20th anniversary is an important milestone
We invited the core OpenCV team and the luminaries in Computer Vision to share their thoughts of the past, present and future of the industry.
Anniversary Video 2
In the second video in the series, we continue remembering the history of OpenCV.Watch now
Interview with Andrew Ng
Andrew Ng, the founder of DeepLearning.AI, remembers his about his work with Gary Bradski at Stanford University and reflects on the role of OpenCV for the entire computer vision community.
Interview with Jitendra Malik
Jitendra Malik, Arthur J. Chick Professor of Electrical Engineering and Computer Sciences at the University of California, Berkeley, talks about his first memories about OpenCV and the development of computer vision technologies over the past 20 years.
OpenCV + OpenVINO
OpenCV turns 20, and OpenVINO toolkit turns two!
Your AI and Computer Vision Apps… Now Faster
OpenVINO provides high performance Deep Learning inference even on edge devices — and unlocks new solutions across multiple industries.Learn more Download
Join the celebration!
Trusted by worldwide specialists
lines of code
The road so far
1999: OpenCV goes open-source
Based on Gary’s recommendation, Intel open-sources the code of the library, which was a huge milestone for Intel, the project and the team as the original plan was for a closed-source solution to be named CVL for “Computer Vision Library” . Gary came up with the name “OpenCV” that was inspired by the OpenGL framework that was already popular back then.
2005: DARPA Challenge
In 2005, OpenCV dev team was a part of the team that won the DARPA Grand Challenge in unmanned ground vehicle navigation. It required robots to navigate a 142-mile long course through the Mojave desert in no more than 10 hours. On October 8, 2005, 195 teams registered, 23 raced and 5 finished. The robot named “Stanley” finished the course ahead of all other vehicles in 6 h, 53 min, and 58 s, and was declared the winner of the challenge.
October 2006: OpenCV 1.0 release
In the end of 2006, the version 1.0 was officially released. It was implemented in C and included various image processing operations, computational geometry, face detection, camera calibration, Lucas-Kanade optical flow, motion templates, SIFT features etc. and some classical machine learning methods: decision trees, boosting, SVM, multi-layer perceptrons etc. Also, Adi Shavit created the library logo.
2008: migration to Itseez and Willow Garage
After 2008, OpenCV moved into two new homes – companies named Willow Garage and Itseez.
Willow Garage was focused on cutting-edge robotics technology, and Itseez created the best-in-class Computer Vision algorithms. The main people behind OpenCV including Gary Bradski, Vadim Pisarevsky and Viktor Erukhimov join these teams and continue the development of the library.
Mid 2012: Android and iOS support
In 2012, OpenCV went mobile: it started to support first Android, and then iOS. This started the era of on-device Computer Vision, which meant that the algorithms stopped being run at servers exclusively. Mobile OS support enable a whole lot of CV-based applications for smartphones, as well as in-built camera features for computational photography.
Late 2012: opencv.org and migration to Github
Before 2012, the library development was done in SVN, and it was pretty hard for the community to commit their code to the library. In 2012, Kirill Kornyakov and Andrey Kamaev led the migration to Github and created a transparent contribution process that is used up until now. The worldwide community highly endorsed this move, and in 2013, 35 to 50% of all the pull requests that got in OpenCV was authored by the people outside of the core dev team.
Mid 2018: OpenVINO release
Intel releases OpenVINO toolkit for accelerated Computer Vision and Deep Learning on Intel platforms, and it is highly acclaimed by the community for the ease of its use and fantastic inference speed. It has a write-once, deploy-anywhere approach on Intel architectures: CPU, GPU, Movidius VPU and FPGA. OpenVINO can also be used as a backend for OpenCV DNN module – allowing to use OpenCV interface and enjoy significantly accelerated (up to 3x) neural network inference. A generous collection of models named Open Model Zoo is available for free to OpenVINO and OpenCV+OpenVINO users.
