NVTracker functionality

[gauravchandgupta]

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU) GPU A100 **
**• DeepStream Version 6.4 **
• 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)
Let’s say we have 3 objects detected by detector in frame 0 and in frame 1 only 2 objects are detected by detector and 1 object is missed by the detector. In our pipeline we use detector followed by tracker,so we are expecting that tracker should have still have given us 3 objects in frame1 but it gives only 2.This issue is seen in 6.4 deepstream tracker. Please let me know how can this be overcome ?

[kesong]

Can you have a try with shadow tracking target data? Gst-nvtracker — DeepStream documentation 6.4 documentation

[gauravchandgupta]

Thanks for helping us.We tried your suggestion and we probed the source pad of nvtracker in python like this
def tracker_probe(self,pad, info, u_data):
gst_buffer = info.get_buffer()
if not gst_buffer:
print(“Unable to get GstBuffer”)
return
print(“in tracker probe”)
batch_meta = pyds.gst_buffer_get_nvds_batch_meta(hash(gst_buffer))

    batch_user_meta_list = batch_meta.batch_user_meta_list
    print("batch_user_meta_list",batch_user_meta_list)
    while batch_user_meta_list is not None:
        user_meta = pyds.NvDsUserMeta.cast(batch_user_meta_list.data)
        user_meta_base_meta = user_meta.base_meta
        print("hello",int(user_meta_base_meta.meta_type))
        if int(user_meta_base_meta.meta_type) == 19:
            user_meta_data = pyds.NvDsTargetMiscDataBatch.cast(user_meta.user_meta_data)
            ab =  pyds.NvDsTargetMiscDataStream.cast(user_meta_data.list)

But we get error when we run the above code in the last line . So can u help us in getting rect_params field available in NvDsTargetMiscDataFrame in python. Or do we need to use another method to get all the bbox of shadow tracks by probing tracker source pad.

[kesong]

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

You method is right. Maybe you need write python bindings for NvDsTargetMiscDataFrame.