awesome-cv

Index

• General Sources(Computer Vision)

• Digital Image Processing

• Deep Learning

  • General
  • Networks
    • Convolutional Neural Networks
    • Generative Adversarial Networks
    • Recurrent Neural Networks
    • Autoencoders
    • Graph Convolutional Networks
    • Temporal Convolutional Networks
  • Problems
    • Object Detection
    • Image Segmentation
    • Pose Estimation
    • Anomaly Detection

• Math

• Datasets

• Photography and Camera Specs

• Stereo Vision

• 3D Laser Scanning and Structured Light

• Photogrammetry and 3D Reconstruction

• OCR

• Video Streaming

• Production Level

• IoT

• OOP

• Linux

• Algorithms(General)

• Tools

• Mix of interesting and cool stuff

General Sources(Computer Vision)

• Computer Vision for Visual Effects (ECSE-6969) Lectures Spring 2014

• The Ancient Secrets of Computer Vision

• First Principles of Computer Vision Youtube Channel

• Autonomous Vision Group, CVPR 2020 Keynote Talks

• Cyrill Stachniss Youtube Channel

Digital Image Processing

• Intro to Digital Image Processing (ECSE-4540) Lectures, Spring 2015

• Image Processing: What are occlusions?

• Ordering coordinates clockwise with Python and OpenCV

• OpenCV Object Tracking

• Principal Component Analysis

• Optical Flow in OpenCV (C++/Python)

• Faster alternatives for calcOpticalFlowSF

• Principal Component Analysis | LearnOpenCV

• Caire: a content aware image resize library

Deep Learning

General

• Neural Networks and Deep Learning(Book)

• Machine Learning & Deep Learning Fundamentals

• Dive into Deep Learning

• Deep Learning Materials by Deep Learning Wizard

• The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

• Awesome-Pytorch-list

• Effect of Batch Size on Neural Net Training

• How to avoid machine learning pitfalls: a guide for academic researchers

• Mind Mapping for Depth Estimation

• A Brief Overview of Loss Functions in Pytorch

Networks

• Convolutional Neural Networks

  • Lecture Collection | Convolutional Neural Networks for Visual Recognition(Stanford)

  • Convolutional Neural Networks(Stanford Lecture Notes)

  • Intuitively Understanding Convolutions for Deep Learning

  • CNN Explainer: Learn Convolutional Neural Network (CNN) in your browser!

  • Lecture Collection | Convolutional Neural Networks for Visual Recognition (Spring 2017)

  • How Convolutional Neural Networks work

  • How convolutional neural networks work, in depth

  • Convolutional Neural Networks for Visual Recognition (Spring 2017)

  • What is the vanishing gradient problem?

  • Deep Residual Learning for Image Recognition (Paper Explained)

  • Convolution arithmetic

  • Transposed Convolution Demystified

  • A Gentle Introduction to Batch Normalization for Deep Neural Networks

  • What is skip architecture in CNN?

  • Comprehensive look at 1X1 Convolution in Deep Learning

• Generative Adversarial Networks

  • A Friendly Introduction to Generative Adversarial Networks

  • Image Deblurring using Generative Adversarial Networks

• Recurrent Neural Networks

  • Recurrent Neural Networks - EXPLAINED!

  • MIT 6.S191: Recurrent Neural Networks

  • Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM)

  • An introduction to ConvLSTM

  • What is the difference between ConvLSTM and CNN LSTM?

  • Video Classification with CNN, RNN, and PyTorch

  • PyTorch Implementation of ConvLSTM Cell

  • The Unreasonable Effectiveness of Recurrent Neural Networks

• Autoencoders

  • An Introduction to Autoencoders: Everything You Need to Know

  • Comprehensive Introduction to Autoencoders

  • What is the main difference between GAN and autoencoder?

  • Building Autoencoders in Keras

• Graph Convolutional Networks

  • Getting the Intuition of Graph Neural Networks

  • Understanding Graph Convolutional Networks for Node Classification

• Temporal Convolutional Networks

  • Temporal Convolutional Networks and Forecasting

Problems

• Object Detection

  • Zero to Hero: Guide to Object Detection using Deep Learning: Faster R-CNN,YOLO,SSD

  • awesome-object-detection

  • Non-maximum Suppression (NMS)

  • Selective Search for Object Detection | R-CNN

  • PyTorch Tutorial to Object Detection.(SSD)

  • Object Detection Accuracy (mAP) Cheat Sheet

  • Tackling the Small Object Problem in Object Detection

  • YOLOv4 - Ten Tactics to Build a Better Model

  • The Power of Tiling for Small Object Detection

  • An Improved Faster R-CNN for Small Object Detection

  • Real-time Hand-Detection using Neural Networks (SSD) on Tensorflow

  • Object Detection with RetinaNet(Keras)

  • DeepSORT: Deep Learning to Track Custom Objects in a Video

• Image Segmentation

  • What is Semantic Segmentation, Instance Segmentation, Panoramic segmentation?

