Cropping A Detected Object On A Video With Tensorflow Api And Opencv

Question

-Python 3.6 -Tensorflow 1.11 with GPU support. -Opencv 3.4.2

I am working on Tensorflow Api, and I have already trained my dataset. It works fine. But I have to crop the detected object and make some preprocess on it. It seems easy, because Tensroflow draws the detected object with green box as well. When I try to find the coordinates of the object it gives me numbers of range 0 to 1. When I put the coordinates on Opencv Crop Image I have to multply the image with pictures height and width, but it works wrong.

Tensorflow.org says that I can use "tf.image.crop_and_resize" function. But I can't run it on my own code.

This is my run_inference_for_single_image function and returns output_dict:

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

This is my video capture funtion. It Crops the wrong coordinates.

video = cv2.VideoCapture(0)
ret = video.set(3,1080)
ret = video.set(4,720)

while(True):

    # Acquire frame and expand frame dimensions to have shape: [1, None, None, 3]
    # i.e. a single-column array, where each item in the column has the pixel RGB value
    ret,frame = video.read()
    frame = cv2.flip(frame, 1)

    frame_expanded = np.expand_dims(frame, axis=0)

    # Perform the actual detection by running the model with the image as input
    (boxes, scores, classes, num) = sess.run(
        [detection_boxes, detection_scores, detection_classes, num_detections],
        feed_dict={image_tensor: frame_expanded})


    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,
        min_score_thresh=0.50)
    # Draw the results of the detection (aka 'visulaize the results')
    output_dict = run_inference_for_single_image(frame, detection_graph)
    max_boxes_to_draw = output_dict['detection_boxes'].shape[0]
    for i in range(min(max_boxes_to_draw, output_dict['detection_boxes'].shape[0])):
        if output_dict['detection_scores'][i] > 0.95:
            if output_dict['detection_classes'][i] in category_index.keys():
                class_name = category_index[output_dict['detection_classes'][i]]['name']
                print(output_dict['detection_boxes'][i])



                crop_img = frame[int((output_dict['detection_boxes'][i][0]) * 720): int(
                    (output_dict['detection_boxes'][i][2]) * 720),
                           int((output_dict['detection_boxes'][i][1]) * 1080):int(
                               (output_dict['detection_boxes'][i][3]) * 1080)]

                cv2.imshow("asdasd", crop_img)
                print(class_name)

    cv2.imshow('Object detector', frame)
    # Press 'q' to quit
    if cv2.waitKey(1) == ord('q'):
        break

It might be about output_dict.

class_name = category_index[output_dict['detection_classes'][i]]['name'] => This codes give me the name of the class. It works well.

Cropping A Detected Object On A Video With Tensorflow Api And Opencv

Answers (1)

Related Questions