Roboflowoak Luxonis Oak Deployment Camera Resolution

Community Help
1

Hello,

I am currently in need of assistance regarding the roboflowoak deployment. My project is to use the roboflowoak luxonis oak-d deployment for my oak d camera with raspberry pi 4. The model I’m running is the YOLOv8 model and thankfully it works. The problem I have right now is that the camera frame is really lagging and it makes detecting the fast moving object almost impossible. Is there a way to lower the resolution caught by the oak d camera while using this roboflowoak package.

Thank you

  • **Project Type: YOLOv8 Detection
  • **Operating System & Browser: Raspberry Pi 4 OS
  • **Project Universe Link or Workspace/Project ID: Deploy Model (roboflow.com)
2

Based on the information provided in the extracts, there isn’t a direct mention of how to lower the resolution of the camera feed using the roboflowoak package. However, there are some general tips that might help improve the frame rate:

  1. Model Choice: The choice of model can significantly impact the frame rate. For instance, it’s mentioned that the Roboflow “Fast” model can process frames at a higher rate (9-10 FPS) compared to the “Accurate” model (4-6 FPS) when connected to a Raspberry Pi 4 Model B 8GB (Raspbian OS 64-bit) as the host device source. If you’re not already using a faster model, you might want to consider switching.

  2. Image Size: The size of the images being processed can also affect the frame rate. In the provided extracts, it’s mentioned that images were resized to 640x640 prior to training the model source. If you’re processing images at a higher resolution, reducing the image size might help improve the frame rate.

Unfortunately, without more specific information or code examples in the provided extracts, it’s difficult to provide a more detailed solution. I would recommend checking the Roboflow documentation or reaching out to their support for more assistance.

Hi! I’m Roboflow’s AI powered bot. This is an automated response powered using AI with knowledge from our docs, blog, knowledge base, and previous forum responses. If you find this to be a helpful answer, please mark it as the solution using the checkbox icon below. If this doesn’t solve your issue, please follow up with what you’ve tried/why, and the community will continue to chime in as usual.