# 目标检测

Source: [https://docs.qualcomm.com/doc/80-70018-50SC/topic/gst-ai-object-detection.html](https://docs.qualcomm.com/doc/80-70018-50SC/topic/gst-ai-object-detection.html)

**gst-ai-object-detection** 应用程序可以检测图像和视频中的对象。这些用例展示了使用 Qualcomm Neural Processing SDK runtime 执行 [YOLOv5](https://github.com/ultralytics/yolov5)、[YOLOv8](https://github.com/ultralytics/ultralytics) 和 [YOLO-NAS](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md)，使用 Qualcomm AI Engine Direct 执行 YOLOv8，以及使用 LiteRT 执行 YOLOv5 和 YOLOv8。

该图显示了一个 pipeline，从摄像头流、文件、或实时流协议 (RTSP) 流获取输入，执行预处理，在 AI 硬件上运行推理，并将结果显示在屏幕上。有关 pipeline 流中使用的插件的信息，请参见 [Pipeline 流](https://docs.qualcomm.com/doc/80-70018-50SC/topic/gst-ai-object-detection.html#gst-ai-object-detection__section_p2w_33y_kbc)。

Figure : gst-ai-object-detection pipeline
            
            ![](data:image/jpeg;base64,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)

本视频将指导您设置实时摄像头流、实现预处理步骤、在专用硬件上运行 AI 推理以及实时显示检测结果。视频将在新页面中打开。

<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewbox="0 0 640 400" width="640" height="400" style="cursor:auto !important">
    <defs>
      <style>@import url("https://fonts.googleapis.com/css2?family=Roboto+Flex:opsz,wght@8..144,100..1000&display=swap");
.svg-1 .bg-fill { fill: var(--color-background) }
.svg-1 .fill-text { color: var(--color-content); fill: var(--color-content) }
.svg-1 .video-hoverbox { transition: opacity 0.15s ease-in-out }
.svg-1 .video-hoverbox:hover { opacity: 0.9 }</style>
  </defs>

  <foreignobject x="0" y="0" width="640" height="400">
    
        <iframe width="640" height="400" src="https://players.brightcove.net/1414329538001/4JiZQnWhg_default/index.html?videoId=6380739279112" allowfullscreen="" allow="encrypted-media"></iframe>
    <div class="topic-detail"><div class="topic-updated-date"><span> Last Published: </span>Nov 12, 2025</div><div class="prev-and-next-links"><span class="previous-topic-link"><span aria-hidden="true" class="disabled" data-tip="" data-effect="solid"></span></span></div></div>
    </foreignobject>
</svg>

## 示例模型和标签文件

| Runtime | 模型文件 | 标签文件 |
| --- | --- | --- |
| Qualcomm Neural Processing SDK | *yolonas.dlc* | <ul class="ul" id="gst-ai-object-detection__ul_qhr_1qq_32c"><br>                                    <li class="li"><em class="ph i">yolonas.labels</em></li><br><br>                                    <li class="li"><em class="ph i">yolov8.labels</em></li><br><br>                                </ul> |
| LiteRT | *yolov8\_det\_quantized.tflite* | <ul class="ul" id="gst-ai-object-detection__ul_qhr_1qq_32c"><br>                                    <li class="li"><em class="ph i">yolonas.labels</em></li><br><br>                                    <li class="li"><em class="ph i">yolov8.labels</em></li><br><br>                                </ul> |
| Qualcomm AI Engine Direct | *yolov8\_det\_quantized.bin* | <ul class="ul" id="gst-ai-object-detection__ul_qhr_1qq_32c"><br>                                    <li class="li"><em class="ph i">yolonas.labels</em></li><br><br>                                    <li class="li"><em class="ph i">yolov8.labels</em></li><br><br>                                </ul> |
|  |  |  |
|  |  |  |

