Giter VIP home page Giter VIP logo

fullstackhan / deepstream_360_d_smart_parking_application Goto Github PK

View Code? Open in Web Editor NEW

This project forked from nvidia-ai-iot/deepstream_360_d_smart_parking_application

0.0 2.0 0.0 62.28 MB

Describes the full end to end smart parking application that is available with DeepStream 3.0

License: MIT License

Dockerfile 0.65% Shell 1.74% JavaScript 36.79% Scala 13.40% Java 0.01% Python 34.17% HTML 0.55% CSS 12.68%

deepstream_360_d_smart_parking_application's Introduction

DeepStream 3.0 - 360 Degree Smart Parking Application

Architecture

This document describes the full end to end smart parking application that is available with DeepStream 3.0. The above architecture provides a reference to build distributed and scalable DeepStream applications.

Note: The perception server only supports DeepStream 3.0 and will not work with DeepStream 4.0. We will release a compatible 4.0 example soon.

Introduction

The perception capabilities of a DeepStream application can now seamlessly be augmented with data analytics capabilities to build complete solutions, offering rich data dashboards for actionable insights. This bridging of DeepStream’s perception capabilities with data analytics frameworks is particularly useful for applications requiring long term trend analytics, global situational awareness, and forensic analysis. This also allows leveraging major Internet of Things (IOT) services as the infrastructure backbone.

The data analytics backbone is connected to DeepStream applications through a distributed messaging fabric. DeepStream 3.0 offers two new plugins, gstnvmsgconv and gstnvmsgbroker, to transform and connect to various messaging protocols. The protocol supported in this release is Kafka.

To build an end to end implementation of the Analytics layer, DeepStream 3.0 uses open source tools and frameworks that can easily be reproduced for deployment on an on-premise server or in the Cloud. The framework comprises stream and batch processing capabilities. Every component of the Analytics layer, Message Broker, Streaming, NoSQL, and Search Indexer can be horizontally scaled. The streaming analytics pipeline can be used for processes like anomaly detection, alerting, and computation of statistics like traffic flow rate. Batch processing can be used to extract patterns in the data, look for anomalies over a period of time, and build machine learning models. The data is kept in a NoSQL database for state management, e.g. the occupancy of a building, activity in a store, or people movement in a train station. This also provides the capability for forensic analytics, if needed. The data can be indexed for search and time series analytics. Information generated by streaming and batch processing is exposed through a standard API for visualization. The API can be accessed through REST, WebSocket, or messaging, based on the use case. The user interface allows the user to consume all the relevant information. Deployment is based on an open source technology stack. The modules and technology stack are shown with respect to the Streaming Data pipeline.

Getting Started

To get started, clone this repository by either clicking the download button on top right corner, or using the command

git clone https://github.com/NVIDIA-AI-IOT/deepstream_360_d_smart_parking_application.git

To run this application, the user needs to start the following docker containers:

  1. Analytics Server: Check the README inside analytics_server_docker directory and follow the steps to start the docker containers.
  2. Perception Server: Check the README inside perception_docker directory and follow the steps to start the docker container.

Other modules included in this application are as follows:

  1. Apis
  2. Stream
  3. Tracker
  4. Ui

deepstream_360_d_smart_parking_application's People

Contributors

aiyerganapathy avatar sujitbiswas avatar

Watchers

 avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.