Correct way to remove object_meta from the frame/batch_meta

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson
• DeepStream Version 5.0.1
• JetPack Version (valid for Jetson only) 4.4.1
• TensorRT Version 7.1.3
• Issue Type Question
• Requirement details
Removing Objects from the deepstream pipline using nvdsAnalytics ROI-RF feature.

I have a multistream pipline that has a pgie->tracker(past-frame-enabled)->analytics.

The goal would be to detect when an object enters a ROI and remove the object from the pipeline, ie remove its obj_meta from frame_meta and batch_meta.

at the moment i use a pad probe on the src pad of nvdsanalytics element and remove the relevant objects within the ROI via using “pyds.nvds_remove_obj_meta_from_frame(frame_meta, obj)”
So far it works as expected and the object and bounding box dont appear on the OSD, but the tracker still has information about the removed object.
To access the tracker meta I use the pad on the tiler, I assume it has to do with the past frame meta.

user_meta_list = batch_meta.batch_user_meta_list
while user_meta_list is not None:
    user_meta = pyds.NvDsUserMeta.cast(user_meta_list.data)

    if user_meta.base_meta.meta_type != pyds.NvDsMetaType.NVDS_TRACKER_PAST_FRAME_META:
        continue
    past_frame_object_batch = pyds_tracker_meta.NvDsPastFrameObjBatch_cast(user_meta.user_meta_data)
    for past_frame_object_stream in pyds_tracker_meta.NvDsPastFrameObjBatch_list(past_frame_object_batch):
        streamId = past_frame_object_stream.streamID
        print('    past_frame_object_stream:', past_frame_object_stream)
        print('      streamID:', past_frame_object_stream.streamID)
        print('      surfaceStreamID:', past_frame_object_stream.surfaceStreamID)
        for past_frame_object_list in pyds_tracker_meta.NvDsPastFrameObjStream_list(past_frame_object_stream):
            print('        past_frame_object_list:', past_frame_object_list)
            print('          numObj:', past_frame_object_list.numObj)
            print('          uniqueId:', past_frame_object_list.uniqueId)
            print('          classId:', past_frame_object_list.classId)
            print('          objLabel:', past_frame_object_list.objLabel)
            for past_frame_object in pyds_tracker_meta.NvDsPastFrameObjList_list(past_frame_object_list):
                print('            past_frame_object:', past_frame_object)
                print('              frameNum:', past_frame_object.frameNum)
                print('              tBbox.left:', past_frame_object.tBbox.left)
                print('              tBbox.width:', past_frame_object.tBbox.width)
                print('              tBbox.top:', past_frame_object.tBbox.top)
                print('              tBbox.right:', past_frame_object.tBbox.height)
                print('              confidence:', past_frame_object.confidence)
                print('              age:', past_frame_object.age)
                
    try:
        user_meta_list = user_meta_list.next
    except StopIteration:
        break

How can I remove the tracker meta when I remove the object in my analytics callback

Regards Andrew

Hey, can you try remove the user meta using https://docs.nvidia.com/metropolis/deepstream/python-api/PYTHON_API/Methods/methodsdoc.html#nvds-remove-user-meta-from-batch

I have tried to remove it with " nvds_remove_user_meta_from_batch" and " nvds_remove_user_meta_from_frame".

Does it not have to do with the past_frame objects?

if user_meta.base_meta.meta_type != 
pyds.NvDsMetaType.NVDS_TRACKER_PAST_FRAME_META:
        continue
    past_frame_object_batch = pyds_tracker_meta.NvDsPastFrameObjBatch_cast(user_meta.user_meta_data)

Do we not need to somehow remove the past_frames from the batch_meta?

I didn’t get, is the past frame meta removed successfully using the function?

No it did not remove the past_frame_meta from the batch meta.

Ok, could you share your whole repro with us, so we can debug locally.

I have attatched a demo based on deepstream_imagedata-multistream.py but with a tracker and analytics elements in the pipeline

there is the standard tiler_sink_pad_buffer_probe, aswell as nvdsanalytics_src_pad_buffer_prob,
In the analytics probe two functions are called process_nvdsanalytics_meta_data, we check if an object is in the ROI-RF bbox and remove them from the frame meta.
The second function process_tracker_meta_data reads the tracker_meta in a batch.

