之前在做实时监控中人脸识别、人体姿态识别等项目，可以说一直在与视频打交道，今日心血来潮，顺便帮助师妹快速了解目标检测，特意选择了谷歌开源的Object-Detection API实现基于视频的目标检测。
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 inlineimport six.moves.urllib as urllib
import sys
import tarfile
import zipfilefrom collections import defaultdict
from io import StringIO
from PIL import Imagefrom object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_utilCWD_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.sizereturn 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 HTMLdef 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_processwhite_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))