# 使用 LiteRT 进行图像分类和编码

Source: [https://docs.qualcomm.com/doc/80-70018-50SC/topic/single-camera-stream-with-image-classification-and-encode.html](https://docs.qualcomm.com/doc/80-70018-50SC/topic/single-camera-stream-with-image-classification-and-encode.html)

这些用例使用 InceptionV3 LiteRT 模型对单个摄像头流中的场景进行分类，并覆盖或组合分类标签，然后对流进行编码。

## 使用 qtivoverlay 插件来应用分类叠加

运行用例：

    gst-launch-1.0 -e qtiqmmfsrc name=camsrc ! video/x-raw,format=NV12_Q08C,width=1280,height=720,framerate=30/1 ! queue ! tee name=split split. ! \
    queue ! qtimetamux name=metamux ! queue ! qtivoverlay ! queue ! v4l2h264enc capture-io-mode=4 output-io-mode=5 ! \
    h264parse ! queue ! mp4mux ! queue ! filesink location=/etc/media/video.mp4 split. ! queue ! qtimlvconverter ! queue ! \
    qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp;" \
    model=/etc/models/inception_v3_quantized.tflite ! queue ! qtimlvclassification threshold=40.0 results=2 module=mobilenet \
    labels=/etc/labels/classification.labels constants="Inceptionv3,q-offsets=<38.0>,q-scales=<0.17039915919303894>;" ! text/x-raw ! queue ! metamux.Copy to clipboard

要停止用例，请按 CTRL + C。

Figure : 分类叠加和编码的 pipeline
                
                ![](data:image/png;base64,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)

下图显示了用例执行流程：

1. 识别从摄像头源传来的数据流。
2. 使用 overlaylib 叠加分类标签。
3. 将数据流编码为 H.264 码流。
4. 多路复用 MP4 容器中的数据流并将其存储为 MP4 文件。

pipeline 执行的顺序处理阶段如下表所示：

| 处理过程 | 说明 |
| --- | --- |
| [qtiqmmfsrc](https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtiqmmfsrc.html) | <ol class="ol"><br>                                    <li class="li">视频流从摄像头源插件收集，并创建两个副本：<ul class="ul" id="single-camera-stream-with-image-classification-and-encode__ol_kh3_dyv_r1c"><br>                                            <li class="li">一个视频流被发送至 qtimetamux 插件，以保留视频流。</li><br><br>                                            <li class="li">另一个视频流被发送到 ML 推理 pipeline。</li><br><br>                                        </ul><br></li><br><br>                                </ol> |
| **预处理** | **预处理** |
| [qtimlvconverter](https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtimlvconverter.html) | <ol class="ol" id="single-camera-stream-with-image-classification-and-encode__ol_xsf_q5l_vbc"><br>                                    <li class="li">在其接收端口上接收视频流。</li><br><br>                                    <li class="li">执行预处理：<ul class="ul" id="single-camera-stream-with-image-classification-and-encode__ul_ff2_twl_vbc"><br>                                            <li class="li">颜色转换</li><br><br>                                            <li class="li">缩小/放大</li><br><br>                                            <li class="li">在模型需要浮点值作为输入时，对流数据进行归一化</li><br><br>                                        </ul><br></li><br><br>                                    <li class="li">在其发送端口上将视频流转换为张量数据。<p class="p">分类模型使用此张量数据进行推理。</p><br></li><br><br>                                </ol> |
| **推理** | **推理** |
| [qtimltflite](https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtimltflite.html) | <ol class="ol" id="single-camera-stream-with-image-classification-and-encode__ol_bwn_s5l_vbc"><br>                                    <li class="li">加载分类模型。</li><br><br>                                    <li class="li">为选择的 delegate 修改图。</li><br><br>                                    <li class="li">在其接收端口上接收张量数据。</li><br><br>                                    <li class="li">执行推理并在其发送端口上生成包含推理结果的张量数据。</li><br><br>                                </ol> |
| **后处理** | **后处理** |
| [qtimlvclassification](https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtimlvclassification.html) | <ol class="ol" id="single-camera-stream-with-image-classification-and-encode__ol_gr1_w5l_vbc"><br>                                    <li class="li">从其接收端口上的分类模型接收推理张量。</li><br><br>                                    <li class="li">将张量转换为多媒体插件稍后可以处理的视频或文本等格式。 </li><br><br>                                    <li class="li">将阈值应用于所选的结果数。</li><br><br>                                    <li class="li">加载分类模型的相应模块。 <p class="p">在此用例中，qtimlvclassification 执行以下操作：</p><ol class="ol" type="a" id="single-camera-stream-with-image-classification-and-encode__ol_rrb_1xl_vbc"><br>                                            <li class="li">加载 InceptionV3 子模块。</li><br><br>                                            <li class="li">将结果生成为文本结构。</li><br><br>                                            <li class="li">接着发送到 qtimetamux 的接收端口。</li><br><br>                                        </ol><br></li><br><br>                                </ol> |
| [qtimetamux](https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtimetamux.html) | <ol class="ol" id="single-camera-stream-with-image-classification-and-encode__ol_ll3_x5l_vbc"><br>                                    <li class="li">在接收端口上接收视频流和文本流，以及与视频流相对应的分类结果。</li><br><br>                                    <li class="li">在其接收端口上生成包含视频流内容的 GST 缓存。</li><br><br>                                    <li class="li">将数据接收端口上的分类结果添加到其发送端上的 GST 缓存元数据（元数据复用）。</li><br><br>                                </ol> |
| [qtivoverlay](https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtioverlay.html) | <ol class="ol" id="single-camera-stream-with-image-classification-and-encode__ol_wst_y5l_vbc"><br>                                    <li class="li">接收多路复用流。</li><br><br>                                    <li class="li">使用 CL 将分类标签叠加在 VideoFrame 上。 </li><br><br>                                    <li class="li">在其发送端口上生成带有叠加层的 GST 缓存。</li><br><br>                                </ol> |
| [v4l2h264enc](https://docs.qualcomm.com/doc/80-70018-50SC/topic/v4l2h264enc.html) | <ol class="ol"><br>                                    <li class="li">将参数应用于在接收端口上接收到的视频流的每一帧。</li><br><br>                                    <li class="li">将其编码为码流，并通过其发送端口发送。</li><br><br>                                </ol> |
| h264parse | 向 GStreamer 缓存元数据添加更多码流信息。 |
| mp4mux | 接收这些缓存并创建具有格式规范缓存的容器。 |
| **输出** | **输出** |
| Filesink | 将生成的数据流存储在 /opt/video.mp4 文件中。 |
| 播放 | 从主机拉取 video.mp4 并在媒体播放器上播放：<br>`scp root@<IP address of<br>                                        target device>:/opt/ <destination<br>                                directory>` |

