OpenCV 4.0 has relased since more than 3 years after 3.0 release. As a most wildly used CV libary which can be used to object detection, image classification, moving object detection and human face detecion. It inculds lots of machine learning and state of art computer vision algorithms. Also, it supports bunch of coding languages, like C++, java, python…
Summary of Upgrade
- C++ 11 required. Lots of C API from 1.x have removed. CMake >= 3.5.1
- New module G-API has been added. It declares image processing task in form of expressions and then submit it for execution – using a number of available backends.
- More DNN module supported.
3.1 Mask-RCNN model. Here is a guid using Tensorflow ojbect detection.
3.2 Integrated ONNX(Open Neural Network Exchange ) parser.
- Kinect Fusion algorithm has been implemented and optimized for CPU and GPU (OpenCL)
- QR code detector and decoder
- high-quality DIS dense optical flow algorithm has been moved from opencv_contrib to the video module.
- Persistence (storing and loading structured data to/from XML, YAML or JSON) in the core module has been completely reimplemented in C++ and lost the C API as well.