Ravi Bhandari

Home

I am a PhD candidate at the Department of CSE, IIT Bombay, since Autumn 2014. I am working under the guidance of Prof. Bhaskaran Raman. My detailed CV can be found here.

Research Interests

My current research interests are in the area of mobile computing, where i am specifically looking at ways to Improve Road Safety Through Smart-Sensing. Recently i have developed a liking for wearable computing in general, and earables in particular. More about my ongoing research can be found here.

In the past

I graduated with a B.Tech degree in Information and Communication Technology (ICT) from DA-IICT, Gandhinagar, India in the year 2011. I went on to pursue an M.Tech degree in ICT from IIT Jodhpur in the year 2011-2013. My master's thesis titled "Water Conservation through ICT" aimed at reducing water consumption using on-demand micro-irrigation techniques. I also worked for an year at Samsung Research Institute, Delhi before joining PhD programme at IIT Bombay in July 2014.

Research

My research interest lies in the area of mobile computing and its applications in improving road safety. The abstract of some works that i undertook during my PhD journey are as under. Please see the publication section for paper links.

• CrowdLoc

  Determining the location of a mobile user is central to several crowd-sensing applications. Using a Global Positioning System is not only power-hungry, but also unavailable in many locations. While there has been work on cellular-based localization, we consider an unexplored opportunity to improve location accuracy by combining cellular information across multiple mobile devices located near each other. For instance, this opportunity may arise in the context of public transport units having multiple travelers.
  Based on theoretical analysis and an extensive experimental study on several public transportation routes in two cities, we show that combining cellular information across nearby phones considerably improves location accuracy. Combining information across phones is especially useful when a phone has to use another phone’s fingerprint database, in a fingerprinting-based localization scheme. Both the median and 90 percentile errors reduce significantly. The location accuracy also improves irrespective of whether we combine information across phones connected to the same or different cellular operators.
  Sharing information across phones can raise privacy concerns. To address this, we have developed an id-free broadcast mechanism, using audio as a medium, to share information among mobile phones. We show that such communication can work effectively on smartphones, even in real-life, noisy-road conditions.
  Acknowledgements: The authors would like to thank Information Technology Research Academy (ITRA) Media Lab Asia for partly providing the funding for this work. A sincere thanks to Piyush Bhatore for implementation of the SoundShare app and Laxman Sawant for data collection.



• FullStop

  Road safety is a critical issue worldwide. We believe that mobile devices can play a positive role in this context by detecting dangerous conditions and providing feedback. This paper focuses on a specific problem in developing countries: the stopping behaviour of buses in the vicinity of bus stops. For instance, buses could arrive at a bus stop but continue rolling forward instead of coming to a complete halt, or could stop some distance away from the bus stop, possibly even in the middle of a busy road. Such behaviours put at risk the passengers boarding or alighting the bus, and also the people waiting at a bus stop.
  We present FullStop, a smartphone-based system that detects safety risks emanating from stopping behaviour like the ones listed above. We show that the GPS and inertial sensors are unable to perform the fine-grained detection needed. Therefore, our approach in FullStop is based on the view obtained from looking out to the front of the vehicle using the camera of a smartphone that is mounted on the front windshield. Using optical flow vectors, with several refinements, FullStop running on a smartphone is able to effectively detect various unsafe bus stopping behaviours.
  Acknowledgements: Ravi Bhandari would like to thank Microsoft Research India and Confederation of Indian Industry (CII) for the financial support provided under the aegis of the "Prime Ministers Fellowship for Doctoral Research". The authors would like to thank Laxman Sawant for his support in collecting video data and Sridhar Pratapa for the ground truth marking.



