Python Deepstream Tracking Object Time in Frame

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hi, I would like to extract the time that the tracked object is in frame. Currently I am using the Deepstream_test_3 and Deepstream_test_2 for pulling and tracking object via the rtsp stream from an IP Camera. Would anyone be able to recommend the approach?

# tiler_sink_pad_buffer_probe  will extract metadata received on OSD sink pad
# and update params for drawing rectangle, object information etc.
def tiler_src_pad_buffer_probe(pad,info,u_data):
    frame_number=0
    num_rects=0
    gst_buffer = info.get_buffer()
    if not gst_buffer:
        print("Unable to get GstBuffer ")
        return

    # Retrieve batch metadata from the gst_buffer
    # Note that pyds.gst_buffer_get_nvds_batch_meta() expects the
    # C address of gst_buffer as input, which is obtained with hash(gst_buffer)
    batch_meta = pyds.gst_buffer_get_nvds_batch_meta(hash(gst_buffer))
    l_frame = batch_meta.frame_meta_list
    while l_frame is not None:
        try:
            # Note that l_frame.data needs a cast to pyds.NvDsFrameMeta
            # The casting is done by pyds.glist_get_nvds_frame_meta()
            # The casting also keeps ownership of the underlying memory
            # in the C code, so the Python garbage collector will leave
            # it alone.
            frame_meta = pyds.glist_get_nvds_frame_meta(l_frame.data)
        except StopIteration:
            break

        '''
        print("Frame Number is ", frame_meta.frame_num)
        print("Source id is ", frame_meta.source_id)
        print("Batch id is ", frame_meta.batch_id)
        print("Source Frame Width ", frame_meta.source_frame_width)
        print("Source Frame Height ", frame_meta.source_frame_height)
        print("Num object meta ", frame_meta.num_obj_meta)
        '''
        frame_number=frame_meta.frame_num
        l_obj=frame_meta.obj_meta_list
        num_rects = frame_meta.num_obj_meta
        obj_counter = {
        PGIE_CLASS_ID_VEHICLE:0,
        PGIE_CLASS_ID_PERSON:0,
        PGIE_CLASS_ID_BICYCLE:0,
        PGIE_CLASS_ID_ROADSIGN:0
        }
        while l_obj is not None:
            try: 
                # Casting l_obj.data to pyds.NvDsObjectMeta
                obj_meta=pyds.glist_get_nvds_object_meta(l_obj.data)
            except StopIteration:
                break
            obj_counter[obj_meta.class_id] += 1
            try: 
                l_obj=l_obj.next
            except StopIteration:
                break
        display_meta=pyds.nvds_acquire_display_meta_from_pool(batch_meta)
        display_meta.num_labels = 1
        py_nvosd_text_params = display_meta.text_params[0]
        py_nvosd_text_params.display_text = "Frame Number={} Number of Objects={} Vehicle_count={} Person_count={}".format(frame_number, num_rects, obj_counter[PGIE_CLASS_ID_VEHICLE], obj_counter[PGIE_CLASS_ID_PERSON])
        py_nvosd_text_params.x_offset = 10;
        py_nvosd_text_params.y_offset = 12;
        py_nvosd_text_params.font_params.font_name = "Serif"
        py_nvosd_text_params.font_params.font_size = 10
        py_nvosd_text_params.font_params.font_color.red = 1.0
        py_nvosd_text_params.font_params.font_color.green = 1.0
        py_nvosd_text_params.font_params.font_color.blue = 1.0
        py_nvosd_text_params.font_params.font_color.alpha = 1.0
        py_nvosd_text_params.set_bg_clr = 1
        py_nvosd_text_params.text_bg_clr.red = 0.0
        py_nvosd_text_params.text_bg_clr.green = 0.0
        py_nvosd_text_params.text_bg_clr.blue = 0.0
        py_nvosd_text_params.text_bg_clr.alpha = 1.0
        #print("Frame Number=", frame_number, "Number of Objects=",num_rects,"Vehicle_count=",vehicle_count,"Person_count=",person)
        pyds.nvds_add_display_meta_to_frame(frame_meta, display_meta)
        print("Frame Number=", frame_number, "Number of Objects=",num_rects,"Vehicle_count=",obj_counter[PGIE_CLASS_ID_VEHICLE],"Person_count=",obj_counter[PGIE_CLASS_ID_PERSON])

        # Get frame rate through this probe
        fps_streams["stream{0}".format(frame_meta.pad_index)].get_fps()
        try:
            l_frame=l_frame.next
        except StopIteration:
            break

    return Gst.PadProbeReturn.OK

I’m think it will have to extract with this probe, but I don’t know what meta data to call/how to display the time elapsed from the original frame the object was detected.

2

Can you get “frame_meta->ntp_timestamp” ?

3

I’m declaring the variable along with others:

ntp_timestamp = frame_meta.ntp_timestamp    
        frame_number=frame_meta.frame_num
        l_obj=frame_meta.obj_meta_list
        num_rects = frame_meta.num_obj_meta
        obj_counter = {
        PGIE_CLASS_ID_VEHICLE:0,
        PGIE_CLASS_ID_PERSON:0,
        PGIE_CLASS_ID_BICYCLE:0,
        PGIE_CLASS_ID_ROADSIGN:0

then printing it out in console, but it always is zero.

print(ntp_timestamp, "Frame Number=", frame_number, "Number of Objects=",num_rects,"Vehicle_count=",obj_counter[PGIE_CLASS_ID_VEHICLE],"Person_count=",obj_counter[PGIE_CLASS_ID_PERSON])
  1. Where should I be declaring the variable?
  2. Can we track the object age through _NvMOTTrackedObj?
  3. How do we edit the tracking labels on the osdpad? Like instead of only the infered class label, but would be like “Person 7seconds”
4

In the probe function user can start the timer/counter for given tracking object and continue to increment it as long as the same object is seen.
To display - the user needs to iterate over object metadata and update “display_text”. For this user needs to first backup the existing “display_text”, then free it and update the “display_text” with the string that user wants

1 Like