ubuntu 16.04下人脸识别库face_recognition的使用及顺序控制节点启动

（1）安装dlib

sudo pip install dlib

结果出现了问题：
ImportError: cannot import name main
解决方法：pip地址改变解决方法

（2）安装 face_recognition

参考链接：
人脸识别库face_recognition安装简单教程

sudo pip install face_recognition

安装完成输入以下代码检测：

$ python
>>> import face_recognition

（3）使用usb_cam实时获取usb摄像头的图像

使用usb_cam获取实时usb摄像头图像

（4） 建立ros包，接收图像并转化为人脸识别后的图像

参考链接：
译：ROS和Openv之间的图像转换（Python）

接收图像的订阅节点：usb_cam/image_raw
发布人脸识别的节点：face_recognition_image
将usb_cam的launch文件里面的image_view节点改为/face_recognition_image

catkin_create_pkg sub_image rospy cv_bridge std_msgs sensor_msgs

#!/usr/bin/env python
from __future__ import print_function
 
import roslib
#roslib.load_manifest('my_package')
import sys
import rospy
import cv2
from std_msgs.msg import String
from sensor_msgs.msg import Image
from cv_bridge import CvBridge, CvBridgeError

import numpy as np
import face_recognition

class image_converter:
 
  def __init__(self):
    self.image_pub = rospy.Publisher("face_recognition_image",Image)
 
    self.bridge = CvBridge()
    self.image_sub = rospy.Subscriber("usb_cam/image_raw",Image,self.callback)
 
  def callback(self,data):
    try:
      cv_image = self.bridge.imgmsg_to_cv2(data, "bgr8")
    except CvBridgeError as e:
      print(e)
 	
    face_locations = face_recognition.face_locations(cv_image)
    
    for (A,B,C,D) in face_locations:
        cv2.rectangle(cv_image,(D,A),(B,C),(0,255,0),2)

    #cv2.imshow('image',cv_image)
    #cv2.waitKey(3)
 
    try:
      self.image_pub.publish(self.bridge.cv2_to_imgmsg(cv_image, "bgr8"))
    except CvBridgeError as e:
      print(e)
 
def main(args):
  ic = image_converter()
  rospy.init_node('image_converter', anonymous=True)
  try:
    rospy.spin()
  except KeyboardInterrupt:
    print("Shutting down")
  cv2.destroyAllWindows()
 
if __name__ == '__main__':
    main(sys.argv)

（5） 运行结果

roscore
rosrun sub_image sub_image.py
roslaunch usb_cam usb_cam-test.launch

(6)顺序控制节点启动

经过测试，需要先运行sub_image，在运行usb_cam，否则会出现大段红色警告。
顺序控制节点启动的方法：建立bash文件，multi_launch.sh，写入以下代码

#!/bin/bash

rosrun sub_image sub_image.py &
sleep 1
echo "sub_image starting success!"

roslaunch usb_cam usb_cam-test.launch &
sleep 1

wait
exit 0

#!/bin/bash表示是bash程序，sleep是延时1s，echo打印输出
执行bash文件：

chmox 777 multi_launch.sh
roscore
./multi_launch.sh