> ## Documentation Index
> Fetch the complete documentation index at: https://dragonwingdocs.qualcomm.com/llms.txt
> Use this file to discover all available pages before exploring further.

# 使用 sample_object_segmentation 分割对象

`sample_object_segmentation` 示例应用程序使用 ROS 2 节点检测和分割图像中的对象。它使用 Qualcomm® AI Engine Direct SDK (QNN) 进行模型推理。

该示例应用程序使用 Ultralytics YOLOv8 模型预测图像中对象的边界框、分割掩码和类别。

<Note>
  **注意**

  更多信息,请参见 GitHub 上的 [sample\_object\_segmentation](https://github.com/qualcomm-qrb-ros/qrb_ros_samples/tree/main/ai_vision/sample_object_segmentation)。
</Note>

<video
  autoPlay
  muted
  loop
  playsInline
  width={400}
  height={401}
  src="https://mintlify.s3.us-west-1.amazonaws.com/qualcomm-prod/zh/SDKs/QIR-SDK-2.0/media/80-65220-2-qirp-sdk-qsg/yolo-segment.mp4"
  style={{
width: "50%",
display: "block",
margin: "0 auto" }}
/>

<p style={{ textAlign: 'center', fontWeight: 'bold' }}>
  图: `sample_object_segmentation` 的示例效果
</p>

## `sample_object_segmentation` 的管道流程

<img src="https://mintlify.s3.us-west-1.amazonaws.com/qualcomm-prod/zh/SDKs/QIR-SDK-2.0/media/80-65220-2-qirp-sdk-qsg/sample_object_segmentation-regenerate.svg" style={{width: "100%"}} />

<p style={{ textAlign: 'center', fontWeight: 'bold' }}>
  图: `sample_object_segmentation` 的管道流程
</p>

## `sample_object_segmentation` 中使用的 ROS 节点

|                                      **ROS 节点**                                     |                   **描述**                  |
| :---------------------------------------------------------------------------------: | :---------------------------------------: |
|        [qrb\_ros\_camera](https://github.com/qualcomm-qrb-ros/qrb_ros_camera)       | Qualcomm ROS 2 软件包,使用参数捕获图像并将其发布到 ROS 主题。 |
|    [yolo\_preprocess](https://github.com/qualcomm-qrb-ros/qrb_ros_tensor_process)   |        订阅图像数据,进行整形和调整大小,并重新发布到下游主题。       |
| [qrb\_ros\_nn\_inference](https://github.com/qualcomm-qrb-ros/qrb_ros_nn_inference) |     加载已训练的 AI 模型,接收预处理后的图像,执行推理并发布结果。     |
|   [yolo\_postprocess](https://github.com/qualcomm-qrb-ros/qrb_ros_tensor_process)   |            将推理输出与 YOLO 标签文件匹配。            |
|     [yolo\_overlay](https://github.com/qualcomm-qrb-ros/qrb_ros_tensor_process)     |   订阅 YOLO 后处理和图像数据,并将对象分割结果作为 ROS 主题显示。   |

## `sample_object_segmentation` 中使用的 ROS 主题

|           **ROS 主题**          |                       **类型**                       |             **发布者**             |
| :---------------------------: | :------------------------------------------------: | :-----------------------------: |
|        `/cam0_stream1`        |               `sensor_msgs.msg.Image`              |          `camera_node`          |
| `/qrb_inference_input_tensor` |      `qrb_ros_tensor_list_msgs.msg.TensorList`     |      `yolo_preprocess_node`     |
|        `/resized_image`       |               `sensor_msgs.msg.Image`              |      `yolo_preprocess_node`     |
| `/yolo_segment_tensor_output` |      `qrb_ros_tensor_list_msgs.msg.TensorList`     |       `nn_inference_node`       |
|     `/yolo_segment_result`    | `qrb_ros_vision_msgs.msg.Detection2DWithMaskArray` | `yolo_segment_postprocess_node` |
|    `/yolo_segment_overlay`    |               `sensor_msgs.msg.Image`              |   `yolo_segment_overlay_node`   |

<Note>
  **注意**

  `yolo_segment_overlay_node` 使用严格时间戳(exact-time)策略同步 `/yolo_segment_result` 和 `/resized_image` 两个输入。两者都必须处于发布状态,才能产生 `/yolo_segment_overlay`。
</Note>

