DeepStream Inference on Large Image by Splitting into Smaller Parts

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

Hi, NVs,

"I need to detect objects in a high-resolution image or video using DeepStream. I want to split the original image into smaller patch images (for example, 8 patch images per full image) and use nvinfer to obtain bounding boxes. Afterward, I aim to combine the results from the 8 patches into one. How can I achieve this?

Is this something like SAHI?

  1. The partition should have some overlap in case some objects may cross the partition parts.
  2. The nvpreprocess plugin can be used to customize the partition parts tensor generation, you can set ROIs as your partition parts.
  3. The postprocessing should be customized to handle the bboxes clusterring after the coordinates be converted back to the original image.

We do not have such sample yet.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.