初试darknet_ros

初试darknet_ros

1.安装darknet_ros

Github

1.1下载源码

cd catkin_workspace/src
git clone --recursive git@github.com:leggedrobotics/darknet_ros.git
cd ../

推荐采用git clone。
如果下载zip安装包，需在catkin_workspace/src/darknet_ros/darknet/下载darknet。
建议提前下载好默认编译所需权重，放在catkin_workspace/src/darknet_ros/darknet_ros/yolo_network_config/weights/中以减少编译时间，所需权重下载链接为：yolov2、yolov2-tiny、yolov3。

1.2编译

catkin_make -DCMAKE_BUILD_TYPE=Release

可能错误

问题1

YoloObjectDetector.cpp:516:49: error: no matching function for call to ‘_IplImage::_IplImage(cv::Mat&)’

则需对catkin_workspace/src/darknet_ros/darknet_ros/src/YoloObjectDetector.cpp文件进行修改，应为line515至line519，但具体结合文件。
修改前：

// line515:ling519
IplImageWithHeader_ YoloObjectDetector::getIplImageWithHeader() {
  IplImage* ROS_img = new IplImage(camImageCopy_);
  IplImageWithHeader_ header = {.image = ROS_img, .header = imageHeader_};
  return header;
}

修改后：

IplImageWithHeader_ YoloObjectDetector::getIplImageWithHeader() {
  IplImage ROS_img = cvIplImage(camImageCopy_);
  IplImageWithHeader_ header = {.image = &ROS_img, .header = imageHeader_};
  return header;
}

修改后再次编译，应可成功编译。

2.安装usb_cam

sudo apt-get install ros-kinetic-usb-cam

3.修改darknet_ros配置文件

修改catkin_workspace/src/darknet_ros/darknet_ros/config/ros.yaml，以订阅摄像头图像。

subscribers:

  camera_reading:
    topic: /camera/rgb/image_raw
    queue_size: 1
...

修改为

subscribers:

  camera_reading:
    topic: /usb_cam/image_raw
    queue_size: 1
...

4.运行测试

cd catkin_workspace/src
source devel/setup.bash
roslaunch darknet_ros darknet_ros.launch
roslaunch usb_cam usb_cam-test.launch

5.使用其它YOLO模型

以YOLO-s为例。

5.1yolos.yaml

yolos.yaml路径为catkin_workspace/src/darknet_ros/darknet_ros/config/yolos.yaml，其内容为

yolo_model:

  config_file:
    name: yolos.cfg
  weight_file:
    name: yolos_32000.weights
  threshold:
    value: 0.3
  detection_classes:
    names:
      - soldier

5.2yolo_s.launch

yolo_s.launch路径为catkin_workspace/src/darknet_ros/darknet_ros/launch/yolo_s.launc，其内容为：

<?xml version="1.0" encoding="utf-8"?>

<launch>
  <!-- Console launch prefix -->
  <arg name="launch_prefix" default=""/>
  <arg name="image" default="/camera/rgb/image_raw" />

  <!-- Config and weights folder. -->
  <arg name="yolo_weights_path"          default="$(find darknet_ros)/yolo_network_config/weights"/>
  <arg name="yolo_config_path"           default="$(find darknet_ros)/yolo_network_config/cfg"/>

  <!-- ROS and network parameter files -->
  <arg name="ros_param_file"             default="$(find darknet_ros)/config/ros.yaml"/>
  <arg name="network_param_file"         default="$(find darknet_ros)/config/yolos.yaml"/>

  <!-- Load parameters -->
  <rosparam command="load" ns="darknet_ros" file="$(arg ros_param_file)"/>
  <rosparam command="load" ns="darknet_ros" file="$(arg network_param_file)"/>

  <!-- Start darknet and ros wrapper -->
  <node pkg="darknet_ros" type="darknet_ros" name="darknet_ros" output="screen" launch-prefix="$(arg launch_prefix)">
    <param name="weights_path"          value="$(arg yolo_weights_path)" />
    <param name="config_path"           value="$(arg yolo_config_path)" />
    <remap from="camera/rgb/image_raw"  to="$(arg image)" />
  </node>

 <!--<node name="republish" type="republish" pkg="image_transport" output="screen" 	args="compressed in:=/front_camera/image_raw raw out:=/camera/image_raw" /> -->
</launch>

5.3模型的yolos.cfg文件和yolos.weights文件

yolos.cfg路径为catkin_workspace/src/darknet_ros/darknet_ros/yolo_network_config/cfg/yolos.cfg。
yolos.cfg路径为catkin_workspace/src/darknet_ros/darknet_ros/yolo_network_config/cfg/yolos.weights。