Networked Sensing | Ramesh Govindan

We have had a long interest in networked sensing, the idea that information from network-connected sensors can be mined to understand environments and behaviors

MobiCom

UbiPose: Towards Ubiquitous Outdoor AR Pose Tracking Using Aerial Meshes

Weiwu Pang, Chunyu Xia, Branden Leong, and 3 more authors

In Proceedings of the 29th Annual International Conference on Mobile Computing and Networking, 2023

Bib Link

@inproceedings{ubipose,
  author = {Pang, Weiwu and Xia, Chunyu and Leong, Branden and Ahmad, Fawad and Paek, Jeongyeup and Govindan, Ramesh},
  title = {UbiPose: Towards Ubiquitous Outdoor AR Pose Tracking Using
  		  Aerial Meshes},
  booktitle = {Proceedings of the 29th Annual International Conference on
  		  Mobile Computing and Networking},
  year = {2023},
  series = {ACM MobiCom '23},
  address = {New York, NY, USA},
  publisher = {Association for Computing Machinery},
  isbn = {9781450399906},
  url = {https://doi.org/10.1145/3570361.3613263},
  doi = {10.1145/3570361.3613263},
  articleno = {49},
  numpages = {16},
  keywords = {augmented reality, outdoor pose estimation, aerial mesh},
  location = {Madrid, Spain},
  topics = {sensing},
}

ICLR

MCAL: Minimum Cost Human-Machine Active Labeling

Hang Qiu, Krishna Chintalapudi, and Ramesh Govindan

In The Eleventh International Conference on Learning Representations , 2023

Bib Link

@inproceedings{qiu2023,
  title = {{MCAL}: Minimum Cost Human-Machine Active Labeling},
  author = {Qiu, Hang and Chintalapudi, Krishna and Govindan, Ramesh},
  booktitle = {The Eleventh International Conference on Learning
  		  Representations },
  year = {2023},
  url = {https://openreview.net/forum?id=1FxRPKrH8bw},
  topics = {sensing},
}

ToSN
Sensing the Sensor: Estimating Camera Properties with Minimal Information

Pradipta Ghosh, Xiaochen Liu, Hang Qiu, and 3 more authors

ACM Trans. Sen. Netw., Feb 2022

Abs Bib Link

Public outdoor surveillance cameras often have limited metadata describing their properties. Frequently, a public camera’s precise position, orientation, focal length, and image center are unknown; these attributes are necessary to precisely pinpoint the location of events seen in the camera. In this article, we ask: what is the minimal information needed to accurately estimate these properties for public cameras? We show, using a judicious combination of projective geometry, neural networks, and crowd-sourced annotations from human workers, that it is possible to, for example, localize 95% of the cameras in our test data set to within 12 m using a single image taken from the camera. This performance is an order of magnitude better than PoseNet, a state-of-the-art neural network that needs significantly more information than our approach, and can only estimate position and orientation (and not other properties). Finally, we show that the camera’s inferred pose and properties can help design a number of virtual sensors, all of which have good accuracy.
@article{ghosh22, author = {Ghosh, Pradipta and Liu, Xiaochen and Qiu, Hang and Vieira, Marcos A. M. and Sukhatme, Gaurav S. and Govindan, Ramesh}, title = {Sensing the Sensor: Estimating Camera Properties with Minimal Information}, year = {2022}, issue_date = {May 2022}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, volume = {18}, number = {2}, issn = {1550-4859}, url = {https://doi.org/10.1145/3508393}, doi = {10.1145/3508393}, journal = {ACM Trans. Sen. Netw.}, month = feb, articleno = {28}, numpages = {26}, topics = {sensing}, keywords = {mechanical turk, Localization, neural network, camera, vanishing point} }
TMC
Synthesis of Large-Scale Instant IoT Networks

