OpenCV 4.7 版本发布!算法家族又有新成员
共 2174字,需浏览 5分钟
·
2022-12-31 00:30
一如既往,OpenCV在新年来临之际,刚刚更新了小版本,来到了4.7版。
除了继续对DNN模块、算法加速优化外,算法家族也有了新成员。
下文来自:
https://github.com/opencv/opencv/wiki/ChangeLog#version470
Highlights of this release:
DNN模块改进:
New ONNX layers 增加了新的ONNX layers
Signinficant performance optimization for convolutions. Winograd algoritm implementation. 对卷积进行了重要的性能优化,实现了卷积优化算法Winograd 。
OpenVino 2022.1 support.
Added CANN backend support #22634. Link to the manual: https://github.com/opencv/opencv/wiki/Huawei-CANN-Backend. CANN 是华为开发的神经网络加速计算架构,增加CANN后端支持可以更好支持在华为硬件上的神经网络推理。
Added batched NMS for multi-class object detection. 增加batched NMS ,用于多类别目标检测。
Algorithms改进与新增:
ArUco markers and April tags support including ChAruco and diamond boards detection and calibration. AR增强现实库ArUco的进一步支持,ChAruco and diamond boards 的检测与校正。
QR code detection and decoding quality imrovement. Alignment markers support. Benchmark for QR codes: https://github.com/opencv/opencv_benchmarks/tree/develop/python_benchmarks/qr_codes
QR码的检测与校正质量改进。性能增强详见 QR 码的benchmark。
Nanotrack v2 tracker based on neural networks.
新增基于神经网络的跟踪算法Nanotrack v2。
Stackblur algoruthm implementation.
高斯模糊的高效优化算法Stackblur的实现,“StackBlur作为高斯模糊的近似计算,速度在kernel size <= 5的情况下,接近高斯模糊速度,在大kernel size情况下(如kernel size=101),速度远超高斯模糊” 详见:
https://zhuanlan.zhihu.com/p/574498840
Multimedia 实现优化:
FFmpeg 5.x support.
CUDA 12.0 support. Hardware accelerated video codecs support on NVIDIA platforms with modern Video Codec SDK (NVCUVID and NVENCODEAPI).支持CUDA 12.0,支持NVIDIA 平台的硬件加速编码。
CV_16UC1 read/write video support with FFmpeg. 支持FFmpeg 用CV_16UC1类型读写视频。
Orientation meta support on Mac with native media API.
New iterator-based API for multi-page image formats.
libSPNG support for PNG format. 支持PNG格式图像读写的libSPNG,安全、易用,且速度更快。
SIMD acceleration for self-built libJPEG-Turbo 对自建的libJPEG-Turbo 进行了SIMD加速。
H264/H265 support on Android. Multiple fixes for video decoder, endcoder and camera memory layout. Android上的H264/H265支持。
G-API
Exposed all core APIs to Python, including stateful kernels. 开发G-API的Python接口
Optimization:
New universal intrinsics backend for scalable vector instructions. The first scalable implementation for RISC-V RVV 1.0. 支持 RISC-V 指令集。