A privacy-focused, intelligent security camera system.

Related tags

Deep Learningsmart-sec-cam
Overview

Self-Hosted Home Security Camera System

A privacy-focused, intelligent security camera system.

Features:

  • Multi-camera support w/ minimal configuration. Supports USB cameras and the Raspberry Pi camera module.
  • Motion detection that automatically saves videos and lets you view them in the web app.
  • Encrypted in transit, both from the cameras to the server and the server to your browser.
  • Self-Hosted
  • Free and Open Source

Example screenshots

Setting up the server

Docker:

  1. Clone this repository
  2. Generate SSL certificates: ./create-certs.sh. Alternatively, you may place your own certs in the certs dir
  3. Build and run the docker containers: API_URL=<server-hostname:server-port> docker-compose up -d --build. For example, if the API was running on the host sec-cam-server and port 8444, you should use API_URL=sec-cam-server:8444

Adding a camera

Installation:

NOTE: These instructions assume you are deploying to a raspberry pi running Raspbian OS.

  1. Install the python3-opencv package and dependencies: sudo apt-get install python3-opencv libatlas-base-dev
  2. Clone this repository
  3. Install the package: cd backend && python3 -m pip install .[streamer]. If you are using the Raspberry Pi camera module, run cd backend && python3 -m pip install .[streamer,picam].
  4. Update --server_url in run.sh to point at the host you deployed the server to.
  5. In the Web UI, you should see live video from that camera.
Comments
  • CORS error with self-signed certificates

    CORS error with self-signed certificates

    Some browsers like Firefox don't like cross-origin requests to URLs using self-signed certs even if you've already trusted certificate on the UI.

    Workaround:

    In the browser you're using, load an API endpoint (something like https://:8444/rooms) and go through the "this certificate can't be trusted" warning. Then, go back to the UI and refresh the page and see if its fixed.

    bug help wanted 
    opened by scottbarnesg 5
  • Run one system

    Run one system

    Can this be ran on all on one system with just a usb camera plugged in, and being able to serve the web user interface to localhost? Also, if so, would it all be in one container, or multiple? Thanks

    question 
    opened by neu-ma-tic 2
  • Add authentication

    Add authentication

    Currently, the UI is available to anyone with network access to the host. We need to develop or integrate an authentication solution to provide login capabilities.

    enhancement 
    opened by scottbarnesg 2
  • Fix CORS issue with self-signed certificates

    Fix CORS issue with self-signed certificates

    Changes:
    • Updates Flask server to serve React app.
    • Removes unused nginx config
    • Moves frontend container to an intermediate container in server
    • Updates default server port for both the UI and API to 8443
    Testing:
    • Check out this branch
    • Generate new (untrusted) certs: ./create-certs.sh
    • Start the server: docker-compose up -d --build
    • Open the Web UI in Firefox at https://localhost:8443. After clicking through the certificate warnings, open the debug console and verify there are no CORS errors.
    • Navigate to the videos page: https://localhost:8443/videos. Verify the videos load correctly and that there are no CORS errors in the debug console.

    Closes #16

    opened by scottbarnesg 1
  • Improve motion detection algorithm

    Improve motion detection algorithm

    Currently, the motion detection algorithm performs background subtraction on the incoming video frames to detection motion. This can cause "false positives", flagging motion that we don't care about (e.g. the wind blowing tree branches)

    This should be enhanced to identify more specific "objects of interest" (e.g. a person walking by).

    enhancement help wanted 
    opened by scottbarnesg 1
  • Run camera streamer code as a systemd service

    Run camera streamer code as a systemd service

    • Adds a base .service file for running streamer as a systemd service.
    • Adds create-streamer-service.sh to configure .service file for per-system installation.
    • Updates README.md with instructions on how to install streamer service under systemd.
    opened by scottbarnesg 0
  • Improve motion detection

    Improve motion detection

    Changes:

    • Replaces background-subtraction based motion detection with contour-based approach
    • Saved videos now have a box drawn around areas in which motion is detected
    • Adds --capture-delay argument to streamer.
    • Adds a size limit to the streamer's frame capture queue.

