# Qualcomm Intelligent Multimedia SDK

- [Introduction](https://imsdkdocs.qualcomm.com/index.md): Qualcomm® Intelligent Multimedia SDK
- [Installation](https://imsdkdocs.qualcomm.com/installation.md)
- [Quickstart](https://imsdkdocs.qualcomm.com/app-builder-quickstart.md): Choose a development path and jump into its quickstart guide
- [Coding Agent](https://imsdkdocs.qualcomm.com/app-builder-coding-agent.md): Generate QIM SDK applications with AI coding agent skills
- [Benefits](https://imsdkdocs.qualcomm.com/benefits.md)
- [Release Notes](https://imsdkdocs.qualcomm.com/relnotes.md): What's new, fixed, and known issues for each QIM SDK release
- [Object Detection](https://imsdkdocs.qualcomm.com/supportedmodels/object-detection.md): QIM SDK supported models for Object Detection
- [Image Classification](https://imsdkdocs.qualcomm.com/supportedmodels/image-classification.md): QIM SDK supported models for Image Classification
- [Semantic Segmentation](https://imsdkdocs.qualcomm.com/supportedmodels/semantic-segmentation.md): QIM SDK supported models for Semantic Segmentation
- [Pose Estimation](https://imsdkdocs.qualcomm.com/supportedmodels/pose-estimation.md): QIM SDK supported models for Pose Estimation
- [Super Resolution](https://imsdkdocs.qualcomm.com/supportedmodels/super-resolution.md): QIM SDK supported models for Super Resolution
- [Depth Estimation](https://imsdkdocs.qualcomm.com/supportedmodels/depth-estimation.md): QIM SDK supported models for Depth Estimation
- [Audio Classification](https://imsdkdocs.qualcomm.com/supportedmodels/audio-classification.md): QIM SDK supported models for Audio Classification
- [Plugins Introduction](https://imsdkdocs.qualcomm.com/plugin-reference/introduction.md): Documentation for QIM SDK GStreamer plugins
- [qtimlvconverter](https://imsdkdocs.qualcomm.com/plugin-reference/qtimlvconverter.md): AI pre-processing plugin
- [qtimlonnx](https://imsdkdocs.qualcomm.com/plugin-reference/qtimlonnx.md): ONNX Runtime inference element for GStreamer AI and multimedia pipelines.
- [qtimlqnn](https://imsdkdocs.qualcomm.com/plugin-reference/qtimlqnn.md): GStreamer inference element that executes neural network models using QNN runtime.
- [qtimltflite](https://imsdkdocs.qualcomm.com/plugin-reference/qtimltflite.md): TensorFlow Lite inference element for GStreamer AI and multimedia pipelines.
- [qtimldemux](https://imsdkdocs.qualcomm.com/plugin-reference/qtimldemux.md): GStreamer plugin for demultiplexing batched AI inference outputs in Vision AI SDK.
- [qtimlpostprocess](https://imsdkdocs.qualcomm.com/plugin-reference/qtimlpostprocess.md): AI post-processing plugin
- [qtimlsnpe](https://imsdkdocs.qualcomm.com/plugin-reference/qtimlsnpe.md): neural network models using Qualcomm’s SNPE
- [qtivtransform](https://imsdkdocs.qualcomm.com/plugin-reference/qtivtransform.md): AI pre-processing plugin
- [qtivcomposer](https://imsdkdocs.qualcomm.com/plugin-reference/qtivcomposer.md): Video composition pipelines plugin
- [qtivoverlay](https://imsdkdocs.qualcomm.com/plugin-reference/qtivoverlay.md): Hardware-accelerated in-place video overlay plugin
- [qtivsplit](https://imsdkdocs.qualcomm.com/plugin-reference/qtivsplit.md): qtivsplit is a GStreamer plugin that creates new video buffers from an input video frame by applying spatial transformations such as cropping, resizing, and color conversion.
- [qticamsrc](https://imsdkdocs.qualcomm.com/plugin-reference/qticamsrc.md): Hardware-accelerated GStreamer camera source plugin for Qualcomm ISP camera access via the camera service.
- [v4l2h264dec](https://imsdkdocs.qualcomm.com/plugin-reference/v4l2h264dec.md): Hardware-accelerated H.264 video decoder using the V4L2 stateful decoder API on Qualcomm hardware.
- [v4l2h264enc](https://imsdkdocs.qualcomm.com/plugin-reference/v4l2h264enc.md): Hardware-accelerated H.264/AVC video encoder using the V4L2 stateful encoder API on Qualcomm hardware.
- [v4l2h265dec](https://imsdkdocs.qualcomm.com/plugin-reference/v4l2h265dec.md): Hardware-accelerated H.265/HEVC video decoder using the V4L2 stateful decoder API on Qualcomm hardware.
- [v4l2h265enc](https://imsdkdocs.qualcomm.com/plugin-reference/v4l2h265enc.md): Hardware-accelerated H.265/HEVC video encoder using the V4L2 stateful encoder API on Qualcomm hardware.
- [v4l2vp9dec](https://imsdkdocs.qualcomm.com/plugin-reference/v4l2vp9dec.md): Hardware-accelerated VP9 video decoder using the V4L2 stateful decoder API on Qualcomm hardware.
- [v4l2av1dec](https://imsdkdocs.qualcomm.com/plugin-reference/v4l2av1dec.md): Hardware-accelerated AV1 video decoder using the V4L2 stateful decoder API on Qualcomm hardware.
- [qtirtspbin](https://imsdkdocs.qualcomm.com/plugin-reference/qtirtspbin.md): A GstBin-derived sink element that encapsulates RTSP streaming functionality by integrating GStreamer RTSP Server APIs.
- [qtiredissink](https://imsdkdocs.qualcomm.com/plugin-reference/qtiredissink.md): Redis Pub/Sub sink plugin for real-time text-based metadata publishing
- [qtisocketsink](https://imsdkdocs.qualcomm.com/plugin-reference/qtisocketsink.md): Socket Sink plugin
- [qtisocketsrc](https://imsdkdocs.qualcomm.com/plugin-reference/qtisocketsrc.md): Socket Source plugin
- [waylandsink](https://imsdkdocs.qualcomm.com/plugin-reference/waylandsink.md): Display plugin for weston compositor
- [qtimetamux](https://imsdkdocs.qualcomm.com/plugin-reference/qtimetamux.md): AI metadata synchronization and muxing plugin
- [qtimlmetaparser](https://imsdkdocs.qualcomm.com/plugin-reference/qtimetaparser.md): Serializes ML inference metadata from GStreamer buffers into text.
- [qtimsgpub and qtimsgsub](https://imsdkdocs.qualcomm.com/plugin-reference/qtimsg.md): Message broker plugins
- [qtiobjtracker](https://imsdkdocs.qualcomm.com/plugin-reference/qtiobjtracker.md): Real time multi object tracking plugin
- [qtibatch](https://imsdkdocs.qualcomm.com/plugin-reference/qtibatch.md): GStreamer buffer batching element
- [Technology Overview](https://imsdkdocs.qualcomm.com/advanced/technologyoverview.md): Qualcomm Technology components used in by QIM SDK
- [QIM SDK Docker](https://imsdkdocs.qualcomm.com/advanced/docker.md): Build, configure, and run the QIM SDK Docker container on Qualcomm platforms.
- [Debugging Guide](https://imsdkdocs.qualcomm.com/advanced/debugging.md): Developer guide for debugging, profiling, and tracing QIM SDK GStreamer pipelines.
- [Test Automation](https://imsdkdocs.qualcomm.com/advanced/test-automation.md): Automated testing strategies and tools for QIM SDK pipelines.
- [Yocto platform](https://imsdkdocs.qualcomm.com/advanced/yocto-build.md)
- [Ubuntu platform](https://imsdkdocs.qualcomm.com/advanced/ubuntu-build.md)
- [Quickstart Guide](https://imsdkdocs.qualcomm.com/quickstart.md): Explore object detection pipelines with QIM SDK
- [Coding Agent](https://imsdkdocs.qualcomm.com/app-builder/gstreamer-coding-agent.md): Use the QIM SDK GStreamer App Builder skill to generate native C pipeline apps and gst-launch scripts with an AI coding agent.
- [QIM SDK Overview](https://imsdkdocs.qualcomm.com/qimsdk-overview/sdkoverview.md): Step by step guide for building AI pipelines using QIM SDK
- [Data Sources](https://imsdkdocs.qualcomm.com/qimsdk-overview/datasources.md)
- [Preprocessing](https://imsdkdocs.qualcomm.com/qimsdk-overview/preprocessing.md): Converting captured frames into tensors for inferencing
- [Inferencing](https://imsdkdocs.qualcomm.com/qimsdk-overview/inference.md): Pipeline construction for running AI inference
- [Postprocessing](https://imsdkdocs.qualcomm.com/qimsdk-overview/postprocessing.md): Postprocessing of AI inference results
- [Image Classification](https://imsdkdocs.qualcomm.com/qimsdk-overview/classification.md): Building image classification pipelines with QIM SDK
- [Object Detection](https://imsdkdocs.qualcomm.com/qimsdk-overview/objectdetection.md): Building object detection pipelines with QIM SDK
- [Image Segmentation](https://imsdkdocs.qualcomm.com/qimsdk-overview/imgsegmentation.md)
- [Daisy Chaining](https://imsdkdocs.qualcomm.com/qimsdk-overview/daisychaining.md): Daisy Chaining AI Models
- [Building Production Quality Pipelines](https://imsdkdocs.qualcomm.com/qimsdk-overview/building-native-object-detection-application.md)
- [AI](https://imsdkdocs.qualcomm.com/sample-pipelines/aipipelines.md)
- [Multimedia](https://imsdkdocs.qualcomm.com/sample-pipelines/multimediapipelines.md)
- [AI](https://imsdkdocs.qualcomm.com/sample-application/ai-sample-applications.md): Ready-to-run C++ applications demonstrating QIM SDK AI inference capabilities
- [Multimedia](https://imsdkdocs.qualcomm.com/sample-application/multimedia-sample-applications.md): Ready-to-run C++ applications demonstrating QIM SDK camera, video, and audio capabilities
- [AI](https://imsdkdocs.qualcomm.com/sample-application/python-ai-sample-applications.md): Ready-to-run Python AI applications demonstrating QIM SDK inference capabilities using GObject Introspection (GI) bindings
- [Multimedia](https://imsdkdocs.qualcomm.com/sample-application/python-multimedia-sample-applications.md): Ready-to-run Python multimedia applications demonstrating QIM SDK camera, video, and streaming capabilities
- [Concepts of Building Native GStreamer Application](https://imsdkdocs.qualcomm.com/qimsdk-overview/building-native-app.md)
- [Plugins Introduction](https://imsdkdocs.qualcomm.com/plugin-reference/introduction.md): Documentation for QIM SDK GStreamer plugins
- [Quick start guide](https://imsdkdocs.qualcomm.com/app-builder/cpp-quickstart.md): A Quick demonstration of C++ SDK for building AI application on Qualcomm platforms
- [Coding Agent](https://imsdkdocs.qualcomm.com/app-builder/cpp-coding-agent.md): Use the QIM SDK C++ App Builder skill to generate C++ pipeline apps with an AI coding agent.
- [Reference Applications](https://imsdkdocs.qualcomm.com/app-builder/cpp-reference-applications.md): Reference C++ App Builder pipeline examples
- [Demo Applications](https://imsdkdocs.qualcomm.com/app-builder/cpp-demo-applications.md): Ready-to-run C++ App Builder demo applications
- [SDK Architecture and API Reference](https://imsdkdocs.qualcomm.com/app-builder/cpp-architecture-api-reference.md): Design and API details of the QIM SDK Pipeline SDK (C++ and Python)
- [Plugins Introduction](https://imsdkdocs.qualcomm.com/plugin-reference/introduction.md): Documentation for QIM SDK GStreamer plugins
- [Quick start guide](https://imsdkdocs.qualcomm.com/app-builder/python-quickstart.md): A Quick demonstration of Python SDK for building AI application on Qualcomm platforms
- [Coding Agent](https://imsdkdocs.qualcomm.com/app-builder/python-coding-agent.md): Use the QIM SDK Python App Builder skill to generate Python pipeline apps with an AI coding agent.
