Prototypes – Devthon https://13.233.195.217 Decoding Innovation Tue, 05 Jan 2021 00:55:54 +0000 en-GB hourly 1 https://wordpress.org/?v=6.6.4 https://13.233.195.217/wp-content/uploads/2020/11/cropped-Devthon-Logo-Color400x400-32x32.png Prototypes – Devthon https://13.233.195.217 32 32 Adaptive Traffic https://13.233.195.217/adaptive-traffic/ Thu, 17 Dec 2020 06:47:55 +0000 https://18.224.111.186/?page_id=3321

Adaptive traffic

Using a camera monitoring the road, the prototype was built using a raspberry to monitor the density of the road and thereby dynamically time the signals. This will ease the overhead and also make the signals smarter.

]]>
Anthropopmetry with Stereo Cameras https://13.233.195.217/anthropometry/ Sat, 17 Oct 2020 10:51:19 +0000 https://devthon.org/?page_id=2285

Anthropopmetry with Stereo Cameras

Anthropometry is a science that was first developed in the 19th century and was primarily used to understand the process of evolution. It refers to obtaining systematic measurements of the human body of which the core elements are height, weight, body mass index (BMI), body circumferences (waist, hip, and limbs), and skinfold thickness. Most recently, trends in anthropometric research have shifted towards the use of 3D data. . In India, however, physical anthropometric tools such as stadiometers (height), scales (weight), and calipers (skin thickness) are being used for most purposes. This project aims to challenge this status quo and bring in digital tools for anthropometric measurements in India.

 

Stereoscopy is a technique for creating or enhancing the illusion of depth in an image by means of stereopsis. The reason our prototype is able to predict human measurements from a digital source is due to the presence of a stereo camera. A stereo camera is a type of camera with two or more lenses with a separate image sensor for each lens. This allows the camera to simulate human depth vision, and by using two vantage points, 3D information can be extracted by examining the relative positions of objects in the two panels.

The 3 people team from ilabs helps officials prioritize the bins and help for a faster and more efficient waste disposal from public roads also coded an algorithm which would help garbage collection vans take the shortest route and cover a maximum number of garbage bins on the way, thus, saving time and fuel.

  • The only major hardware requirement is the Coral Dev Board – a single‐board computer containing an Edge TPU coprocessor.
  • In terms of software, PoseNet (vision model under the TensorFlow platform) is the Coral submodule used for pose detection and GStreamer is the open source multimedia library used for streaming the video inputs and outputs.
  • The project is primary coded in Python.

The first step in creating the plugin was to construct a stereo camera setup. This was done using two phones taped together, such that the cameras were in a horizontal line with each other. While not an ideal setup, this seemed to work well enough for testing. Calibration of the two cameras was then performed using tools from OpenCV. This allowed us to calculate the Q matrix of the stereo camera system, which could then be used to project points into a 3D space.

The plugin uses PoseNet, a pose estimation model from Google. The key points from both video streams are first identified, and then matched with each other. Then, using the Q matrix, the 2D coordinates of the key points are projected into 3D real coordinates. Distance between the desired points is then calculated using the Euclidean distance formula.

The use of PoseNet comes with both benefits and limitations. One benefit was that PoseNet has been optimized to run on the Coral Dev Board, which is what we used to run our prototype. However, there are a limited set of key points that can be detected with PoseNet, which meant that the closest estimate of the height that could be achieved was the distance between the eye and the ankle.

Another issue we faced was that outliers in the data were causing the height value to fluctuate often. This was solved using an exponential moving average, and by clipping the outliers to within one standard deviation from the mean. By clipping the values rather than ignoring them, we allow the plugin to work effectively even if the person in the frame changes during the course of the video stream, as after a few seconds, the height average will catch up to this new height.

Further improvements to this project could be achieved through a variety of different means. Constructing a better stereo camera setup would help to improve the accuracy of the measurements. Using a different model could allow for better key points to be able to calculate the height more effectively. Finally, adding image processing elements to the pipeline for noise reduction could help to improve the accuracy of PoseNet or another pose estimation model.

