Dear OpenCV users!
1 year after 3.1 release and after the OpenCV core team has moved back to Intel we are pleased to announce OpenCV 3.2 release, with tons of improvements and bug fixes. 969 patches have been merged and 478 issues (bugs & feature requests) have been closed.
Big thanks to everyone who participated! If you contributed something but your name is missing, please, let us know.
Merry Christmas and Happy New Year!
The detailed list of changes since 3.1 can be found at https://github.com/opencv/opencv/wiki/ChangeLog. Here is the short summary:
Results from 11 GSoC 2016 projects have been submitted to the library:
- Ambroise Moreau (Delia Passalacqua) – sinusoidal patterns for structured light and phase unwrapping module
- Alexander Bokov (Maksim Shabunin) – DIS optical flow (excellent dense optical flow algorithm that is both significantly better and significantly faster than Farneback’s algorithm – our baseline), and learning-based color constancy algorithms implementation
- Tyan Vladimir (Antonella Cascitelli) – CNN based tracking algorithm (GOTURN)
- Vladislav Samsonov (Ethan Rublee) – PCAFlow and Global Patch Collider algorithms implementation
- João Cartucho (Vincent Rabaud) – Multi-language OpenCV Tutorials in Python, C++ and Java
- Jiri Horner (Bo Li) – New camera model and parallel processing for stitching pipeline
- Vitaliy Lyudvichenko (Anatoly Baksheev) – Optimizations and improvements of dnn module
- Iric Wu (Vadim Pisarevsky) – Base64 and JSON support for file storage. Use names like “myfilestorage.xml?base64” when writing file storage to store big chunks of numerical data in base64-encoded form.
- Edgar Riba (Manuele Tamburrano, Stefano Fabri) – tiny_dnn improvements and integration
- Yida Wang (Manuele Tamburrano, Stefano Fabri) – Quantization and semantic saliency detection with tiny_dnn
- Anguelos Nicolaou (Lluis Gomez) – Word-spotting CNN based algorithm
Big thanks to all the participants!
There have been many contributions besides GSoC:
- Greatly improved and accelerated dnn module in opencv_contrib:
- Many new layers, including deconvolution, LSTM etc.
- Support for semantic segmentation and SSD networks with samples.
- TensorFlow importer + sample that runs Inception net by Google.
- More image formats and camera backends supported
- Interactive camera calibration app
- Multiple algorithms implemented in opencv_contrib
- Supported latest OSes, including Ubuntu 16.04 LTS and OSX 10.12
- Lot’s of optimizations for IA and ARM archs using parallelism, vector instructions and new OpenCL kernels.
- OpenCV now can use vendor-provided OpenVX and LAPACK/BLAS (including Intel MKL, Apple’s Accelerate, OpenBLAS and Atlas) for acceleration
The latest version can be downloaded from SourceForge and GitHub:
Windows self-extracting archive: sourceforge
iOS framework: sourceforge
Android SDK: sourceforge
The source code for all platforms can be downloaded from GitHub: zip and tar.gz