tf之object detect摄像头物体识别测试

最新推荐文章于 2025-05-14 09:22:16 发布

shareinfo2018

最新推荐文章于 2025-05-14 09:22:16 发布

阅读量2.8k

点赞数 3

CC 4.0 BY-SA版权

分类专栏： deeplearning

本文链接：https://blog.youkuaiyun.com/chenyefei/article/details/77046715

deeplearning 专栏收录该内容

33 篇文章

订阅专栏

本博客介绍使用TensorFlow实现的SSD MobileNet V1模型进行实时物体检测的过程。该模型可在各种设备上高效运行，特别适用于摄像头输入的实时场景分析。文中详细展示了从模型下载、配置到最终在摄像头视频流中检测并标注物体类别的完整步骤。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
import cv2
import time  

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 utils import label_map_util
from utils import visualization_utils as vis_util

# What model to download.
MODEL_NAME = 'ssd_mobilenet_v1_coco_11_06_2017'
#MODEL_NAME = 'faster_rcnn_resnet101_coco_11_06_2017'
#MODEL_NAME = 'ssd_inception_v2_coco_11_06_2017'
MODEL_FILE = MODEL_NAME + '.tar.gz'

# 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('/home/chenqy/tf36/models/object_detection/data', 'mscoco_label_map.pbtxt')

#extract the ssd_mobilenet
start = time.clock()
NUM_CLASSES = 90
opener = urllib.request.URLopener()
#opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
# tar_file = tarfile.open(MODEL_FILE)
# for file in tar_file.getmembers():
#   file_name = os.path.basename(file.name)
#   if 'frozen_inference_graph.pb' in file_name:
#     tar_file.extract(file, os.getcwd())
end= time.clock()
print('load the model',(end-start))

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)

cap = cv2.VideoCapture(0)
with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
      writer = tf.summary.FileWriter("logs/", sess.graph)  
      sess.run(tf.global_variables_initializer())  
      while(1):
        start = time.clock()
        ret, frame = cap.read()
        if cv2.waitKey(1) & 0xFF == ord('q'):
            break
        image_np=frame
        # the array based representation of the image will be used later in order to prepare the
        # result image with boxes and labels on it.
        # 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=6)
        end = time.clock()
        print('frame:',1.0/(end - start))
        #print 'frame:',time.time() - start
        cv2.imshow("capture", image_np)
        cv2.waitKey(1)
cap.release()
cv2.destroyAllWindows()

测试比较卡，估计电脑以及虚拟机配置比较差，显示结果：