State governments, service organizations, health departments, and statistical organizations spend lakhs of rupees each year to collect anthropometric data from people residing in villages in India. This is done for collection of health datasets to analyze medical requirements, survey data and many other purposes. The use of older physical measuring devices is very time consuming and laborious. By using this stereo camera setup, this process can be as simple as people successively standing in front of the camera, and the computer recording anthropometric data (and possibly linking it to a centralized health profile). In addition, this data can be shared with government hospitals and doctors to eliminate the need for measurement each time patients visit the hospital. The primary advancement this project needs to become commercially usable is a software user interface for data collection and storage. In addition, identification of a device cheaper than the Coral will benefit in reaching the most remote villages where funding is limited.

People behind the project

]]>
AADR https://13.233.195.217/aadr/ Tue, 01 Sep 2020 03:59:51 +0000 https://devthon.org//?page_id=1996

Accident Detection and Ambulance Dispatch

Vehicle accident is the paramount thread for the people’s life which causes a serious wound or even dead. The automotive companies have made lots of progress in alleviating this thread, but still the probability of detrimental effect due to an accident is not reduced. As the usage of vehicles is increasing drastically, the probability of getting injured due to vehicles is also increased. The main cause for accidents is high speed, drunk driving, inattentiveness, stress and distraction due to electronic gadgets. This can majorly attributed to carelessness of the driver.

Automatic Accident Detection and Rescue System is a hardware solution for vehicles that triggers a message upon an accident and contacts medical emergencies. This solution drastically reduces the response time by automatically triggering the emergency teams to the location. The team has achieved this through a custom hardware and software approach.

The team uses sensors on the car that identify that you have met with an accident. Once the device is certain about the casuality, it then uses the onboard location tracking modules to find the location of the accident and send an alert to the server using the GPRS module on the device. This data is then sent to the ambulances nearby automatically, which respond immediately. 

The team uses an arduino and GPS and GPRS Modules with arduino to send the crash data from the location to the server.

Arduino is an open-source electronics platform based on easy-to-use hardware and software. Arduino boards are able to read inputs – light on a sensor, a finger on a button, or a Twitter message – and turn it into an output – activating a motor, turning on an LED, publishing something online. You can tell your board what to do by sending a set of instructions to the microcontroller on the board.

Global Positioning System (GPS) is a satellite-based system that uses satellites and ground stations to measure and compute its position on Earth. GPS is also known as Navigation System with Time and Ranging (NAVSTAR) GPS. GPS receiver needs to receive data from at least 4 satellites for accuracy purpose. GPS receiver does not transmit any information to the satellites.

]]>
Aid for disabled https://13.233.195.217/aid-for-disabled/ Tue, 01 Sep 2020 03:57:25 +0000 https://devthon.org//?page_id=1993

Aid for disabled

For most people. signt and vision are the most significant and important ways of receiving and understanding information. Dealing with sight loss or low vision is a challenge in iteself and due to urbanisation of cities and the complications that come with it, the effort it takes for a differently abled in such environments is enormous. 

Dispite the extensive innovation and development of technology, it has not reached everyone in the same way. From time to time, we see and hear about projects that make the world more accessible for people who are blind or visually impaired. Here at devthon, one of our teams plans to do the same.

Due to urbanisation, we go from one environement to another all day long. From office to homes; banks to supermarket; parks to gyms; hospitals to medical stores, If one observes, most of these are not designed to be accessed by the visually impaired. 

Due to the structural difficulties that a blind person has to face, navigation and accessibility in physical situations is one of the main challenges faced. So, the team has come up with a smart aid. This is a Navigation system for visually disabled using voice based instructions and open maps. The team uses RFID technology and their own platform to help disabled people navigate public spaces by triangulating their location and guiding them.

