What gstreamer pipeline should I use?

Question

I am trying to stream video from raspberry pi to my pc that is running opencv.

The code that I used on the pi is:

raspivid -t 999999 -h 720 -w 1080 -fps 30 -hf -vf -b 2000000 -o - | gst-launch-1.0 -v fdsrc ! h264parse ! queue ! rtph264pay config-interval=1 pt=96 ! gdppay ! tcpserversink host=192.168.0.103 port=5000

I am using gstreamer to stream the video.

I can use the following command on my pc to get it working...

gst-launch-1.0 -v tcpclientsrc host=192.168.0.103 port=5000  ! gdpdepay !  rtph264depay ! avdec_h264 ! videoconvert ! autovideosink sync=false

What should be the parameter for my opencv VideoCapture function?

Thanks for the help...

PS: I am using python and the opencv is compiled with gstreamer support.

My complete code (Tensorflow is also being used):

import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
import time
import cv2

# Capture Video using webcam
stream_addr = "tcpclientsrc host=192.168.0.103 port=5000 ! gdpdepay ! rtph264depay ! video/x-h264, width=1280, height=720, format=YUY2, framerate=49/1 ! ffdec_h264 ! autoconvert ! appsink sync=false"
# Net cat pipe
pipe = "/dev/stdin"
cap = cv2.VideoCapture("tcpclientsrc host=192.168.0.103 port=5000  ! gdpdepay !  rtph264depay ! ffdec_h264 ! videoconvert ! video/x-raw, format=BGR ! appsink", cv2.CAP_GSTREAMER)
# cap = cv2.VideoCapture()

# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")

# ## Object detection imports
# Here are the imports from the object detection module.
from utils import label_map_util

from utils import visualization_utils as vis_util


# # Model preparation

# ## Variables
#
# Any model exported using the `export_inference_graph.py` tool can be loaded here simply by changing `PATH_TO_CKPT` to point to a new .pb file.
#
# By default we use an "SSD with Mobilenet" model here. See the [detection model zoo](https://github.com/tensorflow/models/blob/master/object_detection/g3doc/detection_model_zoo.md) for a list of other models that can be run out-of-the-box with varying speeds and accuracies.
# What model to download.
MODEL_NAME = 'ssd_mobilenet_v1_coco_11_06_2017'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'

# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'

# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')

NUM_CLASSES = 90

# ## Download Model
if not os.path.isfile(MODEL_FILE) and not os.path.isdir(MODEL_NAME):
    opener = urllib.request.URLopener()
    opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
    tar_file = tarfile.open(MODEL_FILE)
    for file in tar_file.getmembers():
        file_name = os.path.basename(file.name)
        if 'frozen_inference_graph.pb' in file_name:
            tar_file.extract(file, os.getcwd())


# ## Load a (frozen) Tensorflow model into memory.
detection_graph = tf.Graph()
with detection_graph.as_default():
  od_graph_def = tf.GraphDef()
  with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
    serialized_graph = fid.read()
    od_graph_def.ParseFromString(serialized_graph)
    tf.import_graph_def(od_graph_def, name='')


# ## Loading label map
# Label maps map indices to category names, so that when our convolution network predicts `5`, we know that this corresponds to `airplane`.  Here we use internal utility functions, but anything that returns a dictionary mapping integers to appropriate string labels would be fine
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)
list_classname = {}

def printClass(s):
    leng = len(list_classname)
    if s is not None:
        i = s.index(':')
        label = s[:i]
        score = s[i + 2:len(s) - 1]
        if label in list_classname:
            if int(list_classname[label]) < int(score):
                list_classname[label] = score
        else:
            list_classname[label] = score
        if len(list_classname) > leng:
            leng = len(list_classname)
            print(s)

with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
    while True:
      ret, image_np = cap.read()
      # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
      image_np_expanded = np.expand_dims(image_np, axis=0)
      image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
      # Each box represents a part of the image where a particular object was detected.
      boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
      # Each score represent how level of confidence for each of the objects.
      # Score is shown on the result image, together with the class label.
      scores = detection_graph.get_tensor_by_name('detection_scores:0')
      classes = detection_graph.get_tensor_by_name('detection_classes:0')
      num_detections = detection_graph.get_tensor_by_name('num_detections:0')
      # Actual detection.
      (boxes, scores, classes, num_detections) = sess.run(
          [boxes, scores, classes, num_detections],
          feed_dict={image_tensor: image_np_expanded})
      # Visualization of the results of a detection.
      printClass(vis_util.visualize_boxes_and_labels_on_image_array(
          image_np,
          np.squeeze(boxes),
          np.squeeze(classes).astype(np.int32),
          np.squeeze(scores),
          category_index,
          use_normalized_coordinates=True,
          line_thickness=8))

      cv2.imshow('object detection', cv2.resize(image_np, (800,600)))
      if cv2.waitKey(25) & 0xFF == ord('q'):
        cv2.destroyAllWindows()
        break

speak_string = ""
for k in list_classname:
    speak_string = ("Detected, " + k + " probability is " + list_classname[k])
    os.system("say " + speak_string)
    time.sleep(1)

This is the error I receive:

Traceback (most recent call last):
  File "oculus.py", line 112, in <module>
    feed_dict={image_tensor: image_np_expanded})
  File "/Users/SMBP/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 895, in run
    run_metadata_ptr)
  File "/Users/SMBP/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1093, in _run
    np_val = np.asarray(subfeed_val, dtype=subfeed_dtype)
  File "/Users/SMBP/anaconda3/envs/tensorflow/lib/python3.6/site-packages/numpy/core/numeric.py", line 531, in asarray
    return array(a, dtype, copy=False, order=order)
TypeError: int() argument must be a string, a bytes-like object or a number, not 'NoneType

'

Answer 1

Try the following:

VideoCapture cap("tcpclientsrc host=192.168.0.103 port=5000  ! gdpdepay !  rtph264depay ! avdec_h264 ! videoconvert ! video/x-raw, format=BGR ! appsink", CAP_GSTREAMER);

Edit:

cap = cv2.VideoCapture('tcpclientsrc host=192.168.0.103 port=5000  ! gdpdepay !  rtph264depay ! avdec_h264 ! videoconvert ! video/x-raw, format=BGR ! appsink', cv2.CAP_GSTREAMER)