Object Detection API 的配置参考另一篇文章 :https://blog.csdn.net/ytusdc/article/details/89883274
首先写一个测试代码实现摄像头实时捕捉,测试摄像头是否能调用成功
import cv2
import numpy as np
cap = cv2.VideoCapture(0)
while(1):
# get a frame
ret, frame = cap.read()
# show a frame
cv2.imshow("capture", frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
最后上最终代码,实现摄像头实时检测:
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
import time
from distutils.version import StrictVersion
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
# 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 StrictVersion(tf.__version__) < StrictVersion('1.9.0'):
raise ImportError('Please upgrade your TensorFlow installation to v1.9.* or later!')
import cv2
cap = cv2.VideoCapture(0)
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
#CWD_PATH = os.getcwd()
CWD_PATH= "/home/vision/Project/tf-models/research/object_detection"
PATH_TO_CKPT = os.path.join(CWD_PATH, 'ssd_mobilenet_v1_coco_2017_11_17', 'frozen_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, 'data', 'mscoco_label_map.pbtxt')
NUM_CLASSES = 90
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='')
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)
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
while True:
time_start=time.time()
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)
cv2.imshow('object detection', cv2.resize(image_np, (800, 600)))
time_end=time.time()
print('time cost',(time_end-time_start)*1000,'ms')
if cv2.waitKey(25) & 0xFF == ord('q'):
cv2.destroyAllWindows()
break
cap.release()
cv2.destroyAllWindows()