  • Understanding Deep Learning Techniques for Image Segmentation

  • Comparison of Fully Convolutional Networks (FCN) and U-Net for Road Segmentation from High Resolution Imagerie

  • Fully Convolutional Networks for Semantic Segmentation(Paper)

  • A survey of loss functions for semantic segmentation

• Pose/Gaze Estimation

  • Real time human head pose estimation using TensorFlow and OpenCV

  • GazeFollow: Where are they looking?(2015)

  • Where are they looking? PyTorch Implementation

  • Believe It or Not, We Know What You Are Looking at!(Paper-2018)

  • Believe It or Not, We Know What You Are Looking at!(PyTorch Implementation)

• Anomaly Detection

  • Intro to anomaly detection with OpenCV, Computer Vision, and scikit-learn

  • Anomaly detection with Keras, TensorFlow, and Deep Learning

  • A One-Stage Approach for Surface Anomaly Detection with Background Suppression Strategies

  • DEEP LEARNING FOR ANOMALY DETECTION: A SURVEY

Loss Functions

• Binary Cross Entropy/Log Loss for Binary Classification

Math

• Essence of linear algebra

• But what is a partial differential equation?

• The gradient

• Gradient Descent Derivation

• How Gradient Descent Works?

• Intuitive crutches for higher dimensional thinking

• Eigenvectors and eigenvalues

• Making sense of principal component analysis, eigenvectors & eigenvalues(<3)

• Find a point on a rotated rectangle with known angle

• How a Kalman filter works, in pictures

• Kalman and Bayesian Filters in Python

Datasets

• Middlebury Stereo Datasets

• VisDrone Aerial Dataset

• HMDB: a large human motion database

• UCF101 – Action Recognition Data Set

• CelebFaces Attributes Dataset (CelebA)

• Kinetics: large-scale, high-quality human actions dataset

• COCO: common objects in context dataset

• DOTA: Dataset for Object Detection in Aerial Images

• xView: overhead imagery dataset

Photography and Camera Specs

• Angle of view

• What Is Exposure? (A Beginner’s Guide)

• Rolling Shutter vs Global Shutter: What’s the difference?

• EXPOSURE TRIANGLE: APERTURE, ISO & SHUTTER SPEED

• What are Global Shutter and Rolling shutter? How to choose the one that fits the application?

• What Is Focal Length in Photography?

• Focal Length vs Effective Focal Length

• What is a pinhole camera?

• What is Lens Distortion?

Stereo Vision

• Object Distance Measurement By Stereo Vision

• Variants of depth cameras

• Image Rectification

• ActiveStereoNet: The first deep learning solution for active stereo systems

• What Is Camera Calibration?

• Camera Calibration Video Series

• CS6320: 3D Computer Vision Project 2 Stereo and 3D Reconstruction from Disparity

• 3D, Depth Perception, and Stereo(The Ancient Secrets of Computer Vision )

• A High-Precision Calibration Method for Stereo Vision System

• Epipolar geometry

• Stereo Correspondence Algorithms

• Middlebury Stereo Vision Page

• Multiple View Geometry in Computer Vision Second Edition

• A video that includes techniques for improvement accuracy of stereo system precision

• How to verify the correctness of calibration of a webcam?

• Is reprojection error enough in stereo calibration?

• Does a smaller reprojection error always means better calibration?

• What to Expect from a Stereo Vision System

• The Depth I: Stereo Calibration and Rectification(OpenCV)

• The Depth II: Block Matching(OpenCV)

• Calibration of Stereo Cameras for Mobile Robots

• Disparity map post-filtering

• Effect of Baseline On Stereo Vision Systems

• How field of view changes depth estimation in stereo vision?

