How to identify customized detection result from yolov5 in kafka server？

[user41240]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
GPU
• DeepStream Version
6.1
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
11.6
• Issue Type( questions, new requirements, bugs)
new requirements
• 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)
After Deepstream deployed yolov5, each number in the identification result was merged together and sent to kakfa as required, as shown in the figure below. The identification results are sent to kafka in a separate format T,T,3,1,2,2. The requirement is to encapsulate the identification results into two pieces of data, T31 and T22, and then send them to kafka.

[yingliu]

Hello @user41240 Would mind changing the summary&description to English? It will be helpful for other users outside China, thanks.

[user41240]

OK, changed, thanks.

[Fiona.Chen]

You need to identify the characters into string in deepstream app and define your own message structure to contain the strings and send to kafka.

[user41240]

Are there any similar examples or tutorials, please? Thanks

[Fiona.Chen]

There is no update from you for a period, assuming this is not an issue anymore.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

@user41240

Are there any similar examples or tutorials, please?

No. What blocks you? DeepStream is a SDK but not an app. We already have sample deepstream-test5(DeepStream Reference Application - deepstream-test5 app — DeepStream 6.3 Release documentation) for how to transfer message through nvmsgbroker (Gst-nvmsgbroker — DeepStream 6.3 Release documentation) with kafka. The message you need should be customized by yourself. The related APIs are introduced in Gst-nvmsgconv — DeepStream 6.3 Release documentation.