## 前提条件

* 您已完成 [设置运行示例应用程序的环境](./set-up-env-for-sample-app) 中的设置。
* 您已按照以下步骤在主机计算机上使用 QAI-Hub 生成 YOLOv8 模型。

## 生成 YOLOv8 模型

1. 在主机计算机上设置 QAI-Hub。
   1. 登录 [QAI-Hub](https://app.aihub.qualcomm.com/docs/hub/getting_started.html) 并获取您的 API 令牌。
   2. 安装 QAI-Hub。
      ```python theme={null}
      ## It is recommended to use python venv to avoid impacting the host environment.
      python3 -m venv venv_qaihub
      source venv_qaihub/bin/activate
      ## Install QAI-Hub related python packages.
      pip3 install qai-hub
      ## Configure the QAI-Hub token, replacing xxx with your own token obtained from the QAI-Hub page.
      qai-hub configure --api_token xxx
      pip3 install "qai-hub-models[yolov8_seg]"
      ```
2. 在主机计算机上导出模型。
   ```python theme={null}
   # For IQ-9075, after executing the following commands, the model file and coco8.yaml are generated in the host computer.
   python -m qai_hub_models.models.yolov8_seg.export --target-runtime "tflite" --chipset "qualcomm-qcs9075-proxy" --skip-profiling --skip-inferencing
   ```
   ```bash title="SSH Session" theme={null}
   # Push model files to the device's default path according to the preceding export log.
   # On the device, create the path if it doesn't exist.
   mkdir /opt/model
   ```
   ```bash theme={null}
   # On the host computer, scp all model files to the device.
   scp <Host_Export_model_Path>/yolov8_det_float/yolov8_seg.tflite root@<device_ip>:/opt/model
   scp <Host_Export_model_Path>/coco8.yaml root@<device_ip>:/opt/
   ```

更多信息,请参见 GitHub 上的 [qrb\_ros\_tensor\_process](https://github.com/qualcomm-qrb-ros/qrb_ros_tensor_process/tree/main/cv_tensor_process/yolo_v8_process)。

## 运行开箱即用的 `sample_object_segmentation`

<Accordion title="试一试">
  <Steps>
    <Step title="在开发套件上运行示例">
      ```bash title="SSH Session" theme={null}
      # Set up the runtime environment
      source /usr/share/qirp-setup.sh -m
      # Set the ROS_DOMAIN_ID
      export ROS_DOMAIN_ID=123
      # Launch the sample object segmentation
      ros2 launch sample_object_segmentation launch_with_qrb_ros_camera.py model:=/opt/model/yolov8_seg.tflite
      ```
    </Step>

    <Step title="在主机计算机上检查结果">
      在主机计算机的终端中,使用 `rqt` 检查名称为 `/yolo_segment_overlay` 的 ROS 主题。
    </Step>
  </Steps>
</Accordion>

## 构建并运行 `sample_object_segmentation`

以下步骤以 Dragonwing IQ-9075 评估套件为例构建 `sample_object_segmentation` 软件包。

<Accordion title="试一试">
  <Steps>
    <Step title="在主机计算机上构建和打包">
      1. 构建示例应用程序项目。
         ```bash theme={null}
         cd <decompressed_workspace>/images/iq-9075-evk/qirpsdk_artifacts/iq-9075-evk/
         tar -zxvf qirp-sdk_<qirp_version>.tar.gz
         cd qirp-sdk
         source setup.sh
         # build sample
         cd <qirp_decompressed_path>/qirp-samples/ai_vision/sample_object_segmentation
         colcon build
         ```
      2. 打包示例应用程序并推送到设备。
         ```bash theme={null}
         # package and push build result of sample
         cd <qirp_decompressed_path>/qirp-samples/ai_vision/sample_object_segmentation/install/sample_object_segmentation
         tar -czvf sample_object_segmentation.tar.gz lib share
         scp sample_object_segmentation.tar.gz root@[ip-addr]:/opt/
         ```
    </Step>

    <Step title="在开发套件上安装并运行">
      1. 安装示例应用程序。
         ```bash title="SSH Session" theme={null}
         # Install sample package
         tar --no-overwrite-dir --no-same-owner -zxf /opt/sample_object_segmentation.tar.gz -C /usr/ros/jazzy/
         ```
      2. 使用 [运行开箱即用的 sample\_object\_segmentation](#run-out-of-the-box-sample_object_segmentation) 中的步骤运行示例应用程序。
    </Step>
  </Steps>
</Accordion>