The goal is to completely remove an object from the pipline if it is within an ROI, maybe I am removing at the wrong point or am calling the wrong functions

def process_tracker_meta_data(batch_meta):
    user_meta_list = batch_meta.batch_user_meta_list
    # print('======================================================================================')
    batch_tracker_decoded = {}


    while user_meta_list is not None:
        user_meta = pyds.NvDsUserMeta.cast(user_meta_list.data)
        if user_meta.base_meta.meta_type != pyds.NvDsMetaType.NVDS_TRACKER_PAST_FRAME_META:
            continue
        past_frame_object_batch = pyds_tracker_meta.NvDsPastFrameObjBatch_cast(user_meta.user_meta_data)
        for past_frame_object_stream in pyds_tracker_meta.NvDsPastFrameObjBatch_list(past_frame_object_batch):
            streamId = past_frame_object_stream.streamID

            # print('    past_frame_object_stream:', past_frame_object_stream)
            # print('      streamID:', past_frame_object_stream.streamID)
            # print('      surfaceStreamID:', past_frame_object_stream.surfaceStreamID)
            tracked_vehicles = []
            tracked_people = []
            for past_frame_object_list in pyds_tracker_meta.NvDsPastFrameObjStream_list(past_frame_object_stream):
                # print('        past_frame_object_list:', past_frame_object_list)
                # print('          numObj:', past_frame_object_list.numObj)
                # print('          uniqueId:', past_frame_object_list.uniqueId)
                # print('          classId:', past_frame_object_list.classId)
                # print('          objLabel:', past_frame_object_list.objLabel)
                oldest_age = 0
                classId = past_frame_object_list.classId
                uniqueId = past_frame_object_list.uniqueId
                bbox = []
                conf = 0.0
                counter = 0
                for past_frame_object in pyds_tracker_meta.NvDsPastFrameObjList_list(past_frame_object_list):
                    counter += 1
                    # print('            past_frame_object:', past_frame_object)
                    # print('              frameNum:', past_frame_object.frameNum)
                    # print('              tBbox.left:', past_frame_object.tBbox.left)
                    # print('              tBbox.width:', past_frame_object.tBbox.width)
                    # print('              tBbox.top:', past_frame_object.tBbox.top)
                    # print('              tBbox.right:', past_frame_object.tBbox.height)
                    # print('              confidence:', past_frame_object.confidence)
                    # print('              age:', past_frame_object.age)
                print('Unique ID',past_frame_object_list.uniqueId,' past frames: ',counter)




        try:
            user_meta_list = user_meta_list.next
        except StopIteration:
            break
def process_nvdsanalytics_meta_data(batch_meta):
    # Iterate over list of FrameMeta
    l_frame = batch_meta.frame_meta_list
    # print('======================================================')
    while l_frame is not None:
        try:
            # Casting l_frame.data to ipyds.NvDsFrameMeta
            frame_meta = pyds.NvDsFrameMeta.cast(l_frame.data)
            l_user = frame_meta.frame_user_meta_list

            while l_user is not None:
                try:
                    # Cast to NvDsUserMeta and check it either NvDsAnalyticsFrameMeta or not
                    user_meta = pyds.NvDsUserMeta.cast(l_user.data)
                    if user_meta.base_meta.meta_type != pyds.nvds_get_user_meta_type(
                            "NVIDIA.DSANALYTICSFRAME.USER_META"):
                        continue

                    user_meta_analytics = pyds_analytics_meta.NvDsAnalyticsFrameMeta.cast(user_meta.user_meta_data)

                except Exception as ex:
                    print('Exception', ex)
                try:
                    l_user = l_user.next
                except StopIteration:
                    break
        except StopIteration:
            break

        l_obj = frame_meta.obj_meta_list
        while l_obj is not None:
            try:
                frame_meta = pyds.NvDsFrameMeta.cast(l_frame.data)
            except StopIteration:
                break

            frame_number = frame_meta.frame_num
            num_rects = frame_meta.num_obj_meta
            remove_arr = []
            try:
                # Casting l_obj.data to pyds.NvDsObjectMeta
                obj_meta = pyds.NvDsObjectMeta.cast(l_obj.data)
                user_meta_list = obj_meta.obj_user_meta_list
                remove = False

