ros2与深度学习教程-整合物体检测(mobilenet-ssd)

ros2与深度学习教程-整合物体检测(mobilenet-ssd)

说明：　

• 介绍如何整合Openvino使用mobilenet-ssd模型

步骤:

• pipeline_object.launch.py物体识别
• 需要下载例子对应的模型文件

cd /opt/openvino_toolkit/models/
sudo python3 downloader.py --name mobilenet-ssd 　

• 下载到目录/opt/openvino_toolkit/models/public/mobilenet-ssd
• mobilenet-ssd是caffe模型，需要转化caffe模型为openvino格式

#进入目录
cd /opt/intel/openvino_2021/deployment_tools/model_optimizer
#更改目录权限
sudo chmod -R 777 /opt/openvino_toolkit/models/public/mobilenet-ssd
#转化
python3 mo.py --input_model /opt/openvino_toolkit/models/public/mobilenet-ssd/mobilenet-ssd.caffemodel --output_dir /opt/openvino_toolkit/models/public/mobilenet-ssd/

• 复制labels文件

sudo cp ~/openvino2_ws/src/ros2_openvino_toolkit/data/labels/object_detection/mobilenet-ssd.labels /opt/openvino_toolkit/models/public/mobilenet-ssd/

• 并修改代码包里ros2_openvino_toolkit/sample/param目录下pipeline_object.launch.py对应的配置文件pipeline_object.yaml
• 内容如下：

Pipelines:
- name: object
  inputs: [StandardCamera]
  infers:
    - name: ObjectDetection
      model: /opt/openvino_toolkit/models/public/mobilenet-ssd/mobilenet-ssd.xml
      engine: CPU
      label: /opt/openvino_toolkit/models/public/mobilenet-ssd/obilenet-ssd.labels
      batch: 1
      confidence_threshold: 0.5
      enable_roi_constraint: true # set enable_roi_constraint to false if you don't want to make the inferred ROI (region of interest) constrained into the camera frame
  outputs: [ImageWindow, RosTopic, RViz]
  connects:
    - left: StandardCamera
      right: [ObjectDetection]
    - left: ObjectDetection
      right: [ImageWindow]
    - left: ObjectDetection
      right: [RosTopic, RViz]

OpenvinoCommon:

测试：　

• 接好usb摄像头
• 新开终端，执行命令

#run face detection sample code input from StandardCamera.
ros2 launch dynamic_vino_sample pipeline_object.launch.py

• 查看话题

ros2 run rqt_image_view rqt_image_view