- [Reference Applications](https://imsdkdocs.qualcomm.com/app-builder/python-reference-applications.md): Reference Python App Builder pipeline examples
- [Demo Applications](https://imsdkdocs.qualcomm.com/app-builder/python-demo-applications.md): Ready-to-run Python App Builder demo applications
- [SDK Architecture and API Reference](https://imsdkdocs.qualcomm.com/app-builder/python-architecture-api-reference.md): Design and API details of the QIM SDK Pipeline SDK (C++ and Python)
- [Plugins Introduction](https://imsdkdocs.qualcomm.com/plugin-reference/introduction.md): Documentation for QIM SDK GStreamer plugins
- [QIM SDK Tutorials](https://imsdkdocs.qualcomm.com/blogs/blog-index.md)
- [Building a Real-Time Hand Gesture Recognition AI Pipeline Using the QIM SDK](https://imsdkdocs.qualcomm.com/blogs/smart-hand-gesture-recognition.md): A four-stage sequential AI pipeline — palm detection, hand landmark estimation, gesture embedding, and gesture classification — built with Qualcomm QIM SDK for real-time edge deployment.
- [Touchless Smart Board — Transforming Digital Learning with QIM SDK](https://imsdkdocs.qualcomm.com/blogs/smart-board-application.md): A two-stage palm detection and hand landmark pipeline turns hand gestures into a real-time, touchless virtual whiteboard, built with QIM SDK.
- [Building a Wrist-Controlled Car Game Using QIM SDK](https://imsdkdocs.qualcomm.com/blogs/touchless-wrist-steering-car-game.md): A two-stage palm detection and hand landmark pipeline turns wrist movement into a virtual steering wheel for a real-time, touchless split-screen driving game, built with QIM SDK
- [Edge AI for Smart Manufacturing — Real-Time Bottle Counting Using Qualcomm QIM SDK](https://imsdkdocs.qualcomm.com/blogs/product-counting-application.md): A YOLOv8-based object detection pipeline that counts products crossing a center region of interest in real time, built with Qualcomm QIM SDK and QNN HTP acceleration.
- [Multi Stream IP Camera application](https://imsdkdocs.qualcomm.com/blogs/multi-stream-ip-camera.md): A real-time object detection pipeline built with QIM SDK using a YOLOv8 TensorFlow Lite model, supporting multiple input sources and RTSP/WebRTC output.
- [Building a Scalable Multi-Stream AI Video Wall with QIM SDK](https://imsdkdocs.qualcomm.com/blogs/security-video-wall.md): Process up to 31 concurrent IP camera streams in parallel with YOLOv8 object detection, compositing all streams into a single output and streaming over RTSP/WebRTC.
- [Restricted Zone Violation Detection with Foot-Based Spatial Intelligence](https://imsdkdocs.qualcomm.com/blogs/restricted-zone-alarm.md): Real-time pipeline that detects when a person steps into a predefined restricted zone using QIM SDK foot detection — with color-coded visual alerts and RTSP/WebRTC output.
- [Monitoring PPE Compliance with AI-Powered Computer Vision](https://imsdkdocs.qualcomm.com/blogs/montioring-ppe-compliance-with-ai-powered.md): Build a real-time PPE detection pipeline using Qualcomm QIM SDK with daisy-chained ML models for person detection and protective equipment recognition.

## OpenAPI Specs

- [openapi](/api-reference/openapi.json)

## Optional

- [Qualcomm Linux](https://dragonwingdocs.qualcomm.com/qualcomm-linux-qli)
- [Dragonwing](https://www.qualcomm.com/dragonwing)