How to use metadata from the secondary classifier in Python

Accelerated Computing Intelligent Video Analytics DeepStream SDK
6

It is difficult to work with NVIDIA due to its vague information. I figured out the solution reading the bindings. I share the source code (based on Deepstream_test2.py) to someone else that have the same issue in the future:

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:
        frame_meta = pyds.NvDsFrameMeta.cast(l_frame.data)
    except StopIteration:
        break

    frame_number=frame_meta.frame_num
    num_rects = frame_meta.num_obj_meta
    l_obj=frame_meta.obj_meta_list
    while l_obj is not None:
        try:
            obj_meta=pyds.NvDsObjectMeta.cast(l_obj.data)
        except StopIteration:
            break
        class_obj=obj_meta.classifier_meta_list
        while class_obj is not None:
            try:
                class_meta=pyds.NvDsClassifierMeta.cast(class_obj.data)
            except StopIteration:
                break
            c_obj=class_meta.label_info_list
            while c_obj is not None:
                try:
                    c_meta=pyds.NvDsLabelInfo.cast(c_obj.data)
                except StopIteration:
                    break
                print(c_meta.result_label)
                try: 
                    c_obj=c_obj.next
                except StopIteration:
                    break
            try: 
                class_obj=class_obj.next
            except StopIteration:
                break
        obj_counter[obj_meta.class_id] += 1
        try: 
            l_obj=l_obj.next
        except StopIteration:
            break
7 Likes