Dear OpenCV community,
We are glad to announce OpenCV 4.0 alpha release, the first intermediate release before 4.0. OpenCV 4.0 gold is expected in the end of October.
First of all, 4.0 alpha includes all the latest improvements, optimizations and bug fixes from 3.4 branch. In particular:
- ONNX parser has been added to OpenCV DNN module. It supports various classification networks, such as AlexNet, Inception v2, Resnet, VGG etc. The tiny YOLO v2 object detection network is also partially supported.
- A few other notable DNN improvements:
- Mask RCNN support and the example
- Faster object detection when using Intel Inference Engine (a part of Intel OpenVINO)
- Several stability improvements in the OpenCL backend.
- Fast QR code detector (~80FPS @ 640×480 resolution on Core i5 desktop). By 4.0 gold we plan to add the QR code decoder as well, so that we have a complete solution.
- Constantly expanding set of SSE4-, AVX2- and NEON-optimized kernels via so called “wide universal intrinsics”.
Besides, OpenCV 4.0 alpha includes some exclusive features, such as:
- OpenCV is C++11 library now and it requires C++11 compliant compiler. Therefore, some nice features like parallel_for with lambda functions, convenient iteration over cv::Mat, initialization of cv::Mat by listing its elements etc. are available by default.
- The standard
cv::Ptr. Our parallel_for can now use the pool of std::threads as the backend.
- The legacy C API from OpenCV 1.x (using
IplImage, etc.) is partially excluded; the cleanup should mostly be finished by OpenCV 4.0 gold.
- Added basic FP16 support (the new
CV_16Ftype has been added).
- CPU- and GPU-accelerated KinFu live 3d dense reconstruction algorithm has been included into opencv_contrib.
- HPX parallel backend (thanks to Jakub Golinowski)
- The new chessboard detector (thanks to Alexander Duda)
Overall, OpenCV 4.0 alpha release includes 85 patches, including 28 massive merge requests from 3.4 branch.
Please note that even though the release should be quite stable, quite a few changes in OpenCV API and implementation are yet to be done before 4.0 final.
Big thanks to everybody who helped us to make this release and to all the people who supports OpenCV in one or another way!
Here is the incomplete list of contributors to OpenCV 4.0 alpha (if you contributed but do not see your name here, please let us know):
Alexander Alekhin, Dmitry Kurtaev, Maksim Shabunin, Hamdi Sahloul, Vitaly Tuzov, berak, Tomoaki Teshima, catree, Vadim Pisarevsky, Suleyman TURKMEN, Sayed Adel, Kuang Fangjun, Alexander Nesterov, Li Peng, Pavel Rojtberg, Rostislav Vasilikhin, cyy, take1014, yuki takehara, cclauss, Namgoo Lee, k-shinotsuka, shengyu, Alexander Enaldiev, George Mironov, Karpushin Vladislav, Lubov Batanina, Mark Harfouche, Pavel Vlasov, Vlad Karpushin, Wu Zhiwen, gkaneto, luz.paz, pasbi, Adam Rankin, Alessandro de Oliveira Faria (A.K.A.CABELO), Alexander Duda, Andrew Mroczkowski, Arnaud Brejeon, Bahram Dahi, CJ Smith, CYTing1998, Colin Smith, Damien Picard, David, Fangjun Kuang, Florian Echtler, Forrest Reiling, Gaetano Checinski, HarshDolhare, Hiro Kobayashi, Jakub Golinowski, Jiri Horner, Kaartic Sivaraam, Khem Raj, Kyle D. Patterson, LaurentBerger, Li, Peng, Lucas Teixeira, Marat K, Maxim Smirnov, Michael Firman, Nesterov Alexander, Nobuo Tsukamoto, Paul Jurczak, Paul92, Peter Jozsa, Peter Leitzen, Peter Rekdal Sunde, Philipp Hasper, Pierre Jeambrun, Ryan Wong, Sacha, Sancho McCann, Sergey Nuzhny, Simon Que, Spark Echo, Takuho NAKANO, Teng Yiliang, Todor Tomov, Triplesalt, Vlad Kraevskiy, Vladislav Sovrasov, Wenfeng CAI, Zhenqing Hu, abhi-jha, amatyuko, asciian, branka-plateiq, cDc, cabelo, exoson, gnthibault, ilovezfs, jsxyhelu, logic1988, matech96, miaow1988, rockzhan, tompollok, vishwesh5, woody.chow, yom, zarelaky, zuoshaobo
Alexander Alekhin, Pavel Rojtberg, LaurentBerger, Hamdi Sahloul, berak, Maksim Shabunin, Rostislav Vasilikhin, Suleyman TURKMEN, Vitaly Tuzov, catree, Anton Shutikhin, Colin, Dietrich Büsching, Jan Beich, Jiri Horner, Khem Raj, Kushashwa Ravi Shrimali, Li-Chi Huang, SongChiYoung, Unknown, Vadim Pisarevsky, Vladislav Sovrasov, bini, d.bouron, dianlujitao, fegorsch, gdemarcq, gmedan, simonreich, trobro, yarglawaldeg
OpenCV dev team