# 从摄像头到 RTSP 的单流，带 ML 检测
Source: [https://docs.qualcomm.com/doc/80-70020-50SC/topic/single-stream-from-camera-to-rtsp-with-ml-detection.html](https://docs.qualcomm.com/doc/80-70020-50SC/topic/single-stream-from-camera-to-rtsp-with-ml-detection.html)
在媒体播放器（例如 VLC）上通过 RTSP 播放来自摄像头的流。
- 从摄像头到 RTSP 的单流：
Figure : 摄像头至 RTSP 的 pipeline
gst-launch-1.0 -e qtiqmmfsrc ! video/x-raw,format=NV12_Q08C,width=1920,height=1080,framerate=30/1 ! \
v4l2h264enc capture-io-mode=4 output-io-mode=5 ! queue ! h264parse config-interval=1 ! queue ! qtirtspbin address= port=Copy to clipboard
连接至流。关于更多详细信息，请参阅[在主机上查看 RTSP 流](https://docs.qualcomm.com/doc/80-70020-50SC/topic/camera-and-video-encode.html#one_stream_1080p_avc_rtsp_from_live_source__section_ayq_2nh_pyb)。
- 从摄像头到 RTSP 的单流，带 ML 检测元流：
Figure : 具有 ML 检测功能的摄像头到 RTSP 的 pipeline
Figure : 使用 RTSP 源进行预览
在控制台 1 中：
gst-launch-1.0 -e qtiqmmfsrc ! video/x-raw,format=NV12,width=1920,height=1080,framerate=30/1 ! queue ! tee name=split \
split. ! queue ! qtivcomposer name=mixer ! queue ! v4l2h264enc capture-io-mode=4 output-io-mode=5 ! queue ! h264parse config-interval=-1 ! queue ! \
qtirtspbin address= port= \
split. ! queue ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/etc/models/yolov8_det_quantized.tflite ! queue ! \
qtimlvdetection threshold=70.0 results=5 module=yolov8 labels=/etc/labels/yolov8.labels \
constants="yolov8,q-offsets=<21.0, 0.0, 0.0>,q-scales=<3.0546178817749023, 0.003793874057009816, 1.0>;" ! video/x-raw,format=BGRA,width=640,height=360 ! queue ! mixer.Copy to clipboard
## 相关信息
[qtirtspbin](https://docs.qualcomm.com/doc/80-70020-50SC/topic/qtirtspbin.html)
**Parent Topic:** [LiteRT 用例](https://docs.qualcomm.com/doc/80-70020-50SC/topic/tensorflow-lite-use-cases.html)
Last Published: Jul 23, 2025
[Previous Topic
使用 LiteRT 进行视频超分辨率和显示](https://docs.qualcomm.com/bundle/publicresource/80-70020-50SC/topics/video-super-resolution-and-display-with-litert.md) [Next Topic
Qualcomm Neural Processing SDK 用例](https://docs.qualcomm.com/bundle/publicresource/80-70020-50SC/topics/qualcomm-neural-processing-sdk-use-cases.md)