• DeepLane

  Current smartphone-based navigation applications fail to provide lane-level information due to poor GPS accuracy. Detecting and tracking a vehicle’s lane position on the road assists in lane-level navigation. For instance, it would be important to know whether a vehicle is in the correct lane for safely making a turn, perhaps even alerting the driver in advance if it is not, or whether the vehicle’s speed is compliant with a lane-specific speed limit. Recent efforts have used road network information and inertial sensors to estimate lane position. While inertial sensors can detect lane shifts over short windows, it would suffer from error accumulation over time. In this paper we present DeepLane, a system that leverages the back camera of a windshield-mounted smartphone to provide an accurate estimate of the vehicle’s current lane. We employ a deep learning based technique to classify the vehicle’s lane position. DeepLane does not depend on any infrastructure support such as lane markings and works even when there are no lane markings, a characteristic of many roads in developing regions.
  We perform extensive evaluation of DeepLane on real world datasets collected in developed and developing regions. DeepLane can detect vehicle’s lane position with an accuracy of over 90% in both day and night conditions. We have implemented DeepLane as an Android-app that runs at 5 fps on CPU and upto 15 fps on smartphone’s GPU and can also assist existing navigation applications with lane-level information.
  Acknowledgements: Ravi Bhandari would like to thank Microsoft Research India and Confederation of Indian Industry (CII) for the financial support provided under the aegis of the "Prime Ministers Fellowship for Doctoral Research".

Ongoing Projects

• CityProbe

  This is an ongoing MHRD sponsored project at IIT Bombay. It aims to create a city-scale pervasive sensing system for monitoring road conditions, air and sound pollution. My predecessors have worked on creating a live pothole map of Mumbai as shown at the undermentioned link (takes few tens of seconds to load fully). I have been involved in classifying the roads as per their roughness and generate colour coded maps (eg. Blue for smooth road, Red for bad road, Yellow for intermediate roads). Presently this work is underway.
  Map link

Publications and Demo

Peer-reviewed Conferences and Journals

1. Driving Lane Detection on Smartphones using Deep Neural Networks
   Ravi Bhandari, Akshay Uttama Nambi, Bhaskaran Raman, Venkata N. Padmanabhan
   Accepted for publication at ACM Transactions of Sensor Networks 2019
2. 
   FullStop: A Camera-Assisted System for Characterizing Unsafe Bus Stopping
   Ravi Bhandari, Bhaskaran Raman, Venkata N. Padmanabhan
   Accepted for publication at IEEE Transactions of Mobile Computing 2019
3. 
   Demo: HAMS: Driver and Driving Monitoring using a Smartphone
   Akshay Uttama Nambi, Shruthi Bannur, Ishit Mehta, Harshvardhan Kalra, Aditya Virmani, Ravi Bhandari, Venkata N. Padmanabhan, Bhaskaran Raman
   Proceedings of the 24th Annual International Conference on Mobile Computing and Networking (MobiCom 2018)
Demo link
4. 
   DeepLane: Camera-assisted GPS for Driving Lane Detection
   Ravi Bhandari, Akshay Uttama Nambi, Bhaskaran Raman, Venkata N. Padmanabhan
   5th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys 2018)
   Paper link
5. 
   FullStop: Tracking Unsafe Stopping Behaviour of Buses
   Ravi Bhandari, Bhaskaran Raman, Venkata N. Padmanabhan
   Communication Systems and Networks (COMSNETS), 2018 10th International Conference on, pp. 65-72. IEEE, 2018
   Paper link
6. 
   CrowdLoc: Cellular Fingerprinting for Crowds by Crowds
   Ravi Bhandari, Bhaskaran Raman, K. K. Ramakrishnan, Deepthi Chander, Naveen Aggarwal, Divya Bansal, Mahima Choudhary, Nisha Moond, Aneesh Bansal, Megha Chaudhary
   ACM Transactions on Sensor Networks (TOSN) 14, no. 1 (2018): 4
   Paper link
7. 
   GSM-based positioning for public transportation commuters
   Ravi Bhandari, M Chaudhary, A Bansal, B Raman, N Aggarwal, D Bansal, K. K. Ramakrishnan
   ITS Workshop COMSNETS 2015, 10.1109/COMSNETS.2015.7098722
   Paper link
8. 
   Development of affordable ICT solutions for water conservation in agriculture
   Ammar Adil, Venkataramana Badarla, Anand K Plappally, Ravi Bhandari, Poonam Sankhla
   AGRINETS COMSNETS 2015, 10.1109/COMSNETS.2015.7098716
   Paper link

Thesis and Reports

1. 
   Water Conservation through ICT
   Ravi Bhandari
   M.Tech thesis accepted in June 2013
   Thesis link
2. 
   MV2 and ACE Automation Project
   Ravi Bhandari
   B.Tech report accepted in May 2011
   Report link

Contact

News

[Write about your latest awards, fellowships, internships here! :-)]