    Closes #5

    opened by scottbarnesg 0
  • Add authentication

    Add authentication

    Tasks:

    • [x] Implement authentication logic
    • [x] Add login endpoint
    • [x] Enforce authentication on endpoints
    • [x] Integrate authentication into UI
    • [x] Cache token as a cookie
    • [x] Add mechanism to create a user
    • [x] Add /api prefix to all API endpoints
    • [x] Validate token on every page
    • [x] Implement authentication for SocketIO
    • [x] Make Login and Registration pages look acceptable
    • [x] Update README

    Closes #4

    opened by scottbarnesg 0
  • Fix docker-compose build hanging with large video directory

    Fix docker-compose build hanging with large video directory

    Changes:

    • Adds .dockerignore w/ entry to ignore video data dir

    Testing:

    • Create data/videos and put lots of data into it.
    • Check out this branch and run docker-compose build server
    • Verify the command does not hang

    Fixes #20

    opened by scottbarnesg 0
  • Update image transmission to use a video stream

    Update image transmission to use a video stream

    References:

    • https://pericror.com/software/python-create-a-webrtc-video-stream-from-images/
    • https://github.com/aiortc/aiortc
    • https://pypi.org/project/av/
    enhancement 
    opened by scottbarnesg 0
  • Redesign the UI

    Redesign the UI

    The existing UI provides minimal functionality and needs an overhaul

    Key changes:

    • Update video stream page to allow clicking on stream to increase its size on the page. Possible reduce non-selected videos to side-bar.
    • Update the video replay page to make videos searchable by date, time, camera id, etc.
    enhancement help wanted 
    opened by scottbarnesg 0
Releases(0.3.6)

  • 0.3.6(Nov 19, 2022)

  • 0.3.5(Sep 11, 2022)

  • 0.3.4(Aug 11, 2022)

  • 0.3.3(Aug 3, 2022)

    • Updates UI to automatically refresh session token before it expires.
    • Automatically redirects the UI to the login page if token validation fails.
    Source code(tar.gz)
    Source code(zip)

  • 0.3.2(Jul 31, 2022)

    • Improves motion detection algorithm, replacing background subtraction with contour-based algorithm.
    • Recorded videos now have a box drawn around the area of motion detected.
    • Moves motion detection threshold value from input argument to environment variable
    Source code(tar.gz)
    Source code(zip)

  • 0.3.1(Jul 24, 2022)

  • 0.3.0(Jul 23, 2022)

  • 0.2.9(Jun 20, 2022)

  • 0.2.8(Jun 20, 2022)

  • 0.2.7(May 3, 2022)

  • 0.2.6(Apr 24, 2022)

  • 0.2.5.a(Apr 22, 2022)

  • 0.2.4(Apr 21, 2022)

  • 0.2.3(Mar 28, 2022)

    • Makes the motion detection threshold configurable via the cli
    • Fixes an issue that caused docker-compose to hang with a large video data directory
    Source code(tar.gz)
    Source code(zip)

  • 0.2.2(Mar 27, 2022)

    • Fixes an issue that caused CORS errors in some browsers when using self-signed certificates.
    • Updates the server configuration to serve both the Web UI and API from the Flask server.
    • Updates the default server listening port to 8443 for both the web app and API.
    Source code(tar.gz)
    Source code(zip)

  • 0.2.1(Mar 21, 2022)

    • Bug fixes for the motion detection algorithm.
    • Updates the list of saved videos to display in order w/ most recent first.
    • Adds support for dynamically setting the API url in the UI at runtime
    • Updates frontend docker container to Node v16
    Source code(tar.gz)
    Source code(zip)
Owner
Scott Barnes
Software Engineer
Scott Barnes
GitHub Repository
Experiments with Fourier layers on simulation data.

Factorized Fourier Neural Operators This repository contains the code to reproduce the results in our NeurIPS 2021 ML4PS workshop paper, Factorized Fo

Alasdair Tran 57 Dec 25, 2022
SCALoss: Side and Corner Aligned Loss for Bounding Box Regression (AAAI2022).

SCALoss PyTorch implementation of the paper "SCALoss: Side and Corner Aligned Loss for Bounding Box Regression" (AAAI 2022). Introduction IoU-based lo

TuZheng 20 Sep 07, 2022
Time-series-deep-learning - Developing Deep learning LSTM, BiLSTM models, and NeuralProphet for multi-step time-series forecasting of stock price.

