opencv_inference.py

# Playing video from file
cap = cv2.VideoCapture('rackoon.mp4')

# Default resolutions of the frame are obtained.The default resolutions are system dependent.
# We convert the resolutions from float to integer.
frame_width = int(cap.get(3))
frame_height = int(cap.get(4))

# Define the codec and create VideoWriter object.The output is stored in 'output.avi' file.
out = cv2.VideoWriter(FILE_OUTPUT, cv2.VideoWriter_fourcc('M', 'J', 'P', 'G'),
                      10, (frame_width, frame_height))

with detection_graph.as_default():
    with tf.Session(graph=detection_graph) as sess:
        # Definite input and output Tensors for detection_graph
        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.
        detection_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.
        detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
        detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
        num_detections = detection_graph.get_tensor_by_name('num_detections:0')

        while(cap.isOpened()):
            # Capture frame-by-frame
            ret, frame = cap.read()

            # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
            image_np_expanded = np.expand_dims(frame, axis=0)

            # Actual detection.
            (boxes, scores, classes, num) = sess.run(
                [detection_boxes, detection_scores, detection_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(
                frame,
                np.squeeze(boxes),
                np.squeeze(classes).astype(np.int32),
                np.squeeze(scores),
                category_index,
                use_normalized_coordinates=True,
                line_thickness=8)

            if ret == True:
                # Saves for video
                out.write(frame)

                # Display the resulting frame
                cv2.imshow('Charving Detection', frame)

                # Close window when "Q" button pressed
                if cv2.waitKey(1) & 0xFF == ord('q'):
                    break
            else:
                break

    # When everything done, release the video capture and video write objects
    cap.release()
    out.release()

    # Closes all the frames
    cv2.destroyAllWindows()