Automotive Sector
A) Assisted driving solutions
Visualization using Car’s Camera of traffic objects. Identification of traffic objects like, Vehicle, Pedestrians, road signs , etc…etc...
B) Intuitive UI design for Android Infotainment systems
Develop a prototype demonstrating screen designs with seamless interactions and transition logic
for a set of selected automotive usecases of your interest. Focus on selecting the best tools/language/framework
libraries’ for android App development assist the driver in interacting with multiple active application views. Explore the options to achieve efficient graphics performance and responsiveness making use of GPU /hardware accelerators while demonstrating capabilities for Video playback / Video processing from camera inputs or while creating screen transition animation effects.
C) Smart Tourist Mobility (connecting driving in cities and countryside with tourism)
In this scenarios , the IoT enables services and application deployed in a tourist spot such as : roadside smart machines, police control rooms, emergency help, tourist guides, volunteers, parking lots information , crowd density are collected and augmented on the locality maps as “smart tourist maps”. These services are made available to the Infotainment system, which can guide the driver in providing the access to these services.
Conceptualize the backend infrastructure that help to collect and generate PoI (like On Road volunteer, police assist, tourists ,parking lots etc…) from sensor data collected using various IoT devices to augment locality maps with the information to create a custom “Smart Map showing realtime information” from Google Maps or using other open source map data base. Based on this conceptualize a tourist guide app for the Infotainment unit ( Android – JAVA/HTML5) to access this information in SmartMaps and provide various information to driver to avail required services.
Climate Change
Creating state-of-the-art devices to improve distribution, management and purification of water.
A) Change detection and extraction of information and features of interest in RS images using time series information:
Deep Learning based algorithms for identifying the changes in selected time series data and extracting features of interest changed over time will be a very good value addition for water resources, urban dynamics, infrastructure monitoring and disaster management. This is possible only by identification or detection of features on the fly from RS images, which are more amenable for noise from different implicit processes in atmosphere and data processing algorithms. Given time series tiles of Images / RS image ( 2 dates ) the system should
a) Identify changes and highlight areas of change.
b) Extract features that are evident from image 2 and not in image1, categorise in known lists i.e. water, roads, buildings, parks, trees
c) Find features that are missing in image2 w.r.t. image 1.
Dataset: reference dataset can be obtained from realtime satellite sensor data Link
B) Detecting air pollution hot spots and identifying the source trajectories using ML/AI techniques:
At present, air pollution is a global problem. India is also a big sufferer of this problem. India signed COP21 agreement for cutting the carbon emissions from 2025. Challenges involved in the current statement is mining the datasets from different satellites parameters and providing the final output with moderate spatial resolution on pollution information. Hence information will be useful for change detection analysis. Identification of source pathways. Participants must develop AI/ML based software/algorithm to identify/analyse
1. Location of hot spots.
2. Long-term occurrence of hot spots and changes.
Dataset Links: Satellite based data (freely available)
MOPITT
Aura/OMI
C) Paperless Office:
Making the official activities to go paperless - like sending official communications through e-media, automating procedures for protecting the environment. Design a customizable workflow management system to handle submission of documents and approval workflow with facility to sign the document with approval seal. This system should have ability to intimate the concerned party by email and also be manageable by email.
D) Geo Tracking of Waste and Triggering Alerts and Mapping Areas with High Waste Index:
We do have waste lying in cities which makes it hard for cleaning staff to know which area requires attention and urgent garbage, waste pickup. Identifying Waste across in the City. Cameras attached to Govt or Public Vehicles while driving can capture video and identify garbage areas and upload images (image /video scanning ). Ability to capture images of garbage and upload, images will automatically have GEO location position of the image. Viewing the high waste areas. Mapping the location on a map with the Waste Quantity Index (approximate) so that the waste management team, can quickly take action based on the wastage level thrown in an area. Lateral Scenarios, Scaling the solution and Flood Monitoring and reporting.
Women Safety
Creating state-of-the-art safety and security technologies for India
A) Face, expression and gesture recognition based compilation in database of criminal records:
Design a system to capture face, expression and gesture of targeted persons (Criminals) through distributed CCTV System and maintaining it in a database along with time and location stamp. The database so compiled to be used to identify suspects from video clips of crime related CCTV footages captured series of CCTV Systems located on routes and close to scene of crime.
B) AI powered women safety application:
Women safety apps powered with AI and Machine Learning capabilities will collect data and patterns over a period of time and will, later on, provide other users with pre-generated reports – when they take a particular route to their destination. For example – When a user (women) is using an AI-powered safety app, she will want to know the best and safest possible route to their destination. Let’s say; there are 5 different routes that can be used to reach the destination. The app will evaluate all of the routes based on previously collected data. The evaluation of all of the possible routes will be based on various criteria. These criteria could be security in the area, an average number of people during the particular time of the day, previous women harassment cases in the area and so on. In general, the app will interact with several areas leading to the destination and will generate a report based on that interaction and criteria, for the user to see and make which route is the safest of all.
C) AI/ML model that recognises the tone and perform counter action:
A safety application that listens when the app is on. If it hears keywords like ‘bachao’ or ‘help’, it should use a machine learning or artificial intelligence model to judge the tone or emotional state of the statement and automatically trigger some actions like sending texts to nearby police station, she teams etc with geo co-ordinates and start live navigation with them. The model should be able to differentiate a cry for real help from a casual conversation like “could you help me with math test?”. Native language keywords can also be included.
