# 对视频帧应用语义分割

在为某个模型运行 pipeline 命令之前，请遵循所需的[先决条件](https://docs.qualcomm.com/doc/80-70018-15BY/topic/ai-hub-qualcomm-im-sdk.html#prerequisites)。

运行以下命令以确保在连接的显示器上显示结果：

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

## DeepLabV3-Plus\_MobileNet-Quantized

DeepLabV3 Quantized 专为多尺度语义分割而设计，并在各种数据集上进行了训练。

AI Hub 模型基于 [DeepLabV3-Plus-MobileNet-Quantized 的实现](https://github.com/jfzhang95/pytorch-deeplab-xception)。

- 模型：[deeplabv3_plus_mobilenet_quantized.tflite](https://aihub.qualcomm.com/iot/models/deeplabv3_plus_mobilenet_quantized)
- 标签：[voc_labels.txt](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/labels/voc_labels.txt)

gst-launch-1.0 -e --gst-debug=2 \
    filesrc location=/etc/media/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! tee name=split \
    split. ! queue ! qtivcomposer name=mixer sink_1::alpha=0.5 ! queue ! waylandsink sync=true fullscreen=true \
    split. ! queue ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
    external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/etc/models/deeplabv3_plus_mobilenet_quantized.tflite ! queue ! \
    qtimlvsegmentation module=deeplab-argmax labels=/etc/labels/voc_labels.txt \
    constants="deeplab,q-offsets=<92.0>,q-scales=<0.04518842324614525>;" ! video/x-raw,format=BGRA,width=256,height=144 ! queue ! mixer.
    Copy to clipboard

## FCN-Resnet50-Quantized

FCN\_ResNet50 是一种量化机器学习模型，可以从 COCO 数据集中分割图像。

AI Hub 模型基于 [FCN-ResNet50-Quantized 的实现](https://github.com/pytorch/vision/blob/main/torchvision/models/segmentation/fcn.py)。

- 模型：[FCN-ResNet50-Quantized.tflite](https://aihub.qualcomm.com/iot/models/fcn_resnet50_quantized)
- 标签：[voc_labels.txt](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/labels/voc_labels.txt)

Note

QCS6490 目前不支持此 pipeline。

gst-launch-1.0 -e --gst-debug=2 \
    filesrc location=/etc/media/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! tee name=split \
    split. ! queue ! qtivcomposer name=mixer sink_1::alpha=0.5 ! queue ! waylandsink sync=true fullscreen=true \
    split. ! queue ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
    external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/etc/models/fcn_resnet50_quantized.tflite ! queue ! \
    qtimlvsegmentation module=deeplab-argmax labels=/etc/labels/voc_labels.txt \
    constants="deeplab,q-offsets=<0.0>,q-scales=<1.0>;" ! video/x-raw,format=BGRA,width=256,height=144 ! queue ! mixer.
    Copy to clipboard

## FFNet-40S-Quantized

FFNet-40S-Quantized 是一种“无感配网”，它使用道路、人行道和行人等像素类别对街景图像进行分割。

它是在城市景观数据集上进行训练的。

AI Hub 模型基于 [FFNet-40S-Quantized 的这种实现](https://github.com/Qualcomm-AI-research/FFNet)

- 模型：[ffnet_40s_quantized.tflite](https://aihub.qualcomm.com/iot/models/ffnet_40s_quantized)
- 标签：[voc_labels.txt](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/labels/voc_labels.txt)

gst-launch-1.0 -e --gst-debug=2 \
    filesrc location=/etc/media/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! tee name=split \
    split. ! queue ! qtivcomposer name=mixer sink_1::alpha=0.5 ! queue ! waylandsink sync=false fullscreen=true \
    split. ! queue ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
    external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/etc/models/ffnet_40s_quantized.tflite ! queue ! \
    qtimlvsegmentation module=deeplab-argmax labels=/etc/labels/voc_labels.txt constants="ffnet,q-offsets=<178.0>,q-scales=<0.31378185749053955>;" ! \
    video/x-raw,format=BGRA,width=256,height=144 ! queue ! mixer.
    Copy to clipboard

## FFNet-54S-Quantized

FFNet-54S-Quantized 是一种“无感配网”，它使用道路、人行道和行人等像素类别对街景图像进行细分。

它是在城市景观数据集上进行训练的。

AI Hub 模型基于 [FFNet-54S-Quantized 的这种实现](https://github.com/Qualcomm-AI-research/FFNet)。

- 模型：[ffnet_54s_quantized.tflite](https://aihub.qualcomm.com/iot/models/ffnet_54s_quantized)
- 标签：[voc_labels.txt](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/labels/voc_labels.txt)

gst-launch-1.0 -e --gst-debug=2 \
    filesrc location=/etc/media/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! tee name=split \
    split. ! queue ! qtivcomposer name=mixer sink_1::alpha=0.5 ! queue ! waylandsink sync=false fullscreen=true \
    split. ! queue ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
    external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/etc/models/ffnet_54s_quantized.tflite ! queue ! \
    qtimlvsegmentation module=deeplab-argmax labels=/etc/labels/voc_labels.txt constants="ffnet,q-offsets=<178.0>,q-scales=<0.2929433584213257>;" ! \
    video/x-raw,format=BGRA,width=256,height=144 ! queue ! mixer.
    Copy to clipboard

## FFNet-78S-Quantized

FFNet-78S-Quantized 是一种“无感配网”，它使用道路、人行道和行人等像素类别对街景图像进行细分。

它是在城市景观数据集上进行训练的。

AI Hub 模型基于 [FFNet-78S-Quantized 的这种实现](https://github.com/Qualcomm-AI-research/FFNet)。

- 模型：[ffnet_78s_quantized.tflite](https://aihub.qualcomm.com/iot/models/ffnet_78s_quantized)
- 标签：[voc_labels.txt](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/labels/voc_labels.txt)

gst-launch-1.0 -e --gst-debug=2 \
    filesrc location=/etc/media/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! tee name=split \
    split. ! queue ! qtivcomposer name=mixer sink_1::alpha=0.5 ! queue ! waylandsink sync=false fullscreen=true \
    split. ! queue ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
    external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/etc/models/ffnet_78s_quantized.tflite ! queue ! \
    qtimlvsegmentation module=deeplab-argmax labels=/etc/labels/voc_labels.txt constants="ffnet,q-offsets=<171.0>,q-scales=<0.3849360942840576>;" ! \
    video/x-raw,format=BGRA,width=256,height=144 ! queue ! mixer.
    Copy to clipboard

Last Published: Oct 23, 2025

[Previous Topic
检测对象](https://docs.qualcomm.com/bundle/publicresource/80-70018-15BY/topics/object-detection.md) [Next Topic
使用超分辨率对图像进行放大](https://docs.qualcomm.com/bundle/publicresource/80-70018-15BY/topics/super-resolution.md)