• Design parameters for adjusting the visual field of binocular stereo cameras

• Large-Field-of-View Stereo for Automotive Applications

• Easily Create a Depth Map with Smartphone AR

• Choosing Good Stereo Parameters

• Camera Projection

3D Laser Scanning and Structured Light

• CVFX Lecture 24: Structured light scanning

• Third Dimension Youtube Channel

• Udacity Structured light

• I3D Past Projects Youtube Channel

• FabScan PI - An Open-Source 3D Laser Scanner

Photogrammetry and 3D Reconstruction

• Zhaoyang Wang's Homepage

• AliceVision Framework

• PCL(Point Cloud Library)

• Open3D: A Modern Library for 3D Data Processing

• Andreas Geiger Youtube Channel

• 3d Scan Anything Using Just a Camera

• Deep Learning for “Exotic” Data Like 3D Meshes and Point-Clouds

OCR

• A comprehensive guide to OCR with Tesseract, OpenCV and Python

• A synthetic data generator for text recognition

• Python-based tools for document analysis and OCR

• Building Custom Deep Learning Based OCR models

Video Streaming

• GStreamer Tutorials

• Repo of collected sources and projects related to GStreamer

• FFmpeg plugin for Flutter

• Gstreamer command-line cheat sheet

• GStreamer UDP stream examples

• RTSP test stream URL(Big Buck Bunny): rtsp://wowzaec2demo.streamlock.net/vod/mp4:BigBuckBunny_115k.mov

• Install All Essential Media Codecs in Ubuntu With This Single Command

• What’s the Difference Between Codecs & Containers?

• Gstreamer basic real time streaming tutorial

• Stream Video using Gstreamer RTSP Server

• The All You Need Guide to Video Codecs and Compression

• Accelerated GStreamer User Guide

• How to Build Gstreamer RTSP Server

• How to setup an RTSP server on Headless Raspberry Pi and stream RPi Camera data using GStreamer?

• Video streaming from Raspberry PI - Python vs. raspivid + netcat

• complete list of ffmpeg flags / commands

Production Level

• Optimizing TensorFlow Models for Serving (Google Cloud AI Huddle)

• Implementing YOLOv4 with TensorFlow, TFLite and TensorRT

• How to Build Object Detection APIs Using TensorFlow and Flask

• An introduction to MLOps on Google Cloud

• Accelerating Machine Learning App Development with Kubeflow Pipelines (Cloud Next '19)

• TensorFlow Lite Flutter Plugin

• FFmpeg plugin for Flutter

• NVIDIA Jetson Nano and NVIDIA Jetson AGX Xavier for Kubernetes (K8s) and machine learning (ML) for smart IoT

• Submit it!: a lightweight tool for submitting Python functions for computation within a Slurm cluster

• Curated papers, articles, and blogs on data science & machine learning in production

• MLfLow: Open source platform for the machine learning lifecycle

• Best 8 Machine Learning Model Deployment Tools That You Need to Know

• Jetson-Inference: AI Deployment Library & Guide

• Designing and Testing PyZMQ Applications

• A friendly introduction to machine learning compilers and optimizers

• How to consume C++ code in Swift

IoT

• Eclipse Mosquitto - An open source MQTT broker

• MQTT client/broker using Python asynchronous I/O

• Zetta: An API-first, open source software platform for the Internet of Things.

• ØMQ - The Guide

• Designing and Testing PyZMQ Applications

OOP

• Interfaces and Metaclasses in Python

• Actor Model Design Pattern(Python)

Linux

• Renaming files in a folder to sequential numbers

• How to Connect to a Raspberry Pi Remotely via SSH

• DebuggingWithGdb

• How to fix a broken package, when “apt-get install -f” does not work?

• Linux From Scratch

• How do I make a RAM disk?

• Better Than Top: 7 System Monitoring Tools for Linux to Keep an Eye on Vital System Stats

• Sharing WiFi Connection over Ethernet on Ubuntu 18.04

• How to check if port is in use on Linux or Unix

• Randomly copy certain amount of certain file type from one directory into another

Algorithms

• Robust peak detection algorithm (using z-scores)

• DeepSORT: Deep Learning to Track Custom Objects in a Video

Tools

• Optuna - A hyperparameter optimization framework

• A Neural Network Playground

• Make Sense - Image Annotation Tool

• Netron - Neural Network Viewer

• Lens Focal Length and Stereo Baseline Calculator

• Lightning: The ultimate PyTorch research framework

• FiftyOne: The open-source tool for building high-quality datasets and computer vision models

• youtube-dl: Command-line program to download videos from YouTube.com and other video sites

• gradio: Demos for your ML Models

• MLOps-Basics

• pytest: helps you write better programs

Mix of interesting and cool stuff

• Human Vision

• Mercedes-Benz MAGIC BODY CONTROL | S-Class

• LiDAR vs Computer Vision - Why Tesla Autonomy Will Win

• How AI Powers Self-Driving Tesla with Elon Musk and Andrej Karpathy

• Andrej Karpathy - AI for Full-Self Driving at Tesla

• OpenPilot

• Yannic Kilcher Youtube Channel