Check for bounding box availability in only certain areas of the image/video frame

Question

I am trying to detect cars in a certain area of live video stream. For that I used Tensorflow's object detection API. Now, the detection is fair enough and almost all the cars in the live video stream are detected as "car" with bounding boxes around them and with some amount of detection confidence score in percentage.

My question is how do I check for availability of only the desired on required bounding boxes?

For example, since the desired area and the camera used for detection are both fixed in position, I used OpenCV's cv2.rectangle() function and passed the (x1,y1) and (x2,y2) co-ordinates of the desired area. So now, I have constant rectangular box around that area. My task is to somehow know that the car has arrived in this marked rectangle area by printing a logging message "detected" to the Ubuntu terminal.

I am having difficulties comparing bounding box co-ordinates with the rectangle co-ordinates. So the question arises how to

1. Grab only required bounding boxes(thereby required detected cars)?
2. detect whenever these bounding boxes are inside the rectangle/marked area?

Here is the code I 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 PIL import Image

import cv2
cap = cv2.VideoCapture(0)
# This is needed since the notebook is stored in the object_detection 
folder.
sys.path.append("..")
from object_detection.utils import ops as utils_ops

if tf.__version__ != '1.10.1':
  raise ImportError('Please upgrade your tensorflow installation to 
v1.10.1* or later!')


# ## Env setup

# In[3]:

# ## Object detection imports
# Here are the imports from the object detection module.

# In[5]:

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_FROZEN_GRAPH` to point to a 
new .pb file.  
# 
# By default we use an "SSD with Mobilenet" model here. See the 
[detection model zoo] 

# In[6]:
# What model to download.
MODEL_NAME = 'car_inference_graph'

# 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('training', 'object-detection.pbtxt')

NUM_CLASSES = 1

# ## Load a (frozen) Tensorflow model into memory.

# In[7]:
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

# In[8]:

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)

# ## Helper code

# In[9]:

def load_image_into_numpy_array(image):
  (im_width, im_height) = image.size
  return np.array(image.getdata()).reshape(
      (im_height, im_width, 3)).astype(np.uint8)

# # Detection

def run_inference_for_single_image(image, graph):
  with graph.as_default():
    with tf.Session() as sess:
      # Get handles to input and output tensors
      ops = tf.get_default_graph().get_operations()
      all_tensor_names = {output.name for op in ops for output in 
 op.outputs}
      tensor_dict = {}
      for key in [
          'num_detections', 'detection_boxes', 'detection_scores',
          'detection_classes', 'detection_masks'
      ]:
        tensor_name = key + ':0'
        if tensor_name in all_tensor_names:
          tensor_dict[key] = 
tf.get_default_graph().get_tensor_by_name(
              tensor_name)
      if 'detection_masks' in tensor_dict:
        # The following processing is only for single image
        detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], 
[0])
        detection_masks = tf.squeeze(tensor_dict['detection_masks'], 
[0])
        # Reframe is required to translate mask from box coordinates 
to image coordinates and fit the image size.
        real_num_detection = tf.cast(tensor_dict['num_detections'][0], 
tf.int32)
        detection_boxes = tf.slice(detection_boxes, [0, 0], 
[real_num_detection, -1])
        detection_masks = tf.slice(detection_masks, [0, 0, 0], 
[real_num_detection, -1, -1])
        detection_masks_reframed = 
utils_ops.reframe_box_masks_to_image_masks(
            detection_masks, detection_boxes, image.shape[0], 
image.shape[1])
        detection_masks_reframed = tf.cast(
            tf.greater(detection_masks_reframed, 0.5), tf.uint8)
        # Follow the convention by adding back the batch dimension
        tensor_dict['detection_masks'] = tf.expand_dims(
            detection_masks_reframed, 0)
      image_tensor = 
tf.get_default_graph().get_tensor_by_name('image_tensor:0')

      # Run inference
      output_dict = sess.run(tensor_dict,
                             feed_dict={image_tensor: 
np.expand_dims(image, 0)})

      # all outputs are float32 numpy arrays, so convert types as 
appropriate
      output_dict['num_detections'] = 
int(output_dict['num_detections'][0])
      output_dict['detection_classes'] = output_dict[
          'detection_classes'][0].astype(np.uint8)
      output_dict['detection_boxes'] = output_dict['detection_boxes'] 
[0]
      output_dict['detection_scores'] = 
output_dict['detection_scores'][0]
      if 'detection_masks' in output_dict:
        output_dict['detection_masks'] = 
output_dict['detection_masks'][0]
  return output_dict

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.
      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)

      area1 = cv2.rectangle(image_np,(201,267),(355,476), 
   (0,255,0),2)
      area2 = cv2.rectangle(image_np,(354,271),(562,454), 
   (255,0,0),2)
      cv2.imshow("object detection", image_np)

      if 'detection_boxes:0' == 1 in area1[(201,267),(353,468)]:
        print("area1 occupied!")
      else:
        print("area1 free!")

      if 'detection_boxes:1' == 1 in area2[(354,271),(562,454)]:
        print("area2 occupied!")
      else:
        print("area2 free!")

      if cv2.waitKey(1) & 0xFF == ord('q'):
        cv2.destroyAllWindows()
        cap.release()
        break

I find it difficult to find a solution. Please help.

Technical information:

Tensorflow 1.10

OS - Ubuntu 18.04

Python 3.6

OpenCV 3.4.2

Thanks :)

Answer 1

You can use Intersection over Union for this. If the car is in your desired marked rectangle. IOU will have some value otherwise it will be zero.

When car rectangle is exactly in your marked rectangle, it will be close to 1 and that will be your solution