintain object identities across frames. You might need to implement or integrate a lightweight tracking algorithm suitable for mobile devices, such as SORT or a simple centroid-based tracker. Due to the complexity and additional computation, consider the performance and battery impact on the device.

While this approach simplifies the concept, actual implementation might require more steps, and performance optimizations, especially for real-time applications on Android devices.

Feel free to explore more and adjust based on your specific needs. Good luck with your project!

[github-actions]

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐

[cbiras]

Hello @aamir0011! I am trying to do object detection too, but with the smallest model, using torchscript, I have around 4 fps. I want to push this to real-time as much as possible, so I'm curious how did you deal with inference speed?