                while user_meta_list is not None:
                    try:
                        user_meta = pyds.NvDsUserMeta.cast(user_meta_list.data)
                        display_meta = pyds.NvDsUserMeta.cast(user_meta_list.data)
                        rect_params = obj_meta.rect_params  # NvOSD_RectParams *
                        text_params = obj_meta.text_params  # NvOSD_TextParams *
                        unique_id = obj_meta.object_id
                        # print('ID: ',unique_id,' text_params', pyds.get_string(text_params.display_text))
                        user_meta_data = user_meta.user_meta_data
                        if user_meta.base_meta.meta_type != pyds.nvds_get_user_meta_type(
                                "NVIDIA.DSANALYTICSOBJ.USER_META"):
                            continue
                        user_meta_analytics = pyds_analytics_meta.NvDsAnalyticsObjInfo.cast(
                            user_meta.user_meta_data)
                        # print('unique_id:', user_meta_analytics.unique_id)
                        # print('lcStatus:', user_meta_analytics.lcStatus)
                        # print('dirStatus:', user_meta_analytics.dirStatus)
                        # print('ocStatus:', user_meta_analytics.ocStatus)
                        # print('roiStatus:', user_meta_analytics.roiStatus)
                        if 'RF' in user_meta_analytics.roiStatus:
                            remove = True
                            remove_arr.append(obj_meta)
                            # print('Remove')
                        # if remove:
                        #     pyds.nvds_remove_obj_meta_from_frame(frame_meta, obj_meta)
                    except StopIteration:
                        break
                    try:
                        user_meta_list = user_meta_list.next

                    except StopIteration:
                        break
            except StopIteration:
                break

            try:
                l_obj = l_obj.next
                for obj in remove_arr:
                    pyds.nvds_remove_obj_meta_from_frame(frame_meta, obj)
                    # print('REMOVE')

            except StopIteration:
                break

        # Get next FrameMeta in list
        try:
            l_frame = l_frame.next
        except StopIteration:
            break

    # if batch_meta_decoded[0]["current"]["people_count"]:
    #     print('batch_meta_decoded', batch_meta_decoded)
def nvdsanalytics_src_pad_buffer_probe(pad, info, u_data):
    gst_buffer = info.get_buffer()
    if not gst_buffer:
        print("Unable to get GstBuffer ")
        return

    batch_meta = pyds.gst_buffer_get_nvds_batch_meta(hash(gst_buffer))
    process_nvdsanalytics_meta_data(batch_meta)
    process_tracker_meta_data(batch_meta)
    # self.parse_nvdsanalytics_meta_data3(batch_meta)
    return Gst.PadProbeReturn.OK
# tiler_sink_pad_buffer_probe  will extract metadata received on tiler src pad
# and update params for drawing rectangle, object information etc.
def tiler_sink_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.NvDsFrameMeta.cast()
            # 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.NvDsFrameMeta.cast(l_frame.data)
        except StopIteration:
            break

        frame_number=frame_meta.frame_num
        l_obj=frame_meta.obj_meta_list
        num_rects = frame_meta.num_obj_meta
        is_first_obj = True
        save_image = False
        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.NvDsObjectMeta.cast(l_obj.data)
            except StopIteration:
                break
            obj_counter[obj_meta.class_id] += 1
            # Periodically check for objects with borderline confidence value that may be false positive detections.
            # If such detections are found, annoate the frame with bboxes and confidence value.
            # Save the annotated frame to file.
            if((saved_count["stream_"+str(frame_meta.pad_index)]%30==0) and (obj_meta.confidence>0.3 and obj_meta.confidence<0.31)):
                if is_first_obj:
                    is_first_obj = False
                    # Getting Image data using nvbufsurface
                    # the input should be address of buffer and batch_id
                    n_frame=pyds.get_nvds_buf_surface(hash(gst_buffer),frame_meta.batch_id)
                    #convert python array into numy array format.
                    frame_image=np.array(n_frame,copy=True,order='C')
                    #covert the array into cv2 default color format
                    frame_image=cv2.cvtColor(frame_image,cv2.COLOR_RGBA2BGRA)

                save_image = True
                frame_image=draw_bounding_boxes(frame_image,obj_meta,obj_meta.confidence)
            try: 
                l_obj=l_obj.next
            except StopIteration:
                break

