As a big fan of OPENCV 3.3.0 There is what is new! Some my notes about new released. Based on changelog and released notes. Deep neural network module is now accelerated with improved performance also moved into the main repository branch under opencv /modules/dnn . This module is also no more available in contrib branch. There was improved loading models from Troch and TensorFlow and many performance improvements. Support of Caffe 1 TensorFlow Torch/PyTorch Interesting is available layer types list AbsVal AveragePooling BatchNormalization Concatenation Convolution (including dilated convolution) Crop Deconvolution, a.k.a. transposed convolution or full convolution DetectionOutput (SSD-specific layer) Dropout Eltwise (+, *, max) Flatten FullyConnected LRN LSTM MaxPooling MaxUnpooling MVN NormalizeBBox (SSD-specific layer) Padding Permute Power PReLU (including ChannelPReLU with channel-specific sl

The blog is full of OpenCV source code, tutorials, tips, tricks, and from basics to advanced streaming and video processing. The code examples are from C++. Most of the tutorials are dedicated to basics C++ OpenCV image processing, people detection from LBP haar cascades to modern deep learning. The tutorials are as well dealing with GStreamer OpenCV integration to be able to stream OpenCV output as a video stream to the web.