ROS+OpenCV 人脸识别，物体识别

原创

已于 2022-09-24 23:03:59 修改 · 1.3w 阅读

267 ·

CC 4.0 BY-SA版权

文章标签：

#ROS+OpenCV 人脸识别 #ROS+OpenCV 物体识别

于 2020-06-13 13:55:53 首次发布

本文详细介绍如何在ROS环境中搭建人脸识别及物体追踪系统，包括环境准备、功能包创建、程序编写、launch文件配置及执行步骤。通过具体代码示例，展示如何使用OpenCV进行人脸检测与追踪，并提供物体追踪的实现方法。

人脸识别

1.环境准备

首先准备ROS系统，基于ros的软件支持opencv,usbcam

apt install ros-kinetic-desktop-full

apt install ros-kinetic-opencv3

apt install ros-kinetic-usb-cam

2.创建工作空间与功能包

在创建功能包时导入依赖库

$ source /opt/ros/kinetic/setup.zsh
$ mkdir -p ~/catkin_ws/src
$ cd ~/catkin_ws/src
$ catkin_init_workspace
$ cd ~/catkin_ws
$ catkin_make 
$ souce ~/catkiin_ws/devel/setup.zsh
$ cd ~/catkin_ws/src
$ catkin_create_pkg test1 rospy roscpp std_msgs sensor_msgs cv_bridge image_transport 
$ cd ~/catkin_ws
$ catkin_make
$ source devel/setup.zsh

创建文件目录结构

scripts存放代码，launch存放启动文件

$cd test1
$mkdir launch scripts

3.人脸识别程序

$cd test1/scripts

$touch face_detector.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import rospy
import cv2
import numpy as np
from sensor_msgs.msg import Image, RegionOfInterest
from cv_bridge import CvBridge, CvBridgeError

class faceDetector:
    def __init__(self):
        rospy.on_shutdown(self.cleanup);

        # 创建cv_bridge
        self.bridge = CvBridge()
        self.image_pub = rospy.Publisher("cv_bridge_image", Image, queue_size=1)

        # 获取haar特征的级联表的XML文件，文件路径在launch文件中传入
        cascade_1 = rospy.get_param("~cascade_1", "")
        cascade_2 = rospy.get_param("~cascade_2", "")

        # 使用级联表初始化haar特征检测器
        self.cascade_1 = cv2.CascadeClassifier(cascade_1)
        self.cascade_2 = cv2.CascadeClassifier(cascade_2)

        # 设置级联表的参数，优化人脸识别，可以在launch文件中重新配置
        self.haar_scaleFactor  = rospy.get_param("~haar_scaleFactor", 1.2)
        self.haar_minNeighbors = rospy.get_param("~haar_minNeighbors", 2)
        self.haar_minSize      = rospy.get_param("~haar_minSize", 40)
        self.haar_maxSize      = ros

最低0.47元/天解锁文章