Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- ######## Object Detection for Image #########
- #
- # Author: Khai Do
- # Date: 9/3/2019
- ## Some parts of the code is copied from Tensorflow object detection
- ## https://github.com/tensorflow/models/blob/master/research/object_detection/object_detection_tutorial.ipynb
- # Import libraries
- from pandas._libs import json
- import numpy as np
- import os
- import six.moves.urllib as urllib
- import sys
- import tarfile
- import tensorflow as tf
- import zipfile
- import cv2
- from collections import defaultdict
- from io import StringIO
- from matplotlib import pyplot as plt
- from PIL import Image
- from models.research.object_detection.utils import label_map_util
- from models.research.object_detection.utils import visualization_utils as vis_util
- # Define the video stream
- cap = cv2.VideoCapture(0) # Change only if you have more than one webcams
- # What model
- directPath = os.getcwd()
- print(directPath)
- MODEL_NAME = os.path.join(directPath, 'trained-inference-graphs/output_inference_graph_v1.pb')
- # 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(directPath, 'training/label_map.pbtxt')
- # Number of classes to detect
- NUM_CLASSES = 3
- # Load a (frozen) Tensorflow model into memory.
- 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_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
- 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
- with detection_graph.as_default():
- with tf.Session(graph=detection_graph) as sess:
- while True:
- # Read frame from camera
- 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)
- # Extract image tensor
- image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
- # Extract detection boxes
- boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
- # Extract detection scores
- scores = detection_graph.get_tensor_by_name('detection_scores:0')
- # Extract detection classes
- classes = detection_graph.get_tensor_by_name('detection_classes:0')
- # Extract number of detectionsd
- 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)
- # writing coordinates
- coordinates = vis_util.return_coordinates(
- 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=0.80)
- for coordinate in coordinates:
- if not coordinate:
- print("Looking for guesture")
- else:
- print(coordinate)
- (y1, y2, x1, x2, scores, classes) = coordinate
- #textfile = open('filename_string' + ".json", "a")
- #textfile.write(json.dumps(coordinate))
- #textfile.write("\n")
- #print(coordinates)
- # Display output
- cv2.imshow('object detection', cv2.resize(image_np, (1200,900)))
- if cv2.waitKey(25) & 0xFF == ord('q'):
- cv2.destroyAllWindows()
- break
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement