# 示例应用程序

Source: [https://docs.qualcomm.com/doc/80-70022-50SC/topic/example-applications.html](https://docs.qualcomm.com/doc/80-70022-50SC/topic/example-applications.html)

Qualcomm IM SDK 包含示例应用程序，可让您体验 AI/ML 和多媒体功能。此外，基于 Python 的示例应用程序可用于常见用例。这些应用程序可作为在 Qualcomm Linux 和 Ubuntu Server 上运行自定义用例的参考。

Important: 
                
- 确保主机使用 Ubuntu 22.04。
- 针对 Qualcomm Linux 1.6 或 Ubuntu Server，可参见[开始使用 Qualcomm IM SDK](https://docs.qualcomm.com/bundle/publicresource/topics/80-70022-51/install-sdk.html)。
- 本文档包含您必须在 Linux 主机或 Qualcomm Dragonwing^™^ 开发套件（也称为目标设备）上调用的命令：

    - **在目标设备的终端中**：指您必须在目标设备内部运行的命令
    - **在主机的终端中**：指您必须在 Linux 主机上运行的命令
- 本指南中的示例应用程序和 AI 程序兼容 Qualcomm AI^®^ Runtime SDK v2.38 和 LiteRT（或 TFLite）v2.16.1。在开始 AI/ML 开发之前，请确保将匹配的 SDK 下载到主机。

Note:
- 本指南不适用于 Qualcomm Dragonwing^TM^ IQ-615。
- 有关新功能、示例应用程序、已解决问题和局限性的信息，请参阅 [Qualcomm Intelligent Multimedia (IM SDK) Release Notes](https://docs.qualcomm.com/bundle/publicresource/topics/80-70022-52/qim-sdk-release-1-6.html)。

使用以下示例应用程序运行与零售、AI Edge Box、IP 摄像头、无人机和机器人相关的不同用例。

- AI/ML 应用程序重点关注 AI 和 ML 功能。
- 多媒体应用程序使用摄像头、视频和音频功能。
- 基于 Python 的应用程序使用 Python 运行 AI/ML 和多媒体用例。关于更多详细信息，请参阅[运行基于 Python 的应用程序](https://docs.qualcomm.com/doc/80-70022-50SC/topic/python-sample-applications.html)。

要使用基于 GUI 的应用程序运行 AI/ML 和多媒体示例应用程序（无需任何主机设置），请参阅[使用 Qdemo 运行示例应用程序](https://docs.qualcomm.com/bundle/publicresource/topics/80-70022-253/run-sample-apps-qdemo.html#run-sample-applications-using-qdemo)。

## AI/ML 示例应用程序

| 应用程序 | CodeLinaro Git - 源代码路径 | 说明 | QCS6490 | Qualcomm Dragonwing^™^IQ-8275 | Qualcomm Dragonwing^™^IQ-9075 |
| --- | --- | --- | --- | --- | --- |
| [图像分类](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-ai-classification.html) | [gst-ai-classification](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-classification?ref_type=heads) | 对来自摄像头、文件源或实时流协议 (RTSP) 的流执行分类。 | ✔ | ✔ | ✔ |
| [目标检测](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-ai-object-detection.html) | [gst-ai-object-detection](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-object-detection?ref_type=heads) | 对来自摄像头、文件源或 RTSP 的流执行目标检测。 | ✔ | ✔ | ✔ |
| [姿态检测](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-ai-pose-detection.html) | [gst-ai-pose-detection](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r1-rel/gst-sample-apps/gst-ai-pose-detection?ref_type=heads) | 对来自摄像头、文件源或 RTSP 的流执行姿态检测。 | ✔ | ✔ | ✔ |
| [图像分割](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-ai-segmentation.html) | [gst-ai-segmentation](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-segmentation?ref_type=heads) | 对来自摄像头、文件源或 RTSP 的流执行图像分割。 | ✔ | ✔ | ✔ |
| [并行推理](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-ai-parallel-inference.html) | [gst-ai-parallel-inference](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-parallel-inference?ref_type=heads) | 多个 AI/ML 模型在来自摄像头、文件源或 RTSP 的流上并行运行。 | ✔ | ✔ | ✔ |
| [多输入/输出目标检测](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-ai-multi-input-output-object-detection.html) | [gst-ai-multi-input-output-object-detection](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-multi-input-output-object-detection?ref_type=heads) | Edge AI 盒子的用例，其通过摄像头、文件源或 RTSP 等多个源提供输入。 | ✔ | ✔ | ✔ |
| [菊花链检测与分类](https://docs.qualcomm.com/doc/80-70022-50SC/topic/daisy-chain-detection-and-classification.html) | [gst-ai-daisychain-detection-classification](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-daisychain-detection-classification?ref_type=heads) | 对从多个来源（例如摄像头、文件源或 RTSP）的流传输的图像执行级联目标检测和分类。 | ✔ | ✔ | ✔ |
| [菊花链检测和姿态估计](https://docs.qualcomm.com/doc/80-70022-50SC/topic/daisy-chain-detection-and-pose-detection.html) | [gst-ai-daisychain-detection-pose](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-daisychain-detection-pose?ref_type=heads) | 对来自多个源（例如摄像头、文件源或 RTSP）的流执行级联目标检测和姿态检测。 | ✔ | ✔ | ✔ |
| [视频单目深度估计](https://docs.qualcomm.com/doc/80-70022-50SC/topic/mono-depth-from-video.html) | [gst-ai-monodepth](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-monodepth?ref_type=heads) | 对来自摄像头、文件源或 RTSP 流的图像执行单目深度估计。 | ✔ | ✔ | ✔ |
| [视频超分辨率](https://docs.qualcomm.com/doc/80-70022-50SC/topic/video-super-resolution.html) | [gst-ai-superresolution](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-superresolution?ref_type=heads) | 使用低分辨率输入源生成高分辨率视频帧。 | ✔ | ✔ | ✔ |
| [多流推理](https://docs.qualcomm.com/doc/80-70022-50SC/topic/multistream-inference.html) | [gst-ai-multistream-inference](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-multistream-inference?ref_type=heads) | 对来自摄像头、文件源或 RTSP 等多个来源的流执行 AI 推理（目标检测和分类）。 | ✔ | ✔ | ✔ |
| [多流批量推理](https://docs.qualcomm.com/doc/80-70022-50SC/topic/multistream-batch-inference.html)（Alpha 发布版本） | [gst-ai-multistream-batch-inference](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-multistream-batch-inference?ref_type=heads) | 对文件源输入执行批量 AI 推理（目标检测和分割）。 | ✔ | ✔ | ✔ |
| [AI 智能 codec](https://docs.qualcomm.com/doc/80-70022-50SC/topic/ai-smart-codec.html) | [gst-ai-smartcodec-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-smartcodec-example?ref_type=heads) | 对来自摄像头或文件源的输入流减少其网络带宽或存储空间。 | ✔ | ✔ | ✔ |
| [人脸检测](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-ai-face-detection.html) | [gst-ai-face-detection](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-face-detection?ref_type=heads) | 从摄像头、文件或 RTSP 流获取输入，并使用 Qualcomm® AI Hub 检测模型生成预览。 | ✔ | ✔ | ✔ |
| [人脸识别](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-ai-face-recognition.html) | [gst-ai-face-recognition](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-face-recognition?ref_type=heads) | 从摄像头或 RTSP 流获取输入以进行人脸识别。 | ✔ | ✔ | ✔ |
| [音频分类](https://docs.qualcomm.com/doc/80-70022-50SC/topic/audio-classification.html) | [gst-ai-audio-classification](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-audio-classification?ref_type=heads) | 对音频源的流进行分类 | ✔ | ✔ | ✔ |
| [元数据解析](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-ai-metadata-parser.html) | [gst-ai-metadata-parser-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-metadata-parser-example?ref_type=heads) | 使用 appsink 插件解析来自摄像头、文件或 RTSP 源流的元数据。此外，它还能提供流中的人数统计。 | ✔ | ✔ | ✔ |
| [AI USB 摄像头](https://docs.qualcomm.com/doc/80-70022-50SC/topic/ai-usb-camera.html) | [gst-ai-usb-camera-app](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-usb-camera-app?ref_type=heads) | USB 单摄像头流传输，用于预览、视频编码器或网络 (RTSP)，以及目标检测和预览。 | ✔ | ✔ | ✔ |
| [使用 Python 和容器进行图像分割](https://docs.qualcomm.com/doc/80-70022-50SC/topic/image-segmentation-using-python.html)（Alpha 发布版本） | [snpe_segmentation_app.py](https://git.codelinaro.org/clo/le/sdk-tools/-/blob/imsdk-tools.lnx.1.0/snpe-container-python/src/python/snpe/test_snpe/snpe_segmentation_app.py?ref_type=heads) | 使用来自 Docker 的 python 绑定进行分段。 | ✔ | ✔ | ✔ |
| [硬件基准测试应用程序](https://docs.qualcomm.com/doc/80-70022-50SC/topic/vision_ai_demo_app.html) | [QCS6490-Vision-AI-Demo](https://github.com/Avnet/QCS6490-Vision-AI-Demo/tree/QLI-1.5-and-1080p-support) | 用来监控示例应用程序的硬件占用率的 GUI 应用程序 | ✔ | ✖ | ✖ |
| [AI 事件编码器](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-ai-event-encoder.html) | [gst-ai-event-encoder](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-event-encoder?ref_type=heads) | 识别实时视频流中的人物，并将流编码为 MP4 文件。 | ✔ | ✔ | ✔ |

## 多媒体示例应用程序

| 应用程序 | CodeLinaro Git 源路径 | 说明 | QCS6490 | Dragonwing IQ-8275 | Dragonwing IQ-9075 |
| --- | --- | --- | --- | --- | --- |
| **摄像头应用程序** | **摄像头应用程序** | **摄像头应用程序** | **摄像头应用程序** | **摄像头应用程序** | **摄像头应用程序** |
| [单路摄像头流传输](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-camera-single-stream-example.html) | [gst-camera-single-stream-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-camera-single-stream-example?ref_type=heads) | 用于预览、视频编码器或网络 (RTSP) 的单路摄像头流。 | ✔ | ✔ | ✔ |
| [多摄像头流传输](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-multi-camera-stream-example.html) | [gst-multi-camera-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-multi-camera-example?ref_type=heads) | 来自两个摄像头的并发流。立体声和行车记录仪等用例。 | ✔ | ✔ | ✔ |
| [多个流](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-multi-stream-example.html) | [gst-multi-stream-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-multi-stream-example?ref_type=heads) | 使用 [tee](https://gstreamer.freedesktop.org/documentation/coreelements/tee.html) 将单路摄像头的数据复制到两个流中。 | ✔ | ✔ | ✔ |
| [实时拍照](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-snapshot-stream-example.html) | [gst-snapshot-stream-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-snapshot-stream-example?ref_type=heads) | 生成快照并录制视频。需要基于事件（如入侵警报）执行拍照的监控摄像头等用例。 | ✔ | ✖ | ✖ |
| [RTMP 摄像头流传输](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-rtmp-stream-example.html) | gst-rtmp-stream-example | 将来自 ISP 和 RTSP 源的摄像头信号转换为 RTMP 流。用于安全系统和媒体广播。 | ✔ | ✔ | ✔ |
| [在运行中激活-停用流](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-activate-deactivate-streams-runtime.html) | [gst-activate-deactivate-streams-runtime-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-activate-deactivate-streams-runtime?ref_type=heads) | 即时修改摄像头分辨率，无需重新启动传感器。 | ✔ | ✔ | ✔ |
| [在运行中添加-删除流](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-add-remove-streams-runtime.html) | [gst-add-remove-streams-runtime](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-add-remove-streams-runtime) | 动态添加和移除多个流。 | ✔ | ✔ | ✔ |
| [摄像头帧处理](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-appsink-example.html) | [gst-appsink-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-appsink-example?ref_type=heads) | 在编码之前将变换和其他算法应用于摄像头帧。 | ✔ | ✔ | ✔ |
| [摄像头元数据](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-camera-metadata-example.html) | [gst-camera-metadata-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-camera-metadata-example?ref_type=heads) | 场景模式、白平衡和码率等元数据。用于监控和无人机摄像头的高级成像信息。 | ✔ | ✔ | ✔ |
| [摄像头流配置](https://docs.qualcomm.com/doc/80-70022-50SC/topic/camera-stream-configuration.html) | [gst-add-streams-as-bundle-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-add-streams-as-bundle-example?ref_type=heads) | 将多个摄像头流配置为一个 bundle，从而节省时间。 | ✔ | ✔ | ✔ |
| [摄像头连拍](https://docs.qualcomm.com/doc/80-70022-50SC/topic/camera-burst-capture.html) | [gst-camera-burst-capture-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-camera-burst-capture-example?ref_type=heads) | 在连拍模式下拍照。 | ✔ | ✖ | ✖ |
| [摄像头切换](https://docs.qualcomm.com/doc/80-70022-50SC/topic/camera-switch.html) | [gst-camera-switch-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-camera-switch-example?ref_type=heads) | 在两个摄像头之间切换。 | ✔ | ✔ | ✔ |
| [宽动态范围和电子图像稳定](https://docs.qualcomm.com/doc/80-70022-50SC/topic/dynamic-range-and-image-stabilization.html) | [gst-camera-shdr-ldc-eis-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-camera-shdr-ldc-eis-example?ref_type=heads) | 超高动态范围 (sHDR)、低动态范围 (LDR) 和电子图像稳定 (EIS) 等摄像头成像技术。 | ✔ | ✖ | ✖ |
| [解码 JPEG 图像](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-jpg-decode-example.html) | [gst-jpg-decode-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-jpg-decode-example?ref_type=heads) | 解码 JPEG 图像并在屏幕上预览。 | ✔ | ✔ | ✔ |
| **视频应用程序** | **视频应用程序** | **视频应用程序** | **视频应用程序** | **视频应用程序** | **视频应用程序** |
| [视频墙](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-concurrent-videoplay-composition.html) | [gst-concurrent-videoplay-composition](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-concurrent-videoplay-composition?ref_type=heads) | 在设备上播放合成的多个视频。该用例提供了在零售空间和数字标牌使用视频墙的场景。 | ✔ | ✔ | ✔ |
| [智能 codec](https://docs.qualcomm.com/doc/80-70022-50SC/topic/smart-codec.html) | [gst-smartcodec-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-smartcodec-example?ref_type=heads) | 减少摄像头输入的网络带宽或存储空间。 | ✔ | ✔ | ✔ |
| [多格式编码/解码](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-videocodec-concurrent-playback.html) | [gst-videocodec-concurrent-playback](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-videocodec-concurrent-playback?ref_type=heads) | 并发解码和播放多种格式。这是 AI 盒子和视频会议系统的用例，其以不同格式发送视频输入。 | ✔ | ✔ | ✔ |
| [音视频播放](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-audio-video-playback.html) | [gst-audio-video-playback](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r1-rel/gst-sample-apps/gst-audio-video-playback?ref_type=heads) | 音频和视频播放功能。构建需要音频和视频的不同多媒体产品。 | ✔ | ✔ | ✔ |
| [视频转码](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-video-transcode-example.html) | [gst-video-transcode-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-video-transcode-example?ref_type=heads) | AVC 到 HEVC 或 HEVC 到 AVC 格式的视频转码。 | ✔ | ✔ | ✔ |
| [视频播放](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-video-playback-example.html) | [gst-video-playback-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r1-rel/gst-sample-apps/gst-video-playback-example?ref_type=heads) | 视频文件的解码和播放。 | ✔ | ✔ | ✔ |
| [录制和预览转换后的视频流](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-transform-example.html) | [gst-transform-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-transform-example?ref_type=heads) | 转换视频流（旋转、翻转和缩放）。 | ✔ | ✔ | ✔ |
| [使用 Weston 进行视频合成](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-weston-composition-example.html) | [gst-weston-composition-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-weston-composition-example?ref_type=heads) | 各种来源的组合，例如实时摄像头输入和离线文件。 | ✔ | ✔ | ✔ |
| [对音频和视频流进行编码](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-audio-video-encode.html) | [gst-audio-video-encode](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-audio-video-encode?ref_type=heads) | 对音频和视频数据进行编码，然后将其存储到用户指定的输出文件中。 | ✔ | ✔ | ✔ |
| **音频应用程序** | **音频应用程序** | **音频应用程序** | **音频应用程序** | **音频应用程序** | **音频应用程序** |
| [音频播放](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-audio-decode-sample.html) | [gst-audio-decode-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-audio-decode-example?ref_type=heads) | 播放音频文件。 | ✔ | ✔ | ✔ |
| [音频录制](https://docs.qualcomm.com/doc/80-70022-50SC/topic/gst-audio-encode-example-without-flac.html) | [gst-audio-encode-example](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/tree/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-audio-encode-example?ref_type=heads) | 录制采集的音频并将其编码为 FLAC 或 WAV 格式。 | ✔ | ✔ | ✔ |

