Helping People with Visual Impairment to Easily Use Buses through Computer Vision

Helping People with Visual Impairment to Easily Use Buses through Computer Vision

In this 8-weeks challenge, 50 collaborators worked on solving a significant daily-life mobility & orientation challenge for people who are blind or visually impaired using AI solutions

 

 

The Problem

People with visual impairment face an enormous amount of challenges daily. One of the biggest challenges is in orientation & mobility – the ability to walk safely and accurately from point A to point B.

Public transportation, such as buses, is the main tool for individuals to navigate and get to where they want.

In this challenge, together with RenewSenses LTD, an Israeli company developing assistive technologies for people who are blind, we will assist people with visual impairment in their experience of catching a bus. 

Results from this challenge will be directly tested with people with visual impairment through pilots the company is conducting – enabling fast feedback and creating a highly meaningful challenge that will impact the daily-life independence of many.

The challenge inckudes integrating the solution into the company’s app. The project needs Computer Vision, Object Detection or OCR knowledge, also image data preparation methods, and/or mobile deployment experience.

 

The Project Outcomes

  1. Detecting whether a bus is arriving through real-time object recognition (considering that bus might look different in different countries
  2. Determining if it’s the right bus the user needs through OCR for the text on the bus.
  3. Determining whether a seat is empty/not empty to assist users in finding an empty seat on the bus using object detection.

 

Challenge deliverables is tested directly with a big community of people with visual impairment. The need for this kind of solution is huge and the impact of the developed algorithm will get to users’ hands immediately.

Find more information on how an Omdena project works

 

Using Satellite Imagery to Detect and Assess the Damage of Armyworms in Farming

Using Satellite Imagery to Detect and Assess the Damage of Armyworms in Farming

50 Omdena’s collaborators worked to build AI solutions to detect the spread of armyworms, estimate the damage they cause and save the agriculture industry.

 

 

The Problem

Armyworms are caterpillar pests of grass pastures and cereal crops, where they attack grains and feed on leaves. A very hungry caterpillar is rampaging through crops across the world, leaving a trail of destruction in its wake. The fall armyworm, also known as Spodoptera frugiperda (fruit destroyer), loves to eat corn but also plagues many other crops vital to human food security, such as rice and sorghum.

This invasive eating machine originated in the Americas, but in the last few years, it has gone global. It was reported in Africa in 2016 with a noticeable outbreak in Mali, Ivory Coast, and Ouganda. 

Another type of invasive insect is the Desert Locust which is one of the species of short-horned grasshoppers (Acridoidea).
During plagues, Desert Locusts may spread over an enormous area of some 29 million square kilometers.

The spread of these pests into the world will cause huge pressure on the global food production systems.

 

The Project Outcomes

Using satellite images, the team was able to detect and identify the damage assessment of either or all together (depending on data availability):

  • Fall Armyworm
  • Africa Armyworm
  • Locust Desert, surge/outbreak in Mali (or Ivory Coast or Ouganda) in order to design an insurance product.

 

 

Find more information on how an Omdena project works
Improving Transparency and Democratizing Access to Public Sector Contracts using NLP

Improving Transparency and Democratizing Access to Public Sector Contracts using NLP

In a two-month challenge, a global team of 50 Omdena’s collaborators contributed to help democratize access to contract opportunities buried within public government documents and improve public sector transparency.

 

The Problem

There are a lot of signals that indicate upcoming opportunities hidden within the public government documents. Early notification is seen as key to giving companies without an existing relationship (and the related insider info) an opportunity to participate in these contracts. The ultimate desire is for better communities in which to raise our families and build our businesses by improving a broken procurement process where incumbents win the majority of the contracts.

In order to never miss an opportunity about upcoming contract opportunities, policy changes, or any important local government topics, Ontopical combs publicly available information from government departments then processes and analyzes text and transcripts to deliver unique insights. The bad news is that sorting through that online information isn’t easy. There is no one place collecting relevant information.

 

The Project Outcomes

Ontopical has gathered years of Municipal Council meeting agendas, minutes, and videos. Using these council meeting minutes, agendas & video transcriptions as well as data from Request for Proposal (RFP) posting sites, as training data, train a model to recognize upcoming business opportunities in meeting agendas, minutes, and videos LONG BEFORE any RFP is posted. This will help democratize access to upcoming contract opportunities by providing all with the advance notice required to submit a strong proposal. This will greatly help to make the process of submitting proposals in response to RFPs more transparent.

 

Find more information on how an Omdena project works

 

Rating Road Safety Through Machine Learning to Prevent Road Accidents

Rating Road Safety Through Machine Learning to Prevent Road Accidents

The International Road Assessment Programme (iRAP) is a registered charity established to help tackle the devastating social and economic cost of road crashes. The charity’s vision is for a world free of high-risk roads. In this project, more than 30 technology changemakers have built AI based solutions to increase road safety by mapping the crash risk on roads.

 

The Problem

Road crashes are the biggest killer of young people worldwide aged 5 to 29 years. The tragedy of death and injury impacts every community on earth. Based on current trends 500 million people will suffer life-changing brain, spinal, limb, and internal injuries between now and 2030. The economic cost will be more than US$25 trillion. Almost half of those killed will be vulnerable road users – motorcyclists, bicyclists, and pedestrians. Low-income and middle-income countries, where nine out of ten of the world’s road deaths occur, will suffer the most impact from this global road safety crisis.

iRAP is a registered charity established to help tackle the devastating social and economic cost of road crashes. The charity’s vision is for a world free of high-risk roads. iRAP already works with partners all around the world to apply the iRAP Global Standard in assessing the crash risk on a road and the associated Star Rating performance of road infrastructure.