        # 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()
        if save_image:
            cv2.imwrite(folder_name+"/stream_"+str(frame_meta.pad_index)+"/frame_"+str(frame_number)+".jpg",frame_image)
        saved_count["stream_"+str(frame_meta.pad_index)]+=1        
        try:
            l_frame=l_frame.next
        except StopIteration:
            break

    return Gst.PadProbeReturn.OK

def draw_bounding_boxes(image,obj_meta,confidence):
    confidence='{0:.2f}'.format(confidence)
    rect_params=obj_meta.rect_params
    top=int(rect_params.top)
    left=int(rect_params.left)
    width=int(rect_params.width)
    height=int(rect_params.height)
    obj_name=pgie_classes_str[obj_meta.class_id]
    image=cv2.rectangle(image,(left,top),(left+width,top+height),(0,0,255,0),2)
    # Note that on some systems cv2.putText erroneously draws horizontal lines across the image
    image=cv2.putText(image,obj_name+',C='+str(confidence),(left-10,top-10),cv2.FONT_HERSHEY_SIMPLEX,0.5,(0,0,255,0),2)
    return image

def cb_newpad(decodebin, decoder_src_pad,data):
    print("In cb_newpad\n")
    caps=decoder_src_pad.get_current_caps()
    gststruct=caps.get_structure(0)
    gstname=gststruct.get_name()
    source_bin=data
    features=caps.get_features(0)

    # Need to check if the pad created by the decodebin is for video and not
    # audio.
    if(gstname.find("video")!=-1):
        # Link the decodebin pad only if decodebin has picked nvidia
        # decoder plugin nvdec_*. We do this by checking if the pad caps contain
        # NVMM memory features.
        if features.contains("memory:NVMM"):
            # Get the source bin ghost pad
            bin_ghost_pad=source_bin.get_static_pad("src")
            if not bin_ghost_pad.set_target(decoder_src_pad):
                sys.stderr.write("Failed to link decoder src pad to source bin ghost pad\n")
        else:
            sys.stderr.write(" Error: Decodebin did not pick nvidia decoder plugin.\n")

def decodebin_child_added(child_proxy,Object,name,user_data):
    print("Decodebin child added:", name, "\n")
    if(name.find("decodebin") != -1):
        Object.connect("child-added",decodebin_child_added,user_data)   
    if(is_aarch64() and name.find("nvv4l2decoder") != -1):
        print("Seting bufapi_version\n")
        Object.set_property("bufapi-version",True)

def create_source_bin(index,uri):
    print("Creating source bin")

    # Create a source GstBin to abstract this bin's content from the rest of the
    # pipeline
    bin_name="source-bin-%02d" %index
    print(bin_name)
    nbin=Gst.Bin.new(bin_name)
    if not nbin:
        sys.stderr.write(" Unable to create source bin \n")

    # Source element for reading from the uri.
    # We will use decodebin and let it figure out the container format of the
    # stream and the codec and plug the appropriate demux and decode plugins.
    uri_decode_bin=Gst.ElementFactory.make("uridecodebin", "uri-decode-bin")
    if not uri_decode_bin:
        sys.stderr.write(" Unable to create uri decode bin \n")
    # We set the input uri to the source element
    uri_decode_bin.set_property("uri",uri)
    # Connect to the "pad-added" signal of the decodebin which generates a
    # callback once a new pad for raw data has beed created by the decodebin
    uri_decode_bin.connect("pad-added",cb_newpad,nbin)
    uri_decode_bin.connect("child-added",decodebin_child_added,nbin)

