基于谷歌开源的Object-Detection API实现视频目标检测（tensorflow+opencv+anaconda3）

测试环境：Win7、Anaconda3、tensorflow、opencv、CPU

一、Anaconda3下安装tensorflow和opencv

1、创建anaconda虚拟环境

conda create -n tf_object python=3.6.7
 

其中tf_object为虚拟环境名称，可以根据自己喜好起名。

激活虚拟环境 activate tf_object  若退出可执行deactivate

2、安装tensorflow

打开Anaconda中的Anaconda Navigator

点击环境，然后选择虚拟环境tf_object

然后选择All，再搜索tensorflow再点击Apply进行安装；opencv的安装按照同样的方式进行安装，具体操作可以搜索相关CSDN博客。

进行验证，是否安装成功！！

打开cmd，再激活tf_object环境，然后输入python，再输入

 

   

    

   
   

    

     import tensorflow
    
   

   

    

   
   

    

     import cv2
    
   
 

不报错则安装成功！！

二、protoc安装

什么是Protoc？Protoc是用来编译.Proto文件，Protocol Buffers (ProtocolBuffer/ protobuf )是Google公司开发的一种数据描述语言，类似于XML能够将结构化数据序列化，可用于数据存储、通信协议等方面。现阶段支持C++、JAVA、Python等三种编程语言。

Protoc用于编译相关程序运行文件，进入Protoc下载页，下载类似下图中带win32的压缩包。

然后解压这个文件，并记住bin文件夹路径，最好不要出现中文。

三、Git安装

git +网址是目前主流的在线下载指令，在官网找到Windows下载安装，按步骤操作就行，记得选择windows的命令框

四、安装其他包

 

   

    

   
   

    

     pip 
     install pillow
    
   

   

    

   
   

    

     pip 
     install lxml
    
   

   

    

   
   

    

     pip 
     install jupyter
    
   

   

    

   
   

    

     pip 
     install matplotlib
    
   

   

    

   
   

    

     pip 
     install requests
    
   

   

    

   
   

    

     pip 
     install moviepy
    
   
 

注意这些需要先激活虚拟环境下再安装这些包

五、下载模型并编译

打开cmd输入

git clone http://github.com/tensorflow/models.git
 

下载后放在某个文件夹内，然后在cmd中进入models/research下，再进行编译

E:\protoc\bin\protoc object_detection\protos\*.proto --python_out=.
 

其中E:\protoc\bin\protoc表示你解压的protoc路径；object_detection\protos\*.proto --python_out=.是进行编译object_detection\protos\下的所有proto文件，运行成功，会编译生成py文件。

六、运行notebook demo

打开cmd 进入models/research再输入

jupyter-notebook
 

浏览器自动打开如下

然后新建python3程序，输入以下代码（对之前原始代码进行了些许改进）：

 

   

    

   
   

    

     import os
    
   

   

    

   
   

    

     import cv2
    
   

   

    

   
   

    

     import time
    
   

   

    

   
   

    

     import argparse
    
   

   

    

   
   

    

     import multiprocessing
    
   

   

    

   
   

    

     import numpy 
     as np
    
   

   

    

   
   

    

     import tensorflow 
     as tf
    
   

   

    

   
   

    

     from matplotlib 
     import pyplot 
     as plt
    
   

   

    

   
   

    

     %matplotlib inline
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    

     import six.moves.urllib 
     as urllib
    
   

   

    

   
   

    

     import sys
    
   

   

    

   
   

    

     import tarfile
    
   

   

    

   
   

    

     import zipfile
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    

     from collections 
     import defaultdict
    
   

   

    

   
   

    

     from io 
     import StringIO
    
   

   

    

   
   

    

     from PIL 
     import Image
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    

     from object_detection.utils 
     import label_map_util
    
   

   

    

   
   

    

     from object_detection.utils 
     import visualization_utils 
     as vis_util
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    

     CWD_PATH = os.getcwd()
    
   

   

    

   
   

    

     # Path to frozen detection graph. This is the actual model that is used for the object detection.
    
   

   

    

   
   

    

     MODEL_NAME = 
     'ssd_mobilenet_v1_coco_2017_11_17'
    
   

   

    

   
   

    

