NJ-HEVC's repositories
google-research
Google Research
Bilibili-plus
课程视频、PPT和源代码:侯捷C++系列;台大郭彦甫MATLAB
screen-capture-recorder-to-video-windows-free
a free open source windows "screen capture" device and recorder (also allows VLC/ffmpeg and others to capture/stream desktop/audio)
opencv
Open Source Computer Vision Library
pydicom
Read, modify and write DICOM files with python code
kvazaar
An open-source HEVC encoder
invesalius3
3D medical imaging reconstruction software
AndroidOsdDemo
基于Android NDK Osd实现,利用了SDL2_TTF把矢量字体转成bmp格式,然后把bmp转换成yuv格式,在YUV数据上做OSD叠加。
YUView
The Free and Open Source Cross Platform YUV Viewer with an advanced analytics toolset
bgslibrary
A C++ Background Subtraction Library with wrappers for Python, MATLAB, Java and GUI on QT
HEVC-CU-depths-prediction-CNN
Using convolutional neural networks to predict the Coding Units (CUs) depths in HEVC intra-prediction mode, in order to reduce the time of the encoding process in HEVC.
VQMT
VQMT: Video Quality Measurement Tool. Fast implementations of the following objective image quality metrics: PSNR, SSIM, MS-SSIM, VIFp, PSNR-HVS and PSNR-HVS-M.
Image-Compression-Based-On-ROI
Medical Image Compression Based On ROI (Reason of Interest)
radiomics
MATLAB programming tools for radiomics analysis
HIF-Database
A large-scale database for HEVC in-loop filter (HIF).
Image_Processing_HCMUS
Geometric Transform - Color Transformer - Edge Dectector (prewitt, laplace, sobel)
h264-roi
H.264 video Region of Interest encoding tool, using x264
MRI-QA
The assessment of quality of MRI is in important precursor to ameliorating biases in subsequent data analysis and precluding erroneous acquisitions. Since manual visual inspection is impractical for large volumes of data, as well as being subjective in nature, it is very useful to automate the task of image quality assessment (IQA). There is existing research on IQA, that typically utilize hand-crafted visual features in conjunction with machine learning algorithms. However, these techniques have been made obsolete in many research fields by much more powerful and expressive deep learning based models. We introduce a model that uses a Convolutional Neural Network for feature extraction from 3D volumes of MRI data of a subject and a Fully Connected Network for classification of the quality of the MRI. This model is trained on a multi-site freely available dataset, called ABIDE 1, used in study of Autism. By utilizing two of the seventeen sites as hold-out data, we demonstrate that our model achieves state-of-art performance on unseen data from novel sites. Furthermore, we evaluate our trained model on a MRI dataset from TCIA, used in study of Glioblastoma, to demonstrate the ability of our model to effectively adapt to different types of neuro-imaging data.
A-content-adaptive-Rate-Control-algorithm-implementation
To explore the Content Adaptive Encoding, I try to implement a GOP-level rate Control solution
HEVC-Complexity-Reduction
Source programs to test the deep-learning-based complexity reduction approach for HEVC, at both intra- and inter-modes.
libbpg
libbpg (copy of the source code for easy access)
TiAndSiCmd
计算视频ti及si信息,支持跨平台编译
YUVPlayer
A little simple YUV player.windows VS2010 MFC project (Windows 7 64bit),support manyYUV format file.
saliency
Code for http://saliency.mit.edu/
OpenCV_Select_Non_Rect_ROI
Select non rectangular ROI in video
rate-control-tests
Tests for different rate control modes in x264
PyEdge
Implements the Sobel, Roberts, and Prewitt edge detection operators.
multi-rate-x265
Multi-rate HEVC encoder based on x265 2.0 that implements a CU structure reuse from a high-quality reference to lower-quality dependent encodings, as described in: D. Schroeder, P. Rehm, and E. Steinbach, "Block structure reuse for multi-rate High Efficiency Video Coding", Proc. IEEE ICIP 2015, Sep. 2015, Québec, Canada.