我正在尝试在实时视频流的特定区域检测汽车。为此，我使用了Tensorflow的对象检测API。现在，检测已经足够公平了，实时视频流中几乎所有的汽车都被检测为“汽车”，它们周围有边界框，并且具有一定百分比的检测置信度得分。
我的问题是如何检查所需边界框上仅所需的可用性？
例如，由于所需区域和用于检测的摄像机都固定在位置上，因此我使用了OpenCV的cv2.rectangle()函数，并通过了(x1,y1)和(x2,y2)坐标。所需区域。所以现在，我在该区域周围有一个恒定矩形框。我的任务是通过向Ubuntu终端打印一条“检测到”的日志消息，以某种方式知道汽车已到达此标记的矩形区域。
我很难比较边界框坐标和矩形坐标。因此出现了问题
这是我使用的代码。
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
from collections import defaultdict
from io import StringIO
from PIL import Image
import cv2
cap = cv2.VideoCapture(0)
# This is needed since the notebook is stored in the object_detection
folder.
sys.path.append("..")
from object_detection.utils import ops as utils_ops
if tf.__version__ != '1.10.1':
raise ImportError('Please upgrade your tensorflow installation to
v1.10.1* or later!')
# ## Env setup
# In[3]:
# ## Object detection imports
# Here are the imports from the object detection module.
# In[5]:
from utils import label_map_util
from utils import visualization_utils as vis_util
# # Model preparation
# ## Variables
# Any model exported using the `export_inference_graph.py` tool can be
loaded here simply by changing `PATH_TO_FROZEN_GRAPH` to point to a
new .pb file.
#
# By default we use an "SSD with Mobilenet" model here. See the
[detection model zoo]
# In[6]:
# What model to download.
MODEL_NAME = 'car_inference_graph'
# 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('training', 'object-detection.pbtxt')
NUM_CLASSES = 1
# ## Load a (frozen) Tensorflow model into memory.
# In[7]:
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 maps map indices to category names, so that when our
convolution network predicts `5`, we know that this corresponds to
`airplane`. Here we use internal utility functions, but anything that
returns a dictionary mapping integers to appropriate string labels
would be fine
# In[8]:
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
# In[9]:
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
def run_inference_for_single_image(image, graph):
with 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[0],
image.shape[1])
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:
np.expand_dims(image, 0)})
# 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.uint8)
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
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
while True:
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)
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)
area1 = cv2.rectangle(image_np,(201,267),(355,476),
(0,255,0),2)
area2 = cv2.rectangle(image_np,(354,271),(562,454),
(255,0,0),2)
cv2.imshow("object detection", image_np)
if 'detection_boxes:0' == 1 in area1[(201,267),(353,468)]:
print("area1 occupied!")
else:
print("area1 free!")
if 'detection_boxes:1' == 1 in area2[(354,271),(562,454)]:
print("area2 occupied!")
else:
print("area2 free!")
if cv2.waitKey(1) & 0xFF == ord('q'):
cv2.destroyAllWindows()
cap.release()
break
我发现很难找到解决方案。请帮忙。
技术信息：
Tensorflow 1.10
OS-Ubuntu 18.04
Python 3.6
OpenCV 3.4.2
谢谢：）
答案 0 :(得分：0)
您可以为此使用Intersection over Union。如果汽车在您想要的标记矩形中。 IOU会有一些值，否则将为零。
当汽车矩形正好在您标记的矩形中时，它将接近1，这将是您的解决方案