Reporting and Visualization for Hazardous Events

Overview

IncidenceReporting

Reporting and Visualization for Hazardous Events

Web Page

Problem Statement

Create a solution that spreads awareness of, visualizes the importance of, and/or decreases the time-to-action of safety-related incidents or topics.

Example safety-related incidents: 1) Identification and reporting of tripping hazards 2) Personnel near heavy machinery 3) Escape of toxic gases

Map Visualization

Solution

Video data is collected to detect if someone has fallen, or if personnel are too near heavy machinery, or if another safety-related incident has happened. If someone is too near heavy machinery, a notification will be sent out to them. Additionally, we have a webpage to visualize safety incidents geographically and topically, and we also have a place for people to write anonymous incidence reports.

Pose Estimation

Description

Inspiration for your submission

  • Our inspiration came from Conoco Phillip's Spirit Values. We wanted to create something that represented these values and we believe our application does an excellent representation.
  • SAFETY - Safety is the core idea of our application. We wanted to provide an objective solution to safety.
  • PEOPLE - The people are what drives this application. We gave them the power to view and upload data.
  • INTEGRITY - Integrity is extremely important and this application provides transparency to our people.
  • RESPONSIBILITY - We believe everyone is responsible and this will provide employees with more accountability.
  • INNOVATION - Innovation is what powers this application our fall detection will help us identify safety issues throughout Conoco Phillips.
  • TEAMWORK - Together we can create technology to keep us safe and responsible.

What your submission does

  • Tripping hazards and heavy machinery incident reporting web app
  • Automatic incident reporting
  • Automatic fall detection and reporting using ML
  • Fall recording logging using EchoAR

How you built it

  • Streamlit
  • python
  • C++
  • Firebase

Challenges that you ran into, and how you overcame them

  • Machine Learning Model was tricky to set up
  • Map was not working for a long time

Accomplishments that you're proud of

  • Elegant UI
  • Email integration
  • Pose Estimation

What's next for your product?

  • Integration with CCTV cameras
  • adapt the solution to companies other than ConocoPhillips. We feel our solution can be applied to any company with workplace safety issues
  • Our team split up the work to most efficiently produce a working front end and back end. The front end of our product was constructed using Streamlit, which is a web-app framework that writes markdown from python. This allowed us to easily construct forms and display data in a visually easy-to-digest way for the user. Our data would be stored on a local SQL database such as MySQL, which was able to communicate with our product through the MySQL-Connector python library. Finally, our product also includes a machine learning model that can detect incidents and automatically report them and store the data in the database.

Challenges that you ran into, and how you overcame them

  • We faced adversities when attempting to integrate the different parts of our product such as the database, machine learning, and the front-end data visualization components.

Accomplishments that you're proud of

  • We are proud of producing a Minimum Viable Product that we could showcase to the company and that we believe suits a broad set of use-cases.

What's next for your product?

  • In the future, we hope to update our product in terms of specificity and scale. Some ideas that encompass this could include more incident types and more complex query abilities for the user.

Running the app

streamlit run main.py

Running Machine Learning Algorithm

cd Human-Falling-Detect-Tracks/
python main.py --device=cpu
Owner
Jv Kyle Eclarin
snakes and letters
Jv Kyle Eclarin
Food Drinks and groceries Images Multi Lingual (FooDI-ML) dataset.

Food Drinks and groceries Images Multi Lingual (FooDI-ML) dataset.

41 Jan 04, 2023
A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines

A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines Understanding the results of deep neural networks is

Johan van den Heuvel 2 Dec 13, 2021
TDN: Temporal Difference Networks for Efficient Action Recognition

TDN: Temporal Difference Networks for Efficient Action Recognition Overview We release the PyTorch code of the TDN(Temporal Difference Networks).