Note: 当前版本不支持 YOLOv8 Qualcomm AI Engine direct SDK 模型。

## 前提条件

- 如果还没有安装 eSDK，请[下载并安装 eSDK](https://docs.qualcomm.com/bundle/publicresource/topics/80-70018-51/install-sdk.html#download-and-install-esdk-)。
- 将模型和标签文件推送到设备以运行应用程序。相关说明，可参见[下载模型和标签文件](https://docs.qualcomm.com/doc/80-70018-50SC/topic/download-model-and-label-files.html)。
    该应用程序支持 Qualcomm Neural Processing SDK、Qualcomm AI Engine Direct 和
                        LiteRT 模型。
- 要访问主机，请启用 SSH。有关说明，请参阅[使用 SSH 登录](https://docs.qualcomm.com/bundle/publicresource/topics/80-70018-254/how_to.html#use-ssh)。 
Note: 如果 SSH 已启用，则可以跳过此步骤。
- 从 Linux 主机推送模型文件：

        scp <model_filename> root@<IP address of target device>:/etc/modelsCopy to clipboard
- 请注意，[下载的脚本](https://docs.qualcomm.com/doc/80-70018-50SC/topic/download-model-and-label-files.html)会将示例 video.mp4 视频下载到 /etc/media 目录。如果您使用的是自定义视频，请确保将视频推送到 /etc/media，并在应用程序的 config.JSON 文件中更新文件路径。
- 使用 HDMI 端口将显示器连接到设备。有关说明，请参见[设置 HDMI 显示器](https://docs.qualcomm.com/bundle/publicresource/topics/80-70018-18/samples.html)。
- 启用显示屏：

        export XDG_RUNTIME_DIR=/dev/socket/weston && export WAYLAND_DISPLAY=wayland-1Copy to clipboard

如果启用摄像头或显示器时遇到问题，请参阅[摄像头故障排除](https://docs.qualcomm.com/bundle/publicresource/topics/80-70018-17/troubleshooting.html)和[显示器故障排除](https://docs.qualcomm.com/bundle/publicresource/topics/80-70018-18/debug.html)。

## 运行应用程序

示例应用程序使用 /etc/configs/config\_detection.json 文件读取输入参数。

要创建自己的 config JSON 文件，请使用 [config_detection.json](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/blob/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-object-detection/config_detection.json?ref_type=heads) 作为参考。

1. 进入第二个 SSH shell 并将 YOLO-NAS 标签文件复制到 YOLOv8：

        cp /etc/labels/yolonas.labels /etc/labels/yolov8.labelsCopy to clipboard
2. 使用以下格式的 /etc/configs/config\_detection.json
                        文件：

        {
          "file-path": "<input video path>",
          "ml-framework": "<snpe, or tflite or qnn framework>",
          "yolo-model-type": "<yolov8 or yolonas or yolov5>",
          "model": "<Model Path>",
          "labels": "<Label Path>",
          "constants": "<Model Constants for LiteRT Model>",
          "threshold": <Post-processing threshold, integer value from 1-100>,
          "runtime": "<dsp, cpu or gpu runtime>"
        }Copy to clipboard

Note: 根据模型、输入流和其他属性更新 config JSON
                        文件。关于更多详细信息，请参阅 [Config JSON 字段说明](https://docs.qualcomm.com/doc/80-70018-50SC/topic/gst-ai-object-detection.html#gst-ai-object-detection__section_qjx_hqq_32c)。

    例如，使用视频文件输入、LiteRT、YOLOv8 模型、DSP
                        runtime、自定义常量和自定义阈值来运行应用程序：

        {
          "file-path": "/etc/media/video.mp4",
          "ml-framework": "tflite",
          "yolo-model-type": "yolov8",
          "model": "/etc/models/yolov8_det_quantized.tflite",
          "labels": "/etc/labels/yolov8.labels",
          "constants": "YOLOv8,q-offsets=<21.0, 0.0, 0.0>,q-scales=<3.0546178817749023, 0.003793874057009816, 1.0>;",
          "threshold": 40,
          "runtime": "dsp"
        }Copy to clipboard
3. 运行 gst-ai-object-detection 应用程序：

        gst-ai-object-detection --config-file=/etc/configs/config_detection.jsonCopy to clipboard

