hello.I can’t answer you from a technical perspective, but when I was doing my experiment, due to a bug, I was able to achieve the effect you want. You can use tee+queue to perform two pgie inferences and then osd, and finally the sink will draw the results of the two inferences mixed together. You can take a look at my other question. There is a confusing bug by using multiple “nvinfer” in parallel by “tee” - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| How to draw masks with python | 9 | 130 | September 30, 2024 | |
| Nv OSD mask | 3 | 539 | October 12, 2021 | |
| Deepstream_mrcnn_test could not output mask | 8 | 1680 | October 12, 2021 | |
| Unable to visualize and extract masks when using Mask-RCNN with default Deepstream App | 9 | 744 | October 12, 2021 | |
| Deepstream-app can not visual segmentation mask? | 8 | 1058 | October 12, 2021 | |
| Issue With segmentation mask | 13 | 612 | February 27, 2024 | |
| Drawing mask in deepstream-app | 4 | 563 | September 17, 2021 | |
| In instance segmentation, what should be the data in the mask? | 20 | 1017 | February 21, 2023 | |
| Save image sequence with Maskrcnn inference masks in python | 11 | 1262 | September 7, 2021 | |
| Draw masks using nvdsosd and python bindings | 9 | 137 | February 17, 2025 |