MediaPipe

Quality 0.50 · 1 view · Updated 2 months ago

Open source AI framework by Google

title: "MediaPipe" type: doc version: 1 created: 2026-02-28 author: "Wikipedia contributors" status: active scope: public tags: ["computer-vision-software", "software-using-the-apache-license"] description: "Open source AI framework by Google" topic_path: "technology/computing" source: "https://en.wikipedia.org/wiki/MediaPipe" license: "CC BY-SA 4.0" wikipedia_page_id: 0 wikipedia_revision_id: 0

::summary Open source AI framework by Google ::

::data[format=table title="Infobox software"]

FieldValue
authorCamillo Lugaresi, Jiuqiang Tang, Hadon Nash, Chris McClanahan, Esha Uboweja, Michael Hays, Fan Zhang, Chuo-Ling Chang, Ming Guang Yong, Juhyun Lee, Wan-Teh Chang, Wei Hua,
released
latest release version0.10.26
repo
platformAndroid, JavaScript web, Python, iOS
language count
genreFramework
licenseApache
website
::

| title = | logo = | logo caption = | logo alt = | logo upright = | logo size = | collapsible = | screenshot = | screenshot upright = | screenshot size = | screenshot alt = | caption = | other_names = | author = Camillo Lugaresi, Jiuqiang Tang, Hadon Nash, Chris McClanahan, Esha Uboweja, Michael Hays, Fan Zhang, Chuo-Ling Chang, Ming Guang Yong, Juhyun Lee, Wan-Teh Chang, Wei Hua, Manfred Georg and Matthias Grundmann | developer = | released = | ver layout = | discontinued = | latest release version = 0.10.26 | latest release date = | latest preview version = | latest preview date = | repo = | qid = | programming language = | middleware = | engine = | operating system = | platform = Android, JavaScript web, Python, iOS | included with = | replaces = | replaced_by = | service_name = | size = | standard = | language = | language count = | language footnote = | genre = Framework | license = Apache | website = | AsOf =

MediaPipe is an open source framework with many libraries developed by Google for several artificial intelligence and machine learning solutions. These solutions range from generative artificial intelligence, real-time computer vision, natural language processing and audio techniques. These solutions can also be used on various platforms such as Android, JavaScript web, Python and iOS, supporting edge devices.

History

Google has long used MediaPipe in its products and services. Since 2012, it has been used for real-time analysis of video and audio on YouTube. Over time MediaPipe has been incorporated into many more products such as Gmail, Google Home, etc.

MediaPipe's first stable release was version 0.5.0. It was made open source in June 2019 at the Conference on Computer Vision and Pattern Recognition in Long Beach, California, by Google Research. This initial release included only five pipelines examples: Object Detection, Face Detection, Hand Tracking, Multi-hand Tracking, and Hair Segmentation. From its initial release to April 2023, numerous pipelines have been made. In May 2025, MediaPipe Solutions was introduced. This transition offered more capabilities for on-device machine learning. MediaPipe is now under Google's subdivision, Google AI Edge.

Solutions

MediaPipe's available solutions are:

MediaPipe's legacy solutions are:

  • Face Detection
  • Face Mesh
  • Iris
  • Hands
  • Pose
  • Holistic
  • Selfie segmentation
  • Hair segmentation
  • Object detection
  • Box tracking
  • Instant motion tracking
  • Objectron
  • KNIFT
  • AutoFlip
  • MediaSequence
  • YouTube 8M

Programming Language

MediaPipe is primarily written in the programming language C++, although this is not the sole programing language used in its creation. The other notable programming languages used within its source code include Python, Starlark, and Java.

The ability for MediaPipe to separate itself into a system of components allows for customization. Pre-built solutions are also available and it may help to start with these and slightly optimize them for an ideal output.

How MediaPipe Works

MediaPipe contains a multitude of different components that all work together to create a general purpose computer vision framework. Each component works in its own unique way with different architectures.

Hand Tracking

MediaPipe includes a hand tracking system that has been designed to run efficiently on devices with limited computational resources. This works by estimating a set of 3D landmarks for each detected hand and is intended to remain stable across a wide range of environments including different poses, lightning conditions, and motions.