Note: 可以在 `yolo-model-type` 字段中使用 YOLOv8 值来运行 Yolo-NAS-Quantized.tflite 模型。

要显示可用的帮助选项，请在 SSH shell 中运行以下命令：

    gst-ai-object-detection -hCopy to clipboard

要停止用例，请按 CTRL + C。

## 预期输出

Figure : gst-ai-object-detection 应用程序的预期输出
                
                ![](data:image/png;base64,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)

## Pipeline 流

该表列出了目标检测 pipeline 中使用的插件：

| 插件 | 说明 |
| --- | --- |
| 摄像头源：[qtiqmmfsrc](https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtiqmmfsrc.html) | <ul class="ul" id="gst-ai-object-detection__ul_zyl_gj1_mcc"><br>                                    <li class="li">从摄像头采集实时流。</li><br><br>                                    <li class="li">使用 tee 拆分流进行推理。</li><br><br>                                </ul> |
| 文件源：filesrc | <ul class="ul" id="gst-ai-object-detection__ul_z1z_x4f_w1c"><br>                                    <li class="li">使用 filesrc 采集视频流，然后使用 qtdemux 对视频流进行解复用。</li><br><br>                                    <li class="li">使用 tee 拆分流进行推理。</li><br><br>                                </ul> |
| RTSP 源：rtspsrc | <ul class="ul" id="gst-ai-object-detection__ul_vsj_2r4_tbc"><br>                                    <li class="li">使用 rtspsrc 采集 RTSP 流，然后使用 rtph264depay 进行视频提取。</li><br><br>                                    <li class="li">使用 tee 拆分流进行推理。</li><br><br>                                </ul> |
| h264parse | 渲染 H.264 视频。 |
| [v4l2h264dec](https://docs.qualcomm.com/doc/80-70018-50SC/topic/v4l2h264dec.html) | 解码视频 |
| [qtimlvconverter](https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtimlvconverter.html) | <ol class="ol" id="gst-ai-object-detection__ol_j34_ddg_q1c"><br>                                    <li class="li">在其接收端口上接收视频流。</li><br><br>                                    <li class="li">对流数据执行以下预处理。当模型需要浮点值作为输入时，会执行此预处理。<ol class="ol" type="a" id="gst-ai-object-detection__ol_m5z_cpr_lbc"><br>                                            <li class="li">颜色转换</li><br><br>                                            <li class="li">缩放（放大或缩小）</li><br><br>                                            <li class="li">归一化</li><br><br>                                        </ol><br></li><br><br>                                    <li class="li">将预处理的视频流转换为其发送端口上的张量数据流。 </li><br><br>                                </ol><br><br>                                <br>张量数据流用于 pipeline 后期的推理。 |
| 推理插件：<ul class="ul" id="gst-ai-object-detection__ul_k3l_35k_pdc"><br>                                    <li class="li"><a href="https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtimlsnpe.html">qtimlsnpe</a></li><br><br>                                    <li class="li"><a href="https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtimltflite.html">qtimltflite</a></li><br><br>                                    <li class="li"><a href="https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtimlqnn.html">qtimlqnn</a></li><br><br>                                </ul> | <ol class="ol" id="gst-ai-object-detection__ol_l2x_zjq_nbc"><br>                                    <li class="li">推理 runtime 在其接收端口上接收到张量数据后，会运行推理。</li><br><br>                                    <li class="li">生成一个张量数据流，并在其发送端口上显示推理结果。</li><br><br>                                </ol> |
| [qtimlvdetection](https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtimlvdetection.html) | 处理来自任何目标检测模型的推理结果。<ol class="ol" id="gst-ai-object-detection__ol_ol3_dky_kbc"><br>                                    <li class="li">将阈值应用于所选结果数。</li><br><br>                                    <li class="li">加载 YOLO（YOLOv5、YOLOv8 或 YOLO-NAS）模块。</li><br><br>                                    <li class="li">生成包含可叠加在目标对象上的边框的视频帧。 </li><br><br>                                    <li class="li">将这些处理后的帧发送到 qtivcomposer 的接收端口。</li><br><br>                                </ol> |
| [qtivcomposer](https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtivcomposer.html) | <ol class="ol" id="gst-ai-object-detection__ol_dmb_2vr_lbc"><br>                                    <li class="li">将接收端口获取的内容组成帧。</li><br><br>                                    <li class="li">将包含这些组合帧的 GStreamer 缓存推送到其发送端口。</li><br><br>                                </ol> |
| [Waylandsink](https://docs.qualcomm.com/doc/80-70018-50SC/topic/waylandsink.html) | <ol class="ol" id="gst-ai-object-detection__ol_kjr_fvr_lbc"><br>                                    <li class="li">Waylandsink 将其接收端口上接收的视频流提交给 Weston。</li><br><br>                                    <li class="li">Weston 在本地显示器上渲染视频流。</li><br><br>                                </ol> |