Multimedia Computing Group, Nanjing University 326 Dec 13, 2022
A pytorch reprelication of the model-based reinforcement learning algorithm MBPO

Overview This is a re-implementation of the model-based RL algorithm MBPO in pytorch as described in the following paper: When to Trust Your Model: Mo

Xingyu Lin 93 Jan 05, 2023
N-Omniglot is a large neuromorphic few-shot learning dataset

N-Omniglot [Paper] || [Dataset] N-Omniglot is a large neuromorphic few-shot learning dataset. It reconstructs strokes of Omniglot as videos and uses D

11 Dec 05, 2022
PyTorch implementation of the paper Dynamic Data Augmentation with Gating Networks

Dynamic Data Augmentation with Gating Networks This is an official PyTorch implementation of the paper Dynamic Data Augmentation with Gating Networks

九州大学 ヒューマンインタフェース研究室 3 Oct 26, 2022
An open-source Kazakh named entity recognition dataset (KazNERD), annotation guidelines, and baseline NER models.

Kazakh Named Entity Recognition This repository contains an open-source Kazakh named entity recognition dataset (KazNERD), named entity annotation gui

ISSAI 9 Dec 23, 2022
Implementation of paper: "Image Super-Resolution Using Dense Skip Connections" in PyTorch

SRDenseNet-pytorch Implementation of paper: "Image Super-Resolution Using Dense Skip Connections" in PyTorch (http://openaccess.thecvf.com/content_ICC

wxy 114 Nov 26, 2022
A new video text spotting framework with Transformer

TransVTSpotter: End-to-end Video Text Spotter with Transformer Introduction A Multilingual, Open World Video Text Dataset and End-to-end Video Text Sp

weijiawu 67 Jan 03, 2023
API for RL algorithm design & testing of BCA (Building Control Agent) HVAC on EnergyPlus building energy simulator by wrapping their EMS Python API

RL - EmsPy (work In Progress...) The EmsPy Python package was made to facilitate Reinforcement Learning (RL) algorithm research for developing and tes

20 Jan 05, 2023
Black-Box-Tuning - Black-Box Tuning for Language-Model-as-a-Service

Black-Box-Tuning Source code for paper "Black-Box Tuning for Language-Model-as-a-Service". Being busy recently, the code in this repo and this tutoria

Tianxiang Sun 149 Jan 04, 2023
Code for CVPR 2018 paper --- Texture Mapping for 3D Reconstruction with RGB-D Sensor

G2LTex This repository contains the implementation of "Texture Mapping for 3D Reconstruction with RGB-D Sensor (CVPR2018)" based on mvs-texturing. Due

Fu Yanping(付燕平) 129 Dec 30, 2022
Progressive Coordinate Transforms for Monocular 3D Object Detection

Progressive Coordinate Transforms for Monocular 3D Object Detection This repository is the official implementation of PCT. Introduction In this paper,

58 Nov 06, 2022
AirLoop: Lifelong Loop Closure Detection

AirLoop This repo contains the source code for paper: Dasong Gao, Chen Wang, Sebastian Scherer. "AirLoop: Lifelong Loop Closure Detection." arXiv prep

Chen Wang 53 Jan 03, 2023
Code for "Training Neural Networks with Fixed Sparse Masks" (NeurIPS 2021).

Fisher Induced Sparse uncHanging (FISH) Mask This repo contains the code for Fisher Induced Sparse uncHanging (FISH) Mask training, from "Training Neu

Varun Nair 37 Dec 30, 2022
On-device speech-to-index engine powered by deep learning.

On-device speech-to-index engine powered by deep learning.

Picovoice 30 Nov 24, 2022
A highly modular PyTorch framework with a focus on Neural Architecture Search (NAS).

UniNAS A highly modular PyTorch framework with a focus on Neural Architecture Search (NAS). under development (which happens mostly on our internal Gi

Cognitive Systems Research Group 19 Nov 23, 2022
modelvshuman is a Python library to benchmark the gap between human and machine vision

modelvshuman is a Python library to benchmark the gap between human and machine vision. Using this library, both PyTorch and TensorFlow models can be evaluated on 17 out-of-distribution datasets with

Bethge Lab 244 Jan 03, 2023
YouRefIt: Embodied Reference Understanding with Language and Gesture

YouRefIt: Embodied Reference Understanding with Language and Gesture YouRefIt: Embodied Reference Understanding with Language and Gesture by Yixin Che

16 Jul 11, 2022
GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training @ KDD 2020

GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training Original implementation for paper GCC: Graph Contrastive Coding for Graph Neural N

THUDM 274 Dec 27, 2022