    # We need to create a ghost pad for the source bin which will act as a proxy
    # for the video decoder src pad. The ghost pad will not have a target right
    # now. Once the decode bin creates the video decoder and generates the
    # cb_newpad callback, we will set the ghost pad target to the video decoder
    # src pad.
    Gst.Bin.add(nbin,uri_decode_bin)
    bin_pad=nbin.add_pad(Gst.GhostPad.new_no_target("src",Gst.PadDirection.SRC))
    if not bin_pad:
        sys.stderr.write(" Failed to add ghost pad in source bin \n")
        return None
    return nbin

def main(args):
    # Check input arguments
    if len(args) < 2:
        sys.stderr.write("usage: %s <uri1> [uri2] ... [uriN] <folder to save frames>\n" % args[0])
        sys.exit(1)

    for i in range(0,len(args)-2):
        fps_streams["stream{0}".format(i)]=GETFPS(i)
    number_sources=len(args)-2

    global folder_name
    folder_name=args[-1]
    if path.exists(folder_name):
        sys.stderr.write("The output folder %s already exists. Please remove it first.\n" % folder_name)
        sys.exit(1)

    os.mkdir(folder_name)
    print("Frames will be saved in ",folder_name)
    # Standard GStreamer initialization
    GObject.threads_init()
    Gst.init(None)

    # Create gstreamer elements */
    # Create Pipeline element that will form a connection of other elements
    print("Creating Pipeline \n ")
    pipeline = Gst.Pipeline()
    is_live = False

    if not pipeline:
        sys.stderr.write(" Unable to create Pipeline \n")
    print("Creating streamux \n ")

    # Create nvstreammux instance to form batches from one or more sources.
    streammux = Gst.ElementFactory.make("nvstreammux", "Stream-muxer")
    if not streammux:
        sys.stderr.write(" Unable to create NvStreamMux \n")

    # Set properties of tracker
    config = configparser.ConfigParser()
    config.read('dstest2_tracker_config.txt')
    config.sections()
    #  Tracker
    tracker = Gst.ElementFactory.make("nvtracker", "tracker")
    if not tracker:
        sys.stderr.write(" Unable to create tracker \n")

    for key in config['tracker']:
        if key == 'tracker-width':
            tracker_width = config.getint('tracker', key)
            tracker.set_property('tracker-width', tracker_width)
        if key == 'tracker-height':
            tracker_height = config.getint('tracker', key)
            tracker.set_property('tracker-height', tracker_height)
        if key == 'gpu-id':
            tracker_gpu_id = config.getint('tracker', key)
            tracker.set_property('gpu_id', tracker_gpu_id)
        if key == 'll-lib-file':
            tracker_ll_lib_file = config.get('tracker', key)
            tracker.set_property('ll-lib-file', tracker_ll_lib_file)
        if key == 'll-config-file':
            tracker_ll_config_file = config.get('tracker', key)
            tracker.set_property('ll-config-file', tracker_ll_config_file)
        if key == 'enable-batch-process':
            tracker_enable_batch_process = config.getint('tracker', key)
            tracker.set_property('enable_batch_process', tracker_enable_batch_process)
    tracker.set_property('enable-past-frame', 1)

    #  nvdsAnalytics
    analytics = Gst.ElementFactory.make("nvdsanalytics", "analytics")
    if not analytics:
        sys.stderr.write(" Unable to create analytics \n")

    # Set properties of tracker
    config = configparser.ConfigParser()
    config.read("config_nvdsanalytics.txt")
    config.sections()
    print('config', config)
    # "config-file", "config_nvdsanalytics.txt",
    analytics.set_property("config-file", "config_nvdsanalytics.txt")

    if not tracker:
        sys.stderr.write(" Unable to create tracker \n")