Road Assessment Programme partnerships are now active in more than 100 countries worldwide. After assessing more than 1,000,000 km of roads, iRAP data helps make over US$75 billion of road investment safer. iRAP and partners are currently completing Star Rating assessments using specially commissioned video surveys or, where available and recent enough, Street View or similar public image data.

 

The Solutions: AI for Road Safety

Contributing to the solution in increasing road safety, more than 30 machine learning engineers, subject matter experts, and mentors collaborated as part of an Omdena challenge to work towards iRAP’s vision of “a world free of high-risk roads.”

The challenge revolves around the three main objectives listed below. These are under the Ai-RAP initiative that aims to accelerate road assessments with the help of big data and AI.

Three main objectives of the challenge:

  • Source geo-located crash data and produce iRAP Risk Maps of the historical crashes per kilometer
  • Source road attribute, traffic flow, and speed data and map the safety performance and Star Rating. This applies to more than 100 million km of road worldwide.
  • Produce repeatable road infrastructure key performance indicators that can form the basis of annual performance tracking

 

In this pipeline, we aim to contribute to the second objective by automatically sourcing the crucial component of vehicle count under the traffic or vehicle flow attribute using satellite imageries with the help of Artificial Intelligence.

 

The Data

iRAP partners worldwide have already collected more than 1 million km of road data over the last 20 years. A sample of that data has been presented in the charity’s Vaccines for Roads resource and Big Data tool (check this and this link).

 

The Impact

The United Nations Sustainable Development Goal is to halve road deaths and injuries by 2030. This includes targets to ensure all new roads are 3-star or better for all road users and that by 2030 more than 75% of travel is on 3-star or better roads.

iRAP estimates that achieving those targets will save 450,000 lives every year and prevent more than 100,000,000 deaths and injuries.  The burden of road trauma on individuals, families, communities, and health systems will be significantly reduced. This will result in more than $8 of savings from every $1 invested.

AI Road Safety

AI for Road Safety

 

Increasing Clean Energy Access in Africa Through Predictive Modeling

Increasing Clean Energy Access in Africa Through Predictive Modeling

 

NeedEnergy is an energy-tech startup to provide sustainable and clean energy solutions. In this two-month Omdena Challenge, 50 technology changemakers collaborated to develop predictive models for designing solar rooftop installations and gas pay-as-you-go reticulation services.

 

The Problem

Sub-Saharan Africa has over 600 million people without access to electricity and electricity demand grows at an annual growth rate of 11%, the highest rate of any region worldwide. The number grows to over 700 million if clean cooking energy sources are considered as most people still rely on firewood and charcoal for their day-to-day cooking. These are just a few of the many additional challenges: 

  • The Grid is getting old and results in increased maintenance and operation cost.
  • Cost for unplanned maintenance and unforeseen faults is a pain for utilities and results in loss of revenue.
  • The Grid has not fully migrated to the edge or cloud to benefit from industry 4.0.
  • Data is in abundance but most of it is not utilized, a potential to start solving the above mentioned.

 

Electricity demand for commercial spaces will grow to 390 TWh by 2040 and 70% of this demand will be covered by renewable solar PV energy. This sector will experience one of the biggest energy transitions and an opportunity for a more m modern architecture for the grid of the future.

 

The Project Outcomes

NeedEnergy intends to use predictive analytics for designing solar solutions or clean energy solutions for clients based on their projected energy usage/profile. This will help to increase energy adoption where it is most needed.

You will help to accomplish this by leveraging NeedEnergy`s network of smart energy monitors for both electricity and gas. This will help with decision-making for Commercial and Industrial (C&I) clients who are transitioning to renewable energy. The analytics insights will also be used for energy suppliers. For example, gas suppliers can better plan deliveries and inventory based on the data.

In this project, you will also build predictive models to detect anomalies in the operation of the installed solar asset. An integration with IBM Deep Thunder will be ideal so that weather influences on the installation can be put into perspective when designing or operating the solar installation. 

 

The data

For the project, the data is classified into two main buckets, which we will use to varying degrees depending on how the project unfolds:

  • Historical Data (realized data) – This information contains the highest signal-to-noise ratio and high relevance but is expensive to collect both financially and timely.
    • User data obtained from smart meters onsight.
    • Demographic information obtained from public entities like the local utility and Regional Power Trading Data (research paper to be shared)
  • Forward-Looking Information – This information is used to provide a broader context for prediction purposes and improve accuracy when dealing with new/unseen situations. It takes into account things that may not appear in historical data sets.
    • Weather information
    • News
    • Trading Prices

 

The Omdena team built internal databases to store this information (relational and time series) and also develop an API to allow for easy access in production and for research purposes.

 

Streamlit interactive dashboard showing short-term and long-term energy demand - Source: Omdena

Streamlit interactive dashboard showing short-term and long-term energy demand – Source: Omdena

 

You can view and explore the dashboard using this link. To read more about how the data was collected till how that dashboard was built, please check the articles below.

 

Need Energy about the AI Challenge results