how to use inference output as input for another output with deepstream

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

hi,

i have the following scenario: detecting vehicle → cropping vehicle → detecting license plate from cropped vehicle → cropping detected license plate → reading license plate.

for each stage of detection i have neural net model which relies on the previous model output. is there a way to customize this kind of pipeline in deepstream?

thanks

2

refer https://docs.nvidia.com/metropolis/deepstream/plugin-manual/index.html#page/DeepStream_Plugin_Manual%2Fdeepstream_plugin_details.02.01.html%23wwpID0E0IZ0HA
The plugin can be used for cascaded inferencing. That is, it can perform primary inferencing directly on input data, then perform secondary inferencing on the results of primary inferencing, and so on. See the sample application deepstream-test2 for more details.

3

you mean the test app that comes with the deepstream package? how can i see how it was setup? is there a tutorial for that?

thanks

4

Yes, Under sources/apps/sample_apps/, pls check the README firstly.