Add working version with cv but very slow.

Author: datitran

object_detection_app.py

@@ -1,5 +1,6 @@
-import numpy as np
 import os
+import cv2
+import numpy as np
 import tensorflow as tf
 
 from PIL import Image
@@ -40,44 +41,56 @@ def load_image_into_numpy_array(image):
  (im_height, im_width, 3)).astype(np.uint8)
 
 
-with detection_graph.as_default():
- with tf.Session(graph=detection_graph) as sess:
- image = Image.open('image.jpg')
-
- # 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_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})
-
- # 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)
-
- img = Image.fromarray(image_np)
- img.save("image.jpg")
+def detect_objects(image_stream):
+ with detection_graph.as_default():
+ with tf.Session(graph=detection_graph) as sess:
+ image = Image.fromarray(image_stream)
+
+ # 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_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})
+
+ # 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)
+
+ return image_np
+
 
 if __name__ == '__main__':
- pass
+ video_capture = cv2.VideoCapture(1)
+
+ while True:
+ ret, frame = video_capture.read()
+ cv2.imshow('Video', detect_objects(frame))
+
+ if cv2.waitKey(1) & 0xFF == ord('q'):
+ break
+
+ # When everything is done, release the capture
+ video_capture.release()
+ cv2.destroyAllWindows()