RFID is an acronym for “radio-frequency identification” and refers to a technology whereby digital data encoded in RFID tags or smart labels (defined below) are captured by a reader via radio waves. RFID is similar to barcoding in that data from a tag or label are captured by a device that stores the data in a database. RFID, however, has several advantages over systems that use barcode asset tracking software. The most notable is that RFID tag data can be read outside the line-of-sight, whereas barcodes must be aligned with an optical scanner.

RFID belongs to a group of technologies referred to as Automatic Identification and Data Capture (AIDC). AIDC methods automatically identify objects, collect data about them, and enter those data directly into computer systems with little or no human intervention. RFID methods utilize radio waves to accomplish this. At a simple level, RFID systems consist of three components: an RFID tag or smart label, an RFID reader, and an antenna. RFID tags contain an integrated circuit and an antenna, which are used to transmit data to the RFID reader (also called an interrogator). The reader then converts the radio waves to a more usable form of data. Information collected from the tags is then transferred through a communications interface to a host computer system, where the data can be stored in a database and analyzed at a later time.

]]>
Swacch Hyderabad https://13.233.195.217/swacch-hyderabad/ Tue, 01 Sep 2020 03:54:04 +0000 https://devthon.org//?page_id=1987

Swacch Hyderabad

Smart Bins that decrease the amount of carbon footprint throughout the city.

The team built smart public garbage bins, equipped with RFID to identify the interval at which they are attended which would send out information to servers whenever there is an overflow and in turn, alert garbage collection teams. It would also have a compactor, to compress the waste and increase the capacity of garbage bins by 10 times. 

The 3 people team from ilabs helps officials prioritize the bins and help for a faster and more efficient waste disposal from public roads also coded an algorithm which would help garbage collection vans take the shortest route and cover a maximum number of garbage bins on the way, thus, saving time and fuel.

]]>
MNREGA Dataset Analysis https://13.233.195.217/mnrega-dataset-analysis/ Tue, 01 Sep 2020 03:46:17 +0000 https://devthon.org//?page_id=1978

MNREGA Dataset Analysis

Based on the MNREGA works done in a district since the inception of the scheme, can we find outliers in terms of wage/material expenditure, works done etc?

Team NREGA had two prototypes to showcase. The first one was a decision tree that would be used to understand if all the criteria were being met and thereby understanding whether the final goals of the NREGA scheme were being achieved. So all the data would be checked using the 4 rules that were part of the decision tree and easily be able to analyze if the scheme was being effective or not.

Also the team created a visualization to show the comparison between wages and materials. With the help of the visualization, they were able to clearly show the number of villages that showed a deviation from the average. They were able to find more than 300 villages that had spent more on the materials than the wages, thereby defeating the whole purpose of the scheme. These visualizations could be used to analyze the way villages were using their NREGA funds and easily spot the places where they were being misused.

Please Find the outcomes of the project here

]]>
District Dashboard using NITI Aayog Data https://13.233.195.217/district-dashboard-using-niti-aayog-data/ Tue, 01 Sep 2020 03:44:29 +0000 https://devthon.org//?page_id=1975

District Dashboard using NITI Aayog Data

Based on district data from NITI Aayog, can we build a dash board for comparing districts on various parameters and find sister districts?

This team presented their visualization that they had created to analyze District Level Quality of Life Data. They created visualizations to compare districts on key sectors of development like health, education, water and electricity. Combining this information, they wished to rank different districts on the quality of life. These visualizations could be useful to NGOs, activists, district and state administration to find the deficiencies in key development areas and work towards filling the necessary gaps.

The 3 people team from ilabs helps officials prioritize the bins and help for a faster and more efficient waste disposal from public roads also coded an algorithm which would help garbage collection vans take the shortest route and cover a maximum number of garbage bins on the way, thus, saving time and fuel.

