Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Commit 652fe14

Browse files
added extract detections example
1 parent f9b84e2 commit 652fe14

File tree

4 files changed

+131
-3
lines changed

4 files changed

+131
-3
lines changed

‎detect_from_image.py

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,6 @@
44
import tensorflow as tf
55
from PIL import Image
66
from io import BytesIO
7-
import pathlib
87
import glob
98
import matplotlib.pyplot as plt
109

‎detect_from_video.py

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,6 @@
22
import argparse
33
import tensorflow as tf
44
import cv2
5-
import pathlib
65

76
from object_detection.utils import ops as utils_ops
87
from object_detection.utils import label_map_util

‎detect_from_webcam.py

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,6 @@
22
import argparse
33
import tensorflow as tf
44
import cv2
5-
import pathlib
65

76
from object_detection.utils import ops as utils_ops
87
from object_detection.utils import label_map_util

‎extract_detections_from_webcam.py

Lines changed: 131 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,131 @@
1+
import numpy as np
2+
import argparse
3+
import tensorflow as tf
4+
import cv2
5+
import datetime
6+
import os
7+
from PIL import Image
8+
import pandas as pd
9+
10+
from object_detection.utils import ops as utils_ops
11+
from object_detection.utils import label_map_util
12+
from object_detection.utils import visualization_utils as vis_util
13+
14+
# patch tf1 into `utils.ops`
15+
utils_ops.tf = tf.compat.v1
16+
17+
# Patch the location of gfile
18+
tf.gfile = tf.io.gfile
19+
20+
21+
def load_model(model_path):
22+
model = tf.saved_model.load(model_path)
23+
return model
24+
25+
26+
def run_inference_for_single_image(model, image):
27+
image = np.asarray(image)
28+
# The input needs to be a tensor, convert it using `tf.convert_to_tensor`.
29+
input_tensor = tf.convert_to_tensor(image)
30+
# The model expects a batch of images, so add an axis with `tf.newaxis`.
31+
input_tensor = input_tensor[tf.newaxis,...]
32+
33+
# Run inference
34+
output_dict = model(input_tensor)
35+
36+
# All outputs are batches tensors.
37+
# Convert to numpy arrays, and take index [0] to remove the batch dimension.
38+
# We're only interested in the first num_detections.
39+
num_detections = int(output_dict.pop('num_detections'))
40+
output_dict = {key: value[0, :num_detections].numpy()
41+
for key, value in output_dict.items()}
42+
output_dict['num_detections'] = num_detections
43+
44+
# detection_classes should be ints.
45+
output_dict['detection_classes'] = output_dict['detection_classes'].astype(np.int64)
46+
47+
# Handle models with masks:
48+
if 'detection_masks' in output_dict:
49+
# Reframe the the bbox mask to the image size.
50+
detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
51+
output_dict['detection_masks'], output_dict['detection_boxes'],
52+
image.shape[0], image.shape[1])
53+
detection_masks_reframed = tf.cast(detection_masks_reframed > 0.5, tf.uint8)
54+
output_dict['detection_masks_reframed'] = detection_masks_reframed.numpy()
55+
56+
return output_dict
57+
58+
59+
def run_inference(model, category_index, cap, show_video_steam, label_to_look_for, output_directory, threshold):
60+
# Create output directory if not already created
61+
os.makedirs(output_directory, exist_ok=True)
62+
os.makedirs(output_directory+'/images', exist_ok=True)
63+
64+
if os.path.exists(output_directory+'/results.csv'):
65+
df = pd.read_csv(output_directory+'/results.csv')
66+
else:
67+
df = pd.DataFrame(columns=['timestamp', 'img_path'])
68+
69+
while True:
70+
ret, image_np = cap.read()
71+
72+
# Copy image for later
73+
image_show = np.copy(image_np)
74+
75+
image_height, image_width, _ = image_np.shape
76+
77+
# Actual detection.
78+
output_dict = run_inference_for_single_image(model, image_np)
79+
80+
if show_video_steam:
81+
# Visualization of the results of a detection.
82+
vis_util.visualize_boxes_and_labels_on_image_array(
83+
image_np,
84+
output_dict['detection_boxes'],
85+
output_dict['detection_classes'],
86+
output_dict['detection_scores'],
87+
category_index,
88+
instance_masks=output_dict.get('detection_masks_reframed', None),
89+
use_normalized_coordinates=True,
90+
line_thickness=8)
91+
cv2.imshow('object_detection', cv2.resize(image_np, (800, 600)))
92+
if cv2.waitKey(25) & 0xFF == ord('q'):
93+
cap.release()
94+
cv2.destroyAllWindows()
95+
break
96+
97+
# Get data(label, xmin, ymin, xmax, ymax)
98+
output = []
99+
for index, score in enumerate(output_dict['detection_scores']):
100+
if score < threshold:
101+
continue
102+
label = category_index[output_dict['detection_classes'][index]]['name']
103+
ymin, xmin, ymax, xmax = output_dict['detection_boxes'][index]
104+
output.append((label, int(xmin * image_width), int(ymin * image_height), int(xmax * image_width), int(ymax * image_height)))
105+
106+
# Save incident (could be extended to send a email or something)
107+
for l, x_min, y_min, x_max, y_max in output:
108+
if l == label_to_look_for:
109+
array = cv2.cvtColor(np.array(image_show), cv2.COLOR_RGB2BGR)
110+
image = Image.fromarray(array)
111+
cropped_img = image.crop((x_min, y_min, x_max, y_max))
112+
file_path = output_directory+'/images/'+str(len(df))+'.jpg'
113+
cropped_img.save(file_path, "JPEG", icc_profile=cropped_img.info.get('icc_profile'))
114+
df.loc[len(df)] = [datetime.datetime.now(), file_path]
115+
df.to_csv(output_directory+'/results.csv', index=None)
116+
117+
if __name__ == '__main__':
118+
parser = argparse.ArgumentParser(description='Detect objects inside webcam videostream')
119+
parser.add_argument('-m', '--model', type=str, required=True, help='Model Path')
120+
parser.add_argument('-l', '--labelmap', type=str, required=True, help='Path to Labelmap')
121+
parser.add_argument('-t', '--threshold', type=float, default=0.5, help='Threshold for bounding boxes')
122+
parser.add_argument('-s', '--show', default=True, action='store_true', help='Show window')
123+
parser.add_argument('-la', '--label', default='person', type=str, help='Label name to detect')
124+
parser.add_argument('-o', '--output_directory', default='results', type=str, help='Directory for the outputs')
125+
args = parser.parse_args()
126+
127+
detection_model = load_model(args.model)
128+
category_index = label_map_util.create_category_index_from_labelmap(args.labelmap, use_display_name=True)
129+
130+
cap = cv2.VideoCapture(2)
131+
run_inference(detection_model, category_index, cap, args.show, args.label, args.output_directory, args.threshold)

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /