OpenVisionCapsules: Difference between revisions
m Remove Afc Messages and templates |
m automatic correction by IA |
||
| Line 5: | Line 5: | ||
OpenVisionCapsules is a format for encapsulating Computer Vision or Deep Neural Network algorithms, initially proposed & [https://aotu.ai/docs/capsule_development/introduction/ implemented by Aotu.ai]. It was released through [[OpenCV|OpenCV.org]] as a BSD licensed Open Source Project. Source code is available [https://github.com/opencv/open_vision_capsules here]. | OpenVisionCapsules is a format for encapsulating Computer Vision or Deep Neural Network algorithms, initially proposed & [https://aotu.ai/docs/capsule_development/introduction/ implemented by Aotu.ai]. It was released through [[OpenCV|OpenCV.org]] as a BSD licensed Open Source Project. Source code is available [https://github.com/opencv/open_vision_capsules here]. | ||
The typical [https://aotu.ai/docs/capsule_development/inputs_and_outputs/ input of a VisionCapsule] is a video frame, [https://aotu.ai/docs/capsule_development/inputs_and_outputs/ the output is semantic information] or | The typical [https://aotu.ai/docs/capsule_development/inputs_and_outputs/ input of a VisionCapsule] is a video frame, [https://aotu.ai/docs/capsule_development/inputs_and_outputs/ the output is semantic information] or structured data of the frame, e.g. car, motorcycle, and truck detection. | ||
== The goal of the project == | == The goal of the project == | ||
OpenVisionCapsules was created to address the issue of the fragmented smart vision device market. OpenVisionCapsules specifies the input, the output, how to package, and the entry points of the program. It does not replace the format of any Neural Network or algorithms or a runtime like [[OpenVINO]]. It is simply a packaging format, including all necessary code, files, and metadata required to describe and implement an algorithm. By establishing a standardized communication, the output of an algorithm, or a so-called VisionCapsule, can be consumed by another VisionCapsule. | OpenVisionCapsules was created to address the issue of the fragmented smart vision device market. OpenVisionCapsules specifies the input, the output, how to package, and the entry points of the program. It does not replace the format of any Neural Network or algorithms or a runtime like [[OpenVINO]]. It is simply a packaging format, including all necessary code, files, and metadata required to describe and implement an algorithm. By establishing a standardized communication, the output of an algorithm, or a so-called VisionCapsule, can be consumed by another VisionCapsule. | ||
Because | Because OpenVisionCapsules is a self-contained, portable format, it allows compatible devices to distribute algorithms across devices, and communicate with consistent semantic information. By combining many simple VisionCapsules, on either one device or across multiple devices, sophisticated data can be extracted from video streams to achieve complicated artificial intelligence tasks. | ||
== How does it work == | == How does it work == | ||
Latest revision as of 11:44, 2 August 2025
This article may meet Wikipedia's criteria for speedy deletion as a copyright infringement(Copyvios report) of https://opencv.org/opencv-hardware-partnership-program/ (Duplication Detector report · Copyvios report). This criterion applies only in unequivocal cases, where there is no free-content material on the page worth saving and no later edits requiring attribution – for more complicated situations, see Wikipedia:Copyright violations. See CSD G12.
If this article does not meet the criteria for speedy deletion, or you intend to fix it, please remove this notice, but do not remove this notice from pages that you have created yourself. If you created this page and you disagree with the given reason for deletion, you can click the button below and leave a message explaining why you believe it should not be deleted. You can also visit the talk page to check if you have received a response to your message. Note that once tagged with this notice, this article may be deleted at any time if it unquestionably meets the speedy deletion criteria, or if an explanation posted to the talk page is found to be insufficient. Note to page author: you have not edited the article talk page yet. If you wish to contest this speedy deletion, clicking the button above will allow you to leave a talk page message explaining why you think this article should not be deleted. If you have already posted to the talk page but this message is still showing up, try purging the page cache. Note to administrators: If declining the request due to not meeting the criteria please consider whether there are still copyright problems with the page and if so, see these instructions for cleanup, or list it at Wikipedia:Copyright problems. Please be sure that the source of the alleged copyright violation is not itself a Wikipedia mirror. Also, ensure the submitter of this page has been notified about our copyright policy.Administrators: check links, history (last), and logs before deletion. Consider checking Google. This page was last edited by WikiMasterBot2 (contribs | logs) at 11:44, 2 August 2025 (UTC) (11 months ago) |
What is OpenVisionCapsules?
OpenVisionCapsules is a format for encapsulating Computer Vision or Deep Neural Network algorithms, initially proposed & implemented by Aotu.ai. It was released through OpenCV.org as a BSD licensed Open Source Project. Source code is available here.
The typical input of a VisionCapsule is a video frame, the output is semantic information or structured data of the frame, e.g. car, motorcycle, and truck detection.
The goal of the project
OpenVisionCapsules was created to address the issue of the fragmented smart vision device market. OpenVisionCapsules specifies the input, the output, how to package, and the entry points of the program. It does not replace the format of any Neural Network or algorithms or a runtime like OpenVINO. It is simply a packaging format, including all necessary code, files, and metadata required to describe and implement an algorithm. By establishing a standardized communication, the output of an algorithm, or a so-called VisionCapsule, can be consumed by another VisionCapsule.
Because OpenVisionCapsules is a self-contained, portable format, it allows compatible devices to distribute algorithms across devices, and communicate with consistent semantic information. By combining many simple VisionCapsules, on either one device or across multiple devices, sophisticated data can be extracted from video streams to achieve complicated artificial intelligence tasks.
How does it work
Introducing OpenVisionCapsules
How to build an OpenVisionCapsules compatible Hardware
Download and test some prebuilt VisionCapsules
Comparison with other machine learning models
| Items | Existing Model Formats:
Tensorflow, Keras, Caffe, Torch, ONNX, etc. |
OpenVisionCapsules Format |
|---|---|---|
| Design goal | DNN training | DNN deployment |
| Self-contained DNN model | ✔ / X
Separate files in most formats |
✔ |
| Pre-processing & post processing included | X | ✔ |
| DNN Model Interconnect | X | ✔ |
| Compatible with other formats | X | ✔
Portable format for all others |
References
This article "OpenVisionCapsules" is from Wikipedia. The list of its authors can be seen in its historical and/or the page Edithistory:OpenVisionCapsules. Articles copied from Draft Namespace on Wikipedia could be seen on the Draft Namespace of Wikipedia and not main one.