- **[运行 AI/ML 示例应用程序](https://docs.qualcomm.com/doc/80-70022-50SC/topic/ai-ml-sample-applications.html)**  

将 Qualcomm AI/ML 功能与 Qualcomm AI Runtime SDK（Qualcomm Neural Processing SDK 和 Qualcomm^®^ AI Engine Direct）以及 LiteRT（以前称为 TFLite）模型结合使用。
- **[运行多媒体示例应用程序](https://docs.qualcomm.com/doc/80-70022-50SC/topic/multimedia-sample-applications.html)**  

多媒体示例应用程序提供了自定义用例，可实现 Qualcomm Linux 的摄像头、视频、音频、图形和显示功能。
- **[运行基于 Python 的应用程序](https://docs.qualcomm.com/doc/80-70022-50SC/topic/python-sample-applications.html)**  

Qualcomm Linux 通过 [gstreamer1.0-python](https://git.codelinaro.org/clo/le/meta-qti-gst/-/blob/imsdk.lnx.2.0.0.r2-rel/recipes-gst/packagegroups/packagegroup-qcom-gst.bb?ref_type=heads#L45) 软件包提供了对 Python 的集成支持。Qualcomm IM SDK 支持 Python 绑定，允许您使用 Python 创建基于 GStreamer 的应用程序。所有 GST 插件的 Python 绑定均通过 `gst-python`实用工具启用。

Last Published: Nov 05, 2025

[Previous Topic
Qualcomm IM SDK 环境概述](https://docs.qualcomm.com/bundle/publicresource/80-70022-50SC/topics/overview.md) [Next Topic
运行 AI/ML 示例应用程序](https://docs.qualcomm.com/bundle/publicresource/80-70022-50SC/topics/ai-ml-sample-applications.md)