Niti Aayog has public data for districts of all states regarding health, education & utilities. There is a need to analyze this data from following aspects

  • Review visually how districts are doing on various criteria
  • Visually Compare districts on multiple factors and check details
  • Show multiple factors together to understand correlation between the factors.
  • Rank the districts at individual factors as well as across the factors in each of the areas by applying weighted ranking process.
  • Top N & Bottom N analysis by one or more factors across districts.
  • District Administration ( Collector, JC etc)
  • Central Government leadership
  • Public Representatives ( MPs, MLAs )
  • Activists/NGOs/Statisticians
  • General public awareness
  • Include financial data to analyze correlation in  social investment and performance.
  • Trending analysis over time ( for e.g YoY, QoQ ) for quantitative analysis of progress in effectiveness of policy implementation and social projects.
  • overlaying policy timing on data will help doing impact analysis to drive continuous change.
  • Include geographical data to do thematic analysis
]]>
PDS Dataset Analysis https://13.233.195.217/pds-dataset-analysis/ Tue, 01 Sep 2020 03:41:51 +0000 https://devthon.org//?page_id=1972

PDS Dataset Analysis

Based on closing balance reports and key register reports of FPS, can we throw light on the FPS that may be diverting food grain meant for the poor and Identification of leakages in the Public Distribution System

The main problem that the team focused on was the identification of leakages in the Public Distribution System. For achieving this goal, they created visualizations that showed the deviations in the behaviour of ration shop owners who showed huge variations of leftover food grains in the shop across months. By using this visualization, the supply variations across shops can easily be spotted. Also, the correlation between Supply and Number of Ration Food Cards can be seen. This can be used by officials to find fraudulent practices and investigate these shops wherever required.

  • Supply variations across shops
  • Find the correlation between Supply and Number of Ration Food Cards.
  • Variations of Leftover food grains in the shop across months
  • Identifying the GPS location of the shops in the region. ( as per the data provided)
  • Rules for identifying the shops which possibility of fraud occurrence is present.
  • Reporting system for needy to report whether the shop is Open / Close

Please find the outcomes of the project here

]]>
GHMC Grievance Dataset Analysis https://13.233.195.217/ghmc-grievance-dataset-analysis/ Tue, 01 Sep 2020 03:40:09 +0000 https://devthon.org//?page_id=1966

GHMC Grievance Dataset Analysis

Based on grievance data from GHMC for the last one year (Apr 2015 to March 2016), can we find out the most common grievances, officials who are loaded with work, areas from where maximum grievances are coming from etc?

The team worked to visualize the complaints that the GHMC has received in the last year. It could show which were the areas that registered the most number of complaints and also the types of works that were requested the most number of times.

 

They were also able to build a demo for an App that would be able to visualize the status of complaints in a particular region. This would be a handy tool for all decision makers who were part of the GHMC. They could easily monitor if the efforts they were putting in were showing positive results and make changes accordingly.

]]>
Village Dashboard with data on Maa Bhoomi Portal https://13.233.195.217/village-dashboard-with-data-on-maa-bhoomi-portal/ Tue, 01 Sep 2020 03:35:47 +0000 https://devthon.org//?page_id=1963

Village Dashboard with data on Maa Bhoomi Portal

Pahani is a form of Land Record that depicts Rural Land Ownership. Taking the Pahani provided to us as a Primary Data Source we created data sets to address the problem statements.

Based on the Village level Pahani on the Maa Bhoomi portal, can we build a dashboard for micro level planning at a village level on land holding size, type of land. water sources etc?

The first team to present was the team that were using the data from the Village Pahani records. They created a dashboard that could show, compare and calculate the data from the Village Pahani records. It could calculate the average land holding per person in a village, highest/lowest land holdings, type of land, water resource and barren/cultivable land in a village. This dashboard could be used by the common man and also an official like the district collector to measure the rural development metrics and find insights.

  • Average land Holding Per Person Per Village

    From the given raw data we computed the average land holding per person per village.As per our analysis we found that: 0.0025 Acres from a total of 1649 Acres in the village

  • Highest & Lowest Land Holdings Per Village
  • Type Of Land
  • Water Source
  • Barren Vs Cultivable Land In A Village

Please find the outcomes of the project here and here

]]>