Object Recognition App with Video as Source

object_detection_app.py

import os
import cv2
import time
import numpy as np
import tensorflow as tf

from utils import FPS
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util

CWD_PATH = os.getcwd()

# Path to frozen detection graph. This is the actual model that is used for the object detection.
MODEL_NAME = 'dat_model'
PATH_TO_CKPT = os.path.join(CWD_PATH, 'object_detection', MODEL_NAME, 'output_inference_graph.pb')

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

NUM_CLASSES = 1

# Loading label map
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)


def detect_objects(image_np, sess, detection_graph):
    # 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})

    #print(boxes, scores, classes, num_detections)

    # 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,
        min_score_thresh=0.5)
    return image_np


if __name__ == '__main__':
    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='')

    sess = tf.Session(graph=detection_graph)

    video_capture = cv2.VideoCapture('video.mp4')
    fps = FPS().start()

    frame_width = int(video_capture.get(3))
    frame_height = int(video_capture.get(4))

    # define video output
    out = cv2.VideoWriter('outpy.avi', cv2.VideoWriter_fourcc('M', 'J', 'P', 'G'), 10, (frame_width, frame_height))

    count = 0
    while video_capture.isOpened():
        ret, frame = video_capture.read()

        t = time.time()
        detected_image = detect_objects(frame, sess, detection_graph)

        fps.update()

        count += 1
        if count % 100 == 0:
            print(count)

        # write to video file
        out.write(detected_image)

        cv2.imshow('Video', detected_image)

        print('[INFO] elapsed time: {:.2f}'.format(time.time() - t))

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

    fps.stop()
    print('[INFO] elapsed time (total): {:.2f}'.format(fps.elapsed()))
    print('[INFO] approx. FPS: {:.2f}'.format(fps.fps()))

    video_capture.release()
    sess.close()
    cv2.destroyAllWindows()