• Hardware Platform (Jetson / GPU):jetson
• DeepStream Version:5.1
• JetPack Version (valid for Jetson only):4.5
• TensorRT Version:7.1.3
I used primary detector (pgie) followed with tracker and then secondary classifier(sgie) in deepstream pipeline.
pgie is LPD and tracker is IOU/NvDCF and sgie is LPR related to ANPR.
In the first frame the pgie is detect all of plates and sgie is recognize the all of boxes but in the next frames the sgie is applied to the boxes that have changes in boxes like size , …
As I know, the sgie is applied in some criterion. that means the sgie is not apply to all of detected objects in all frames, but it’s applied to that boxes that have relatively changed than the previous frames. I want to know, How I can to config to sgie apply to all detected objects in all frames?