保留正文与补采附件。源页面当前未重新核验；具体限制见交付清单。

Skip to main content Back to top OpenCV 5.0 Open Source Computer Vision 5.0 5.0.0alpha 4.13.0 4.12.0 4.11.0 4.10.0 4.9.0 4.8.0 4.7.0 4.6.0 4.5.5 4.5.4 4.5.3 4.5.2 4.5.1 4.5.0 4.4.0 4.3.0 4.2.0 4.1.2 4.1.1 4.1.0 4.0.1 4.0.0 3.4.20-dev 3.4.20 3.4.19 3.4.18 3.4.17 3.4.16 3.4.15 3.4.14 3.4.13 3.4.12 3.4.11 3.4.10 3.4.9 3.4.8 3.4.7 3.4.6 3.4.5 3.4.4 3.4.3 3.4.2 3.4.1 3.4.0 3.3.1 3.3.0 3.2.0 3.1.0 3.0.0

• Main Page
• Related Pages
• Namespaces
• Classes
• Examples
• Java documentation

Search Ctrl+K Light Dark System Settings

• GitHub

• Main Page

• Related Pages

• Namespaces

• Classes

• Examples

• Java documentation

Search Ctrl+K Light Dark System Settings

• GitHub

OpenCV documentation#

OpenCV (Open Source Computer Vision Library) is an open-source computer vision and machine learning software library. It has more than 2,500 optimised algorithms, a comprehensive mix of both classic and state-of-the-art computer vision and machine learning methods. These can be used to detect and recognise faces, identify objects, classify human actions in video, track camera and object motion, extract 3D models, stitch images together to produce high-resolution panoramas, and much more. The library has interfaces for C++, Python, Java, and JavaScript, runs on Windows, Linux, macOS, Android, and iOS, and accelerates work on CPU (SIMD), CUDA, OpenCL, and Vulkan. OpenCV 5.0 is a major release built on OpenCV 4.x. C++17 is now the minimum required standard, Python 2 support has been dropped (Python 3.6+ is required), and the legacy C API has been fully removed. New data types (CV_16BF, CV_32U, CV_64U, CV_64S, CV_Bool) and proper 0D/1D array support extend the core, while the former calib3d module is split into the geometry, calib, stereo, and ptcloud modules. A next-generation DNN engine now covers over 80% of the ONNX specification (up from under 23%), with ONNX Runtime integration and models hosted on Hugging Face. Performance gains include Universal Intrinsics 2.0 (SSE/AVX/NEON/SVE/RISC-V), Vulkan compute support, image-warping speed-ups of 10% to over 300%, and USAC as the default framework for robust estimation.

Introduction#

• Introduction

How to use pre-built OpenCV binaries#

• Using OpenCV pre-built binaries in your own projects

OpenCV Tutorials#

• OpenCV tutorials

Python Tutorials#

• OpenCV-Python tutorials

Javascript Tutorials#

• OpenCV.js tutorials

Contrib Tutorials#

• Tutorials for contrib module

Main modules#

• Documentation for main modules

Extra modules#

• Documentation for extra modules

Frequently Asked Questions#

• Frequently Asked Questions

Bibliography#

• Bibliography

next Introduction On this page

• Introduction
• How to use pre-built OpenCV binaries
• OpenCV Tutorials
• Python Tutorials
• Javascript Tutorials
• Contrib Tutorials
• Main modules
• Extra modules
• Frequently Asked Questions
• Bibliography

Resources

• OpenCV Wiki
• What's new in 5.0
• Forum
• Stack Overflow
• Issue tracker

Created using Sphinx 8.1.3.

Built with the PyData Sphinx Theme 0.17.1. Ctrl+K [ ](javascript:searchBox.CloseResultsWindow()) [•All](javascript:void(0))[Classes](javascript:void(0))[Namespaces](javascript:void(0))[Files](javascript:void(0))[Functions](javascript:void(0))[Variables](javascript:void(0))[Typedefs](javascript:void(0))[Enumerations](javascript:void(0))[Enumerator](javascript:void(0))[Properties](javascript:void(0))[Friends](javascript:void(0))[Macros](javascript:void(0))[Modules](javascript:void(0))[Pages](javascript:void(0)) Loading... Searching... No Matches