MediaPipe works off of a pre-trained deep learning model that is trained to detect the palm area on human hands, which is done through a detector model named BlazePalm. Starting with the identification of the palm, MediaPipe is able to use the positioning of the palm as an input to a second model that predicts the positions of key landmarks that will represent the hand's structure. ::figure[src="https://upload.wikimedia.org/wikipedia/commons/5/5c/Handes_Before_MediaPipe_Analysis.png" caption="Hands before MediaPipe hand detection"] ::

::figure[src="https://upload.wikimedia.org/wikipedia/commons/f/fc/Hands_After_MediaPipe_Analysis.png" caption="Hands after MediaPipe hand detection"] ::

MediaPipe continuously monitors the confidence of its predictions and re-runs detection when needed to maintain its accuracy, while temporal smoothing helps reduce the jitter between frames. For scenes with more than one hand, the process is repeated independently for each detected region.

Human Pose Estimation

Another area that MediaPipe specializes in is recognizing changes in the human body specifically posture. Mediapipe can support the creation of body posture analysis systems. This can aid in many fields such as ergonomic industry, the arts, sports, and entertainment.

References

References

  1. Hon Law, Wai. "Release MediaPipe v0.10.26 · google-ai-edge/mediapipe".
  2. (2025-03-12). "Sometimes Painful but Certainly Promising: Feasibility and Trade-offs of Language Model Inference at the Edge".
  3. (2024-11-18). "Generative AI on the Edge: Architecture and Performance Evaluation".
  4. (2023-10-09). "International Conference on Multimodal Interaction". Association for Computing Machinery.
  5. (2023-02-20). "Human Pose Estimation Using MediaPipe Pose and Optimization Method Based on a Humanoid Model". Applied Sciences.
  6. (2022-05-23). "Face Mask Detection using MediaPipe Facemesh". IEEE.
  7. (2025-11-17). "Rethinking I/O Caching for Large Language Model Inference on Resource-Constrained Mobile Platforms". Mathematics.
  8. (2024). "Interspeech 2024".
  9. (2025-04-03). "TikTok StitchGraph: Characterizing communication patterns on TikTok through a collection of interaction networks".
  10. (2025-03-24). "Companion Proceedings of the 30th International Conference on Intelligent User Interfaces". ACM.
  11. (2021-09-30). "2021 IEEE 9th Region 10 Humanitarian Technology Conference (R10-HTC)". IEEE.
  12. (2025-07-08). "2025 IEEE 49th Annual Computers, Software, and Applications Conference (COMPSAC)". IEEE.
  13. (2024-12-16). "2024 1st International Conference on Advances in Computing, Communication and Networking (ICAC2N)". IEEE.
  14. (2023-05-12). "2023 3rd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE)". IEEE.
  15. (2024-05-24). "2024 5th International Conference for Emerging Technology (INCET)". IEEE.
  16. (2019-06-14). "MediaPipe: A Framework for Building Perception Pipelines".
  17. (2025-08-10). "An Intelligent Mobile Application to Monitor and Correct Sitting Posture Using Raspberry Pi and MediaPipe Pose Detection".
  18. (2024-05-22). "2024 1st International Conference on Communications and Computer Science (InCCCS)". IEEE.
  19. (2024-09-18). "2024 IEEE International Symposium on Technology and Society (ISTAS)". IEEE.
  20. Pranav Durai, Kukil. (March 1, 2022). "MediaPipe – The Ultimate Guide to Video Processing".
  21. Yong, Ming. "Release MediaPipe v0.5.0 · google-ai-edge/mediapipe".
  22. "Object Detection and Tracking using MediaPipe- Google Developers Blog".
  23. "Introducing MediaPipe Solutions for On-Device Machine Learning- Google Developers Blog".
  24. (2020-06-18). "MediaPipe Hands: On-device Real-time Hand Tracking".
  25. Kukil, Pranav Durai. (2022-03-01). "MediaPipe-The Ultimate Guide to Video Processing".
  26. "On-Device, Real-Time Hand Tracking with MediaPipe".

::callout[type=info title="Wikipedia Source"] This article was imported from Wikipedia and is available under the Creative Commons Attribution-ShareAlike 4.0 License. Content has been adapted to SurfDoc format. Original contributors can be found on the article history page. ::

computer-vision-softwaresoftware-using-the-apache-license