     PATH_TO_CKPT = os.path.join(CWD_PATH, 
     'object_detection', 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(CWD_PATH, 
     'object_detection', 
     'data', 
     'mscoco_label_map.pbtxt')
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    

     NUM_CLASSES = 
     90
    
   

   

    

   
   

    

     # Loading label map
    
   

   

    

   
   

    

     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)
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    

     def detect_objects(image_np, sess, detection_graph):
    
   

   

    

   
   

    
    
     # 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)
    
   

   

    

   
   

    
    
     return image_np
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    

     # First test on images
    
   

   

    

   
   

    

     PATH_TO_TEST_IMAGES_DIR = 
     'object_detection/test_images'
    
   

   

    

   
   

    

     TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 
     'image{}.jpg'.format(i)) 
     for i 
     in range(
     1, 
     3) ]
    
   

   

    

   
   

    

     # Size, in inches, of the output images.
    
   

   

    

   
   

    

     IMAGE_SIZE = (
     12, 
     8)
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    

     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)
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    

     from PIL 
     import Image
    
   

   

    

   
   

    

     for image_path 
     in TEST_IMAGE_PATHS:
    
   

   

    

   
   

    

         image = Image.open(image_path)
    
   

   

    

   
   

    

         image_np = load_image_into_numpy_array(image)
    
   

   

    

   
   

    

         plt.imshow(image_np)
    
   

   

    

   
   

    

         print(image.size, image_np.shape)
    
   
 

运行之后出来结果

继续输入代码：

 

   

    

   
   

    

     #Load a frozen TF model 
    
   

   

    

   
   

    

     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=
     '')
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    

     with detection_graph.as_default():
    
   

   

    

   
   

    
    
     with tf.Session(graph=detection_graph) 
     as sess:
    
   

   

    

   
   

    
        
     for image_path 
     in TEST_IMAGE_PATHS:
    
   

   

    

   
   

    

                 image = Image.open(image_path)
    
   

   

    

   
   

    

                 image_np = load_image_into_numpy_array(image)
    
   

   

    

   
   

    

                 image_process = detect_objects(image_np, sess, detection_graph)
    
   

   

    

   
   

    

                 print(image_process.shape)
    
   

   

    

   
   

    

                 plt.figure(figsize=IMAGE_SIZE)
    
   

   

    

   
   

    

                 plt.imshow(image_process)
    
   
 

得到图片检测结果如下所示

下面部分是对视频进行检测，继续输入代码

 

   

    

   
   

    

     # Import everything needed to edit/save/watch video clips
    
   

   

    

   
   

    

     import imageio
    
   

   

    

   
   

    

     imageio.plugins.ffmpeg.download()
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    

     from moviepy.editor 
     import VideoFileClip
    
   

   

    

   
   

    

     from IPython.display 
     import HTML
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    

     def process_image(image):
    
   

   

    

   
   

    
    
     # NOTE: The output you return should be a color image (3 channel) for processing video below
    
   

   

    

   
   

    
    
     # you should return the final output (image with lines are drawn on lanes)
    
   

   

    

   
   

    
    
     with detection_graph.as_default():
    
   

   

    

   
   

    
        
     with tf.Session(graph=detection_graph) 
     as sess:
    
   

   

    

   
   

    

                 image_process = detect_objects(image, sess, detection_graph)
    
   

   

    

   
   

    
            
     return image_process
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    
 
    
   

   

    

   
   

    

     white_output = 
     'video1_out.mp4'
    
   

   

    

   
   

    

     clip1 = VideoFileClip(
     "video1.mp4").subclip(
     0,
     2)
    
   

   

    

   
   

    

     white_clip = clip1.fl_image(process_image) 
     #NOTE: this function expects color images!!s
    
   

   

    

   
   

    

     %time white_clip.write_videofile(white_output, audio=
     False)
    
   
 

结果如下

输出视频video1_out.mp4保存到了代码所在文件目录中。

可以查看，输入下面代码

 

   

    

   
   

    

     HTML(
     """
    
   

   

    

   
   

    

     <video width="960" height="540" controls>
    
   

   

    

   
   

    

       <source src="{0}">
    
   

   

    

   
   

    

     </video>
    
   

   

    

   
   

    

     """.format(white_output))