    pipeline.add(streammux)
    for i in range(number_sources):
        os.mkdir(folder_name+"/stream_"+str(i))
        frame_count["stream_"+str(i)]=0
        saved_count["stream_"+str(i)]=0
        print("Creating source_bin ",i," \n ")
        uri_name=args[i+1]
        if uri_name.find("rtsp://") == 0 :
            is_live = True
        source_bin=create_source_bin(i, uri_name)
        if not source_bin:
            sys.stderr.write("Unable to create source bin \n")
        pipeline.add(source_bin)
        padname="sink_%u" %i
        sinkpad= streammux.get_request_pad(padname) 
        if not sinkpad:
            sys.stderr.write("Unable to create sink pad bin \n")
        srcpad=source_bin.get_static_pad("src")
        if not srcpad:
            sys.stderr.write("Unable to create src pad bin \n")
        srcpad.link(sinkpad)
    print("Creating Pgie \n ")
    pgie = Gst.ElementFactory.make("nvinfer", "primary-inference")
    if not pgie:
        sys.stderr.write(" Unable to create pgie \n")
    # Add nvvidconv1 and filter1 to convert the frames to RGBA
    # which is easier to work with in Python.
    print("Creating nvvidconv1 \n ")
    nvvidconv1 = Gst.ElementFactory.make("nvvideoconvert", "convertor1")
    if not nvvidconv1:
        sys.stderr.write(" Unable to create nvvidconv1 \n")
    print("Creating filter1 \n ")
    caps1 = Gst.Caps.from_string("video/x-raw(memory:NVMM), format=RGBA")
    filter1 = Gst.ElementFactory.make("capsfilter", "filter1")
    if not filter1:
        sys.stderr.write(" Unable to get the caps filter1 \n")
    filter1.set_property("caps", caps1)
    print("Creating tiler \n ")
    tiler=Gst.ElementFactory.make("nvmultistreamtiler", "nvtiler")
    if not tiler:
        sys.stderr.write(" Unable to create tiler \n")
    print("Creating nvvidconv \n ")
    nvvidconv = Gst.ElementFactory.make("nvvideoconvert", "convertor")
    if not nvvidconv:
        sys.stderr.write(" Unable to create nvvidconv \n")
    print("Creating nvosd \n ")
    nvosd = Gst.ElementFactory.make("nvdsosd", "onscreendisplay")
    if not nvosd:
        sys.stderr.write(" Unable to create nvosd \n")
    if(is_aarch64()):
        print("Creating transform \n ")
        transform=Gst.ElementFactory.make("nvegltransform", "nvegl-transform")
        if not transform:
            sys.stderr.write(" Unable to create transform \n")


    print("Creating EGLSink \n")
    sink = Gst.ElementFactory.make("nveglglessink", "nvvideo-renderer")
    if not sink:
        sys.stderr.write(" Unable to create egl sink \n")

    if is_live:
        print("Atleast one of the sources is live")
        streammux.set_property('live-source', 1)

    streammux.set_property('width', 1920)
    streammux.set_property('height', 1080)
    streammux.set_property('batch-size', number_sources)
    streammux.set_property('batched-push-timeout', 4000000)
    pgie.set_property('config-file-path', "dstest_imagedata_config.txt")
    pgie_batch_size=pgie.get_property("batch-size")
    if(pgie_batch_size != number_sources):
        print("WARNING: Overriding infer-config batch-size",pgie_batch_size," with number of sources ", number_sources," \n")
        pgie.set_property("batch-size",number_sources)
    tiler_rows=int(math.sqrt(number_sources))
    tiler_columns=int(math.ceil((1.0*number_sources)/tiler_rows))
    tiler.set_property("rows",tiler_rows)
    tiler.set_property("columns",tiler_columns)
    tiler.set_property("width", TILED_OUTPUT_WIDTH)
    tiler.set_property("height", TILED_OUTPUT_HEIGHT)

    sink.set_property("sync", 0)

    if not is_aarch64():
        # Use CUDA unified memory in the pipeline so frames
        # can be easily accessed on CPU in Python.
        mem_type = int(pyds.NVBUF_MEM_CUDA_UNIFIED)
        streammux.set_property("nvbuf-memory-type", mem_type)
        nvvidconv.set_property("nvbuf-memory-type", mem_type)
        nvvidconv1.set_property("nvbuf-memory-type", mem_type)
        tiler.set_property("nvbuf-memory-type", mem_type)

    print("Adding elements to Pipeline \n")
    pipeline.add(pgie)
    pipeline.add(tracker)
    pipeline.add(analytics)
    pipeline.add(tiler)
    pipeline.add(nvvidconv)
    pipeline.add(filter1)
    pipeline.add(nvvidconv1)
    pipeline.add(nvosd)

    if is_aarch64():
        pipeline.add(transform)

    if is_aarch64():
        pipeline.add(transform)
    pipeline.add(sink)

    print("Linking elements in the Pipeline \n")
    streammux.link(pgie)

    pgie.link(tracker)
    tracker.link(analytics)
    analytics.link(nvvidconv1)

    nvvidconv1.link(filter1)
    filter1.link(tiler)
    tiler.link(nvvidconv)
    nvvidconv.link(nvosd)

    if is_aarch64():
        nvosd.link(transform)
        transform.link(sink)
    else:
        nvosd.link(sink)