Late 2018: OpenCV 4.0 and C++11
In the new major release, the API has been refined to take advantage of newer C++ standard. Graph-API – an efficient image processing engine – was added. The library has been thoroughly optimized for the latest Intel architectures. The new functionality included 3D reconstruction algorithms, QR code detector and more. Intel China contributed Vulkan-based backend for DNN module.
2019: a distributed development team
Starting from 2019, the core development team of the library consists of distributed teams at Intel, OpenCV China, and xperience.ai. The core teams and the community work together and expand the functionality and the support of the library.
Computer Vision courses, OpenCV.AI and Hardware
Recently, we started adding more elements to the ecosystem. Based on our world-class expertise, we created Computer Vision and Deep Learning courses. We also presented OpenCV AI Kit – an innovative chip for Spatial AI that received a very warm welcome from the community. Moreover, we formed a for-profit arm name OpenCV.AI to create products and consult companies on how to create Computer Vision solutions to solve real-life problems.
Our vision for the next 20 years: a place where all Computer Vision conversations happen
In 2020, OpenCV 5.0 is coming out with an emphasis on deep learning and better performance on lower-power computing platforms. The other OpenCV 5.0 highlights are: Julia and Swift bindings, new 3D vision algorithms with elements of SLAM, as well as the results from the latest GSoC and OSPP programs.
One-stop-shop for best-in-class Computer Vision and AI solutions: OpenCV.AI.
Get OpenCV AI Kit – a Deep Learning-powered board with depth camera onboard.
Computer Vision and Deep Learning taught by the industry experts.
OpenVINO is an open-source toolkit that allows you to harness the full potential of AI and CV across multiple Intel® platforms.
Get answers from over 60K developers from all over the world.
Development and Hardware Partnership Programs
Become an OpenCV Dev Partner.
Coming soon: validate your hardware as OpenCV Ready.
Find Computer Vision algorithms that work best for your product – or sell the models online.
We’re happy to hear from you, let’s celebrate together!
“OpenCV’s original mission was to accelerate the development of academic and commercial computer vision. It is one of the few original plans I know of that actually worked as intended. OpenCV 5.0 continues OpenCV’s evolution into modular, efficient state of the art best practices coding!”
“OpenCV is one of those quietly catalyzing platforms… it has resulted in untold positive change in the world and engineering efficiency over the last 20 years. As part of the OpenCV AI Kit team, we are thrilled to enable embedded Spatial AI to fuel the next 20 years of innovation!”
“Proud to be a part of OpenCV team for so many years and hopefully many years to come. Congratulations and big thanks to all the OpenCV developers, past and present, to the contributors and to the community, of course. Our users are our biggest motivation to keep working on the project. So, keep sending us bug reports, feature requests, patches and words of appreciation.”
“Seldom do you find software libraries that have stood the tests of time and OpenCV leads the list with no doubt. We have been heavily using the library as part of our model based workflow, and it always excites us and customers to apply the technology to various engineering applications. I am convinced given the community the library is here to stay, grow leaps and bounds in the future!”
Prof. Shiqi Yu
“I created OpenCV China website in 2006 and was benefited a lot from OpenCV and OpenCV China website. In 2019, Vadim Pisarevsky and I created OpenCV China Team with the support from AIRS. I’m sure the team will bring more Chinese developers to contribute to OpenCV to make a better world by sharing computer vision knowledge.”
“Happy Birthday to OpenCV! Congratulations to the whole team and community for all this 20 years of effort and inspiration ?”
“During my PhD in the 2000’s, I had to create an art project that analyzed pedestrians in real-time. I found this library named OpenCV and fell in love with it. I then did whatever I could to be involved and managed to join Willow Garage in 2011 and I have been part of the OpenCV adventure since then!”
“Congratulations to OpenCV team and community, library that was born 20 years ago at time of Intel Image Processing Library, single core 32-bit processors and wish another 20 years to shine with Intel OpenVINO and many core 64-bit processors and special neural compute accelerators!”