TensorFlow Object Detection API 技术手册（4）——使用摄像头进行实时目标检测

（一）使用opencv开启摄像头

使用OpenCV打开摄像头并实时显示的代码如下：

import cv2

cap = cv2.VideoCapture(0)

while True:
    ret, frame = cap.read()
    cv2.imshow('object detection', frame)
    if cv2.waitKey(25) & 0xFF == ord('q'):
        cv2.destroyAllWindows()
        break
cap.release()
cv2.destroyAllWindows()

运行显示：

（二）修改Demo代码

要实现对场景的实时检测，我们只需要对Demo代码稍做修改即可

• 导入包

from object_detection.utils import visualization_utils as vis_util
from object_detection.utils import label_map_util
from distutils.version import StrictVersion
import tensorflow as tf
import numpy as np
import cv2

if StrictVersion(tf.__version__) < StrictVersion('1.9.0'):
    raise ImportError('Please upgrade your TensorFlow installation to v1.9.* or later!')

• 开启摄像头

cap = cv2.VideoCapture(0)

• 添加模型位置和标签配置文件位置（使用COCO数据集训练的预训练模型）

PATH_TO_FROZEN_GRAPH = ''
PATH_TO_LABELS = ''

• 载入模型

detection_graph = tf.Graph()
with detection_graph.as_default():
    od_graph_def = tf.GraphDef()
    with tf.gfile.GFile(PATH_TO_FROZEN_GRAPH, 'rb') as fid:
        serialized_graph = fid.read()
        od_graph_def.ParseFromString(serialized_graph)
        tf.import_graph_def(od_graph_def, name='')

category_index = label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS, use_display_name=True)

• 进行检测

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)

            cv2.imshow('object detection', image_np)
            if cv2.waitKey(25) & 0xFF == ord('q'):
                cv2.destroyAllWindows()
                break
cap.release()
cv2.destroyAllWindows()

（三）实时检测

运行上述代码，如下图所示：

（四）完整代码

from object_detection.utils import visualization_utils as vis_util
from object_detection.utils import label_map_util
from distutils.version import StrictVersion
import tensorflow as tf
import numpy as np
import cv2

if StrictVersion(tf.__version__) < StrictVersion('1.9.0'):
    raise ImportError('Please upgrade your TensorFlow installation to v1.9.* or later!')
    
# 开启摄像头
cap = cv2.VideoCapture(0)

# 添加模型位置和标签配置文件位置
PATH_TO_FROZEN_GRAPH = ''
PATH_TO_LABELS = ''

# 载入模型
detection_graph = tf.Graph()
with detection_graph.as_default():
    od_graph_def = tf.GraphDef()
    with tf.gfile.GFile(PATH_TO_FROZEN_GRAPH, 'rb') as fid:
        serialized_graph = fid.read()
        od_graph_def.ParseFromString(serialized_graph)
        tf.import_graph_def(od_graph_def, name='')

category_index = label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS, use_display_name=True)

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)

            cv2.imshow('object detection', image_np)
            if cv2.waitKey(25) & 0xFF == ord('q'):
                cv2.destroyAllWindows()
                break
cap.release()
cv2.destroyAllWindows()

（五）错误提示

使用jupyter运行时可能会报告以下错误，说feed_dict没有获取到数据：

这是由于摄像头没有成功获取到图像的缘故，读者可以使用PyCharm运行完整代码，错误应该会消除。
下一节：TensorFlow Object Detection API 技术手册（5）——制作自己的目标检测数据集