    # create an event loop and feed gstreamer bus mesages to it
    loop = GObject.MainLoop()
    bus = pipeline.get_bus()
    bus.add_signal_watch()
    bus.connect ("message", bus_call, loop)

    tiler_sink_pad=tiler.get_static_pad("sink")
    if not tiler_sink_pad:
        sys.stderr.write(" Unable to get src pad \n")
    else:
        tiler_sink_pad.add_probe(Gst.PadProbeType.BUFFER, tiler_sink_pad_buffer_probe, 0)

    nvdsanalytics_src_pad = analytics.get_static_pad("src")
    # nvdsanalytics_src_pad = gst_element_get_static_pad(nvdsanalytics, "src");
    if not nvdsanalytics_src_pad:
        sys.stderr.write(" Unable to get src pad \n")
    else:
        nvdsanalytics_src_pad.add_probe(Gst.PadProbeType.BUFFER, nvdsanalytics_src_pad_buffer_probe, 0)

    # List the sources
    print("Now playing...")
    for i, source in enumerate(args[:-1]):
        if (i != 0):
            print(i, ": ", source)

    print("Starting pipeline \n")
    # start play back and listed to events		
    pipeline.set_state(Gst.State.PLAYING)
    try:
        loop.run()
    except:
        pass
    # cleanup
    print("Exiting app\n")
    pipeline.set_state(Gst.State.NULL)

if __name__ == '__main__':
    sys.exit(main(sys.argv))

Console printout : (Expected to see no Unique ID and past frame as ROI covers whole screen)

Decodebin child added: decodebin0 

test-app.zip (61.9 KB)
Decodebin child added: rtph264depay0

Decodebin child added: h264parse0 

Decodebin child added: capsfilter0 

Decodebin child added: nvv4l2decoder0 

Seting bufapi_version

Opening in BLOCKING MODE 
NvMMLiteOpen : Block : BlockType = 261 
NVMEDIA: Reading vendor.tegra.display-size : status: 6 
NvMMLiteBlockCreate : Block : BlockType = 261 
In cb_newpad

Unique ID 0  past frames:  3
**********************FPS*****************************************
Fps of stream 0 is  16.8
Unique ID 1  past frames:  3
**********************FPS*****************************************
Fps of stream 0 is  23.2
**********************FPS*****************************************
Fps of stream 0 is  24.8
**********************FPS*****************************************
Fps of stream 0 is  25.8
**********************FPS*****************************************
Fps of stream 0 is  24.4
**********************FPS*****************************************
Fps of stream 0 is  24.4
Unique ID 2  past frames:  3
**********************FPS*****************************************
Fps of stream 0 is  25.4
**********************FPS*****************************************
Fps of stream 0 is  25.2
**********************FPS*****************************************
Fps of stream 0 is  26.0
^CExiting app

Regards Andrew

Hey can you also share the 2 bindings with us

import pyds_tracker_meta
# import pyds_analytics
import pyds_analytics_meta

Thanks, will check it and update you.

I tried to add pyds.nvds_remove_user_meta_from_batch(batch_meta, user_meta) under your process_tracker_meta_data function and the user meta removed successfully.

        if user_meta.base_meta.meta_type != pyds.NvDsMetaType.NVDS_TRACKER_PAST_FRAME_META:
            continue
        pyds.nvds_remove_user_meta_from_batch(batch_meta, user_meta)
        past_frame_object_batch = pyds_tracker_meta.NvDsPastFrameObjBatch_cast(user_meta.user_meta_data)

so we cant remove it in the function “process_nvdsanalytics_meta_data” ?, because this is where we detect that the object is within the ROI and thus where we would want to remove all meta_data of this object from the pipeline.

Yes, we can add it under process_nvdsanalytics_meta_data, have you tried it under process_nvdsanalytics_meta_data? I think it should be same as under process_tracker_meta_data.