## 使用 qtivcomposer 混合原始帧与分类掩码

运行用例：

    gst-launch-1.0 -e --gst-debug=2 qtiqmmfsrc name=camsrc ! video/x-raw,format=NV12_Q08C,width=1280,height=720,framerate=30/1 ! queue ! tee name=split split. ! \
    queue ! qtivcomposer name=mixer sink_1::position="<30, 30>" sink_1::dimensions="<320, 180>" ! queue ! video/x-raw,format=NV12,width=1920,height=1080,interlace-mode=progressive,colorimetry=bt601 ! \
    v4l2h264enc capture-io-mode=4 output-io-mode=5 ! h264parse ! queue ! mp4mux ! queue ! filesink location=/etc/media/video.mp4 split. ! queue ! qtimlvconverter ! queue ! \
    qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp;" \
    model=/etc/models/inception_v3_quantized.tflite ! queue ! qtimlvclassification threshold=40.0 results=2 module=mobilenet \
    labels=/etc/labels/classification.labels constants="Inceptionv3,q-offsets=<38.0>,q-scales=<0.17039915919303894>;" ! video/x-raw,format=BGRA,width=640,height=360 ! queue ! mixer.Copy to clipboard

要停止用例，请按 CTRL + C。

Figure : 使用 qtivcomposer 进行分类和编码的 pipeline
                
                ![](data:image/png;base64,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)

下图显示了用例执行流程：

1. 识别从摄像头源传来的数据流。
2. 使用 qtivcomposer 合成分类标签和视频流。
3. 将数据流编码为 H.264 码流。
4. 多路复用 MP4 容器中的数据流并将其存储为 MP4 文件。