## Config JSON 字段说明

Table : 字段说明 – config_detection.json 文件

| 字段 | 值/描述 |
| :--- | :--- |
| **ml-framework** | 请使用以下模型之一：<ul class="ul" id="gst-ai-object-detection__ul_prm_gck_32c"><br>                                    <li class="li"><code class="ph codeph">snpe</code>–Qualcomm Neural Processing SDK</li><br><br>                                    <li class="li"><code class="ph codeph">tflite</code>–LiteRT</li><br><br>                                    <li class="li"><code class="ph codeph">qnn</code>–Qualcomm AI Engine direct</li><br><br>                                </ul> |
| **yolo-model-type** | 分别运行 `yolov5`、`yolov8` 和<br>                                    `yolonas` 模型。参见[示例模型和标签文件](https://docs.qualcomm.com/doc/80-70018-50SC/topic/gst-ai-object-detection.html#gst-ai-object-detection__section_ohr_1qq_32c)。 |
| **runtime** | 请使用以下 runtime 之一：<ul class="ul" id="gst-ai-object-detection__ul_mry_nck_32c"><br>                                    <li class="li"><code class="ph codeph">cpu</code></li><br><br>                                    <li class="li"><code class="ph codeph">gpu</code></li><br><br>                                    <li class="li"><code class="ph codeph">dsp</code></li><br><br>                                </ul> |
| **Input source** | 请使用以下输入源之一：<ul class="ul" id="gst-ai-object-detection__ul_xym_rck_32c"><br>                                    <li class="li"><code class="ph codeph">camera</code> - 主 (0) 或辅助 (1)。</li><br><br>                                    <li class="li"><code class="ph codeph">file-path</code> - 视频文件目录的路径。</li><br><br>                                    <li class="li"><code class="ph codeph">rtsp-ip-port</code> - RTSP 流的地址：<u class="ph u"><var class="keyword varname">rtsp://&lt;ip&gt;:&lt;port&gt;/&lt;stream&gt;</var></u></li><br><br>                                </ul> |

## 已知问题

AI Hub YOLOv8 和 YOLO-NAS AI Engine direct SDK 模型不支持。这些模型将在未来的版本中更新。

**Parent Topic:** [运行 AI/ML 示例应用程序](https://docs.qualcomm.com/doc/80-70018-50SC/topic/ai-ml-sample-applications.html)

**Related Resources**  

- [使用 LiteRT 进行目标检测和显示](https://docs.qualcomm.com/doc/80-70018-50SC/topic/single-camera-stream-with-object-detection-and-display.html)
- [使用 LiteRT 进行目标检测和编码](https://docs.qualcomm.com/doc/80-70018-50SC/topic/single-camera-stream-with-object-detection-and-encode.html)
- [使用 Neural Processing SDK 进行目标检测和显示](https://docs.qualcomm.com/doc/80-70018-50SC/topic/single-camera-stream-with-object-detection-and-display-with-mobilenet-v2-ssd.html)
- [使用 Neural Processing SDK 进行目标检测和编码](https://docs.qualcomm.com/doc/80-70018-50SC/topic/single-camera-stream-with-object-detection-and-encode-with-mobilenet-v2-ssd.html)

Last Published: Nov 12, 2025

[Previous Topic
图像分类](https://docs.qualcomm.com/bundle/publicresource/80-70018-50SC/topics/gst-ai-classification.md) [Next Topic
姿态检测](https://docs.qualcomm.com/bundle/publicresource/80-70018-50SC/topics/gst-ai-pose-detection.md)