https://github.com/AKSHAYUBHAT/DeepVideoAnalytics

Python
A highly configurable visual search & analytics platform for images and videos.

Deep Video Analytics •

Don't be worried by complexity of this banner, with latest version of docker installed correctly, you can run Deep Video Analytics in minutes locally (even without a GPU) using a single command.

Author: Akshay Bhat, Cornell University.

Deep Video Analytics is a platform for indexing and extracting information from videos and images. For installation instructions & demo go to https://deepvideoanalytics.com

Libraries & Code used

• Pytorch License
• Darknet License
• AdminLTE2 License
• FabricJS License
• Modified PySceneDetect License
• Modified SSD-Tensorflow Individual files are marked as Apache
• Yahoo LOPQ Apache License 2.0
• FAISS License (Non Commercial)
• Facenet License
• MTCNN TensorFlow port of MTCNN for face detection/alignment
• Locally Optimized Product Quantization License
• Docker
• JSFeat not used but included
• Segment annotator Not used but inclued
• Nvidia-docker
• OpenCV
• Numpy
• FFMPEG
• Tensorflow

License & Copyright

Copyright 2016-2017, Akshay Bhat, Cornell University, All rights reserved.

Please contact me for more information, I plan on relaxing the license soon, once a beta version is reached (To the extent allowed by the code/models included. e.g. FAISS disallows commercial use.).