Stock Price Prediction Using Deep Learning Univariate Time Series Predicting stock price using historical data of a company using Neural networks for

Abdultawwab Safarji 7 Nov 27, 2022
Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)

Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)

Yihui He 1k Jan 03, 2023
Practical Single-Image Super-Resolution Using Look-Up Table

Practical Single-Image Super-Resolution Using Look-Up Table [Paper] Dependency Python 3.6 PyTorch glob numpy pillow tqdm tensorboardx 1. Training deep

Younghyun Jo 116 Dec 23, 2022
A clear, concise, simple yet powerful and efficient API for deep learning.

The Gluon API Specification The Gluon API specification is an effort to improve speed, flexibility, and accessibility of deep learning technology for

Gluon API 2.3k Dec 17, 2022
🇰🇷 Text to Image in Korean

KoDALLE Utilizing pretrained language model’s token embedding layer and position embedding layer as DALLE’s text encoder. Background Training DALLE mo

HappyFace 74 Sep 22, 2022
SlotRefine: A Fast Non-Autoregressive Model forJoint Intent Detection and Slot Filling

SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling Reference Main paper to be cited (Di Wu et al., 2020) @article

Moore 34 Nov 03, 2022
Have you ever wondered how cool it would be to have your own A.I

Have you ever wondered how cool it would be to have your own A.I. assistant Imagine how easier it would be to send emails without typing a single word, doing Wikipedia searches without opening web br

Harsh Gupta 1 Nov 09, 2021
Python package for visualizing the loss landscape of parameterized quantum algorithms.

orqviz A Python package for easily visualizing the loss landscape of Variational Quantum Algorithms by Zapata Computing Inc. orqviz provides a collect

Zapata Computing, Inc. 75 Dec 30, 2022
In generative deep geometry learning, we often get many obj files remain to be rendered

a python prompt cli script for blender batch render In deep generative geometry learning, we always get many .obj files to be rendered. Our rendered i

Tian-yi Liang 1 Mar 20, 2022
Speech Emotion Recognition with Fusion of Acoustic- and Linguistic-Feature-Based Decisions

APSIPA-SER-with-A-and-T This code is the implementation of Speech Emotion Recognition (SER) with acoustic and linguistic features. The network model i

kenro515 3 Jan 04, 2023
[ICLR 2022] Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics

CPDeform Code and data for paper Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics at ICLR 2022 (Spotlight). @InProceed

(Lester) Sizhe Li 29 Nov 29, 2022
"Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices", official implementation

Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices This repository contains the official PyTorch implemen

Yandex Research 21 Oct 18, 2022
Diverse Object-Scene Compositions For Zero-Shot Action Recognition

Diverse Object-Scene Compositions For Zero-Shot Action Recognition This repository contains the source code for the use of object-scene compositions f

7 Sep 21, 2022
In this project, we'll be making our own screen recorder in Python using some libraries.

Screen Recorder in Python Project Description: In this project, we'll be making our own screen recorder in Python using some libraries. Requirements:

Hassan Shahzad 4 Jan 24, 2022
A small demonstration of using WebDataset with ImageNet and PyTorch Lightning

A small demonstration of using WebDataset with ImageNet and PyTorch Lightning This is a small repo illustrating how to use WebDataset on ImageNet. usi

50 Dec 16, 2022
Hydra Lightning Template for Structured Configs

Hydra Lightning Template for Structured Configs Template for creating projects with pytorch-lightning and hydra. How to use this template? Create your

Model-driven Machine Learning 4 Jul 19, 2022
Joint-task Self-supervised Learning for Temporal Correspondence (NeurIPS 2019)

Joint-task Self-supervised Learning for Temporal Correspondence Project | Paper Overview Joint-task Self-supervised Learning for Temporal Corresponden

Sifei Liu 167 Dec 14, 2022
Consensus Learning from Heterogeneous Objectives for One-Class Collaborative Filtering

Consensus Learning from Heterogeneous Objectives for One-Class Collaborative Filtering This repository provides the source code of "Consensus Learning

SeongKu-Kang 6 Apr 29, 2022