pipeline 执行的顺序处理阶段如下表所示：

| 处理过程 | 说明 |
| --- | --- |
| [qtiqmmfsrc](https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtiqmmfsrc.html) | <ol class="ol" id="single-camera-stream-with-image-classification-and-encode__ol_l2f_zgm_vbc"><br>                                    <li class="li">从摄像头采集视频流（源）并创建源的两个副本：<ul class="ul" id="single-camera-stream-with-image-classification-and-encode__ol_m2f_zgm_vbc"><br>                                            <li class="li">一个视频流被发送至 qtimetamux 插件，以保留视频流。</li><br><br>                                            <li class="li">另一个视频流被发送到 ML 推理 pipeline。</li><br><br>                                        </ul><br></li><br><br>                                </ol> |
| **预处理** | **预处理** |
| [qtimlvconverter](https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtimlvconverter.html) | <ol class="ol" id="single-camera-stream-with-image-classification-and-encode__ol_t2f_zgm_vbc"><br>                                    <li class="li">在其接收端口上接收视频流。</li><br><br>                                    <li class="li">执行预处理：<ul class="ul" id="single-camera-stream-with-image-classification-and-encode__ul_u2f_zgm_vbc"><br>                                            <li class="li">颜色转换</li><br><br>                                            <li class="li">缩小/放大</li><br><br>                                            <li class="li">当模型期望浮点值作为输入时对流数据进行标准化</li><br><br>                                        </ul><br></li><br><br>                                    <li class="li">在其发送端口上将视频流转换为张量数据。<p class="p">分类模型使用此张量数据进行推理。</p><br></li><br><br>                                </ol> |
| **推理** | **推理** |
| [qtimltflite](https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtimltflite.html) | <ol class="ol" id="single-camera-stream-with-image-classification-and-encode__ol_v2f_zgm_vbc"><br>                                    <li class="li">加载分类模型。</li><br><br>                                    <li class="li">为选择的 delegate 修改图。</li><br><br>                                    <li class="li">在其接收端口上接收张量数据。</li><br><br>                                    <li class="li">执行推理并在其发送端口上生成包含推理结果的张量数据。</li><br><br>                                </ol> |
| **后处理** | **后处理** |
| [qtimlvclassification](https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtimlvclassification.html) | <ol class="ol" id="single-camera-stream-with-image-classification-and-encode__ol_w2f_zgm_vbc"><br>                                    <li class="li">从其接收端口上的分类模型接收推理张量。</li><br><br>                                    <li class="li">将张量转换为多媒体插件稍后可以处理的视频或文本等格式。</li><br><br>                                    <li class="li">将阈值应用于所选的结果数。</li><br><br>                                    <li class="li">加载分类模型的相应模块。 <p class="p">在此用例中，qtimlvclassification 执行以下操作：</p><ol class="ol" type="a" id="single-camera-stream-with-image-classification-and-encode__ol_x2f_zgm_vbc"><br>                                            <li class="li">加载 InceptionV3 子模块。</li><br><br>                                            <li class="li">将结果生成为带有分类标签的视频帧。</li><br><br>                                            <li class="li">将它们发送至 qtivcomposer 的接收端口。</li><br><br>                                        </ol><br></li><br><br>                                </ol> |
| [qtivcomposer](https://docs.qualcomm.com/doc/80-70018-50SC/topic/qtivcomposer.html) | <ol class="ol" id="single-camera-stream-with-image-classification-and-encode__ol_nmc_lxl_vbc"><br>                                    <li class="li">在接收端口上接收原始视频流和分类结果。 </li><br><br>                                    <li class="li">在其发送端口上生成 GST 缓存，其内容由来自其接收端的视频流组成。</li><br><br>                                </ol> |
| [v4l2h264enc](https://docs.qualcomm.com/doc/80-70018-50SC/topic/v4l2h264enc.html) | <ol class="ol" id="single-camera-stream-with-image-classification-and-encode__ol_aff_zgm_vbc"><br>                                    <li class="li">将参数应用于在接收端口上接收到的视频流的每一帧。</li><br><br>                                    <li class="li">将其编码为码流，并通过其发送端口发送。</li><br><br>                                </ol> |
| h264parse | 向 GStreamer 缓存元数据添加更多码流信息。 |
| mp4mux | 接收这些缓存并创建具有格式规范缓存的容器。 |
| **输出** | **输出** |
| Filesink | 将生成的数据流存储在 /etc/media/video.mp4 文件中。 |
| Playback | 从主机拉取 video.mp4 并在媒体播放器上播放：<br>`scp root@<IP address of<br>                                        target device>:/etc/ <destination<br>                                directory>` |

**Parent Topic:** [LiteRT 用例](https://docs.qualcomm.com/doc/80-70018-50SC/topic/tensorflow-lite-use-cases.html)

Last Published: Nov 12, 2025

[Previous Topic
使用 LiteRT 进行图像分类和显示](https://docs.qualcomm.com/bundle/publicresource/80-70018-50SC/topics/single-camera-stream-with-image-classification-and-display.md) [Next Topic
使用 LiteRT 进行音频分类解码与显示](https://docs.qualcomm.com/bundle/publicresource/80-70018-50SC/topics/audio-classification-with-litert.md)