OpenCV 4.13 is out this New Year’s Eve in providing the latest open-source computer vision (CV) capabilities. OpenCV 4.13 brings a wide variety of enhancements to this widely-used computer vision library.
With OpenCV 4.13 there are several performance optimizations for leveraging this computer vision code under Windows on ARM. There are also some test failure fixes for Windows on ARM. Meanwhile on the x86_64 side, there is continuing to be more usage around AVX-512 in different OpenCV code paths for more performance on capable Intel and AMD processors.
OpenCV’s image processing module has added iterative phase correlation capabilities, OpenEXR multi-spectral read/write support, new safety checks for its AVIF encoding/decoding, Raspberry Pi 5 / Raspberry Pi 4 V4L2 stateless HEVC video hardware acceleration with FFmpeg, improved multi QR code detection in the object detection module, and various other performance optimizations.
OpenCV’s JavaScript, Python, and Java bindings have also seen improvements too. Lastly, OpenCV 4.13 also brings NVIDIA CUDA 13.0 support.
Downloads and more details on today’s OpenCV 4.13 release via GitHub.
