panel_detection.py

import numpy as np
import os
import sys
import tensorflow as tf
import glob
from PIL import Image
from tensorflow_utils import label_map_util, ops as utils_ops
import cv2
#  from object_detection.utils import ops as utils_ops


MODEL_NAME = 'solar_panel_inference_graph'

# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_FROZEN_GRAPH = 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')
PATH_TO_LABELS = os.path.join('solar_panel_training', 'labelmap.pbtxt')

DETECTION_GRAPH = tf.Graph()
with DETECTION_GRAPH.as_default():
  od_graph_def = tf.GraphDef()
  with tf.gfile.GFile(PATH_TO_FROZEN_GRAPH, 'rb') as fid:
    serialized_graph = fid.read()
    od_graph_def.ParseFromString(serialized_graph)
    tf.import_graph_def(od_graph_def, name='')


category_index = label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS, use_display_name=True)

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)

PATH_TO_TEST_IMAGES_DIR = "/home/m/code/banshee/test_images/videos/frames"
TEST_IMAGE_PATHS = [file for file in glob.glob(PATH_TO_TEST_IMAGES_DIR + "/*.jpg")]


def detect(path, score_threshold = 0.5):
    img = cv2.imread(path)
    out = run_inference_for_single_image(path)

    rows, cols, _ = img.shape

    result = { "solar_panel": [], "hotspot": [] }
    labelmap = { 1: "solar_panel", 2: "hotspot" }
    num_detections = int(out["num_detections"])
    for i in range(num_detections):
        classId = int(out["detection_classes"][i])
        label = labelmap[classId]
        score = float(out["detection_scores"][i])
        bbox = [float(v) for v in out["detection_boxes"][i]]
        if score > score_threshold:
            ymin, xmin, ymax, xmax = bbox
            p1 = (int(xmin * cols), int(ymin * rows))
            p2 = (int(xmax * cols), int(ymax * rows))
            result[label].append([p1, p2, score])

    return result


def run_inference_for_single_image(path):
    image = Image.open(path)
    # the array based representation of the image will be used later in order to prepare the
    # result image with boxes and labels on it.
    image_np = load_image_into_numpy_array(image)
    # 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 = image_np_expanded

    with DETECTION_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[1], image.shape[2])
                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: image})

            # 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.int64)
            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

if __name__ == "__main__":
    test_img_dir = "test/img"
    test_imgs = os.listdir(test_img_dir)
    #  for path in TEST_IMAGE_PATHS:
    for fn in test_imgs:
        path = f"{test_img_dir}/{fn}"
        img = cv2.imread(path)
        result = detect(path)
        for panel in result["solar_panel"]:
            p1, p2, score = panel
            cv2.rectangle(img, p1, p2, (0, 255, 0), 2)


        for hotspot in result["hotspot"]:
            p1, p2, score = hotspot
            cv2.rectangle(img, p1, p2, (0, 0, 255), 2)
        cv2.imshow("result", img)
        k = cv2.waitKey(0)
        if k == 13: # enter
            continue
        if k == 27: # esc
            cv2.destroyAllWindows()
            exit()

        cv2.destroyAllWindows()