Pradipta Ghosh, Jonathan Bunton, Dimitrios Pylorof, and 6 more authors

IEEE Transactions on Mobile Computing, Feb 2021

Abs Bib

While most networks have long lifetimes, temporary network infrastructure is often useful for special events, pop-up retail, or disaster response. An instant IoT network is one that is rapidly constructed, used for a few days, then dismantled. We consider the synthesis of instant IoT networks in urban settings. This synthesis problem must satisfy complex and competing constraints: sensor coverage, line-of-sight visibility, and network connectivity. The central challenge in our synthesis problem is quickly scaling to large regions while producing cost-effective solutions. We explore two qualitatively different representations of the synthesis problems using satisfiability modulo convex optimization (SMC), and mixed-integer linear programming (MILP). The former is more expressive, for our problem, than the latter, but is less well-suited for solving optimization problems like ours. We show how to express our network synthesis in these frameworks. To scale to problem sizes beyond what these frameworks are capable of, we develop a hierarchical synthesis technique that independently synthesizes networks in sub-regions of the deployment area, then combines these. We find that, while MILP outperforms SMC in some settings for smaller problem sizes, the fact that SMC’s expressivity matches our problem ensures that it uniformly generates better quality solutions at larger problem sizes.
@article{ghosh2021b, title = {Synthesis of Large-Scale Instant IoT Networks}, author = {Ghosh, Pradipta and Bunton, Jonathan and Pylorof, Dimitrios and Vieira, Marcos A. M. and Chan, Kevin and Govindan, Ramesh and Sukhatme, Gaurav S. and Tabuada, Paulo and Verma, Gunjan}, doi = {10.1109/TMC.2021.3099005}, year = {2021}, date = {2021-09-01}, journal = {IEEE Transactions on Mobile Computing}, pubstate = {published}, topics = {sensing}, tppubtype = {article} }

SoCC

Scrooge: A Cost-Effective Deep Learning Inference System

Yitao Hu, Rajrup Ghosh, and Ramesh Govindan

In SoCC ’21: ACM Symposium on Cloud Computing, Seattle, WA, USA, November 1 - 4, 2021, Feb 2021

Bib Link

@inproceedings{hu2021b,
  author = {Hu, Yitao and Ghosh, Rajrup and Govindan, Ramesh},
  editor = {Curino, Carlo and Koutrika, Georgia and Netravali, Ravi},
  title = {Scrooge: {A} Cost-Effective Deep Learning Inference
  		  System},
  booktitle = {SoCC '21: {ACM} Symposium on Cloud Computing, Seattle, WA,
  		  USA, November 1 - 4, 2021},
  pages = {624--638},
  publisher = {{ACM}},
  year = {2021},
  url = {https://doi.org/10.1145/3472883.3486993},
  doi = {10.1145/3472883.3486993},
  timestamp = {Sun, 31 Oct 2021 10:05:01 +0100},
  topics = {sensing,mobile},
  biburl = {https://dblp.org/rec/conf/cloud/HuGG21.bib}
}

IoTDI

Rim: Offloading Inference to the Edge

Yitao Hu, Weiwu Pang, Xiaochen Liu, and 4 more authors

In Proceedings of the 6th ACM/IEEE Conference on Internet of Things Design and Implementation, 2021, Feb 2021

Bib Link

@inproceedings{hu2021,
  title = {Rim: Offloading Inference to the Edge},
  author = {Hu, Yitao and Pang, Weiwu and Liu, Xiaochen and Ghosh, Rajrup and Ko, Bongjun and Lee, Wei-Han and Govindan, Ramesh},
  url = {https://dl.acm.org/doi/abs/10.1145/3450268.3453521},
  year = {2021},
  date = {2021-05-18},
  booktitle = {Proceedings of the 6th ACM/IEEE Conference on Internet of
  		  Things Design and Implementation, 2021},
  pubstate = {published},
  topics = {sensing,mobile},
  tppubtype = {inproceedings}
}

IoTJ

New Frontiers in IoT: Networking, Systems, Reliability, and Security Challenges

Saurabh Bagchi, Tarek F Abdelzaher, Ramesh Govindan, and 4 more authors

IEEE Internet of Things Journal, Feb 2020

Bib Link

@article{bagchi2020new,
  title = {New Frontiers in IoT: Networking, Systems, Reliability,
  		  and Security Challenges},
  author = {Bagchi, Saurabh and Abdelzaher, Tarek F and Govindan, Ramesh and Shenoy, Prashant and Atrey, Akanksha and Ghosh, Pradipta and Xu, Ran},
  url = {https://ieeexplore.ieee.org/document/9136673},
  year = {2020},
  date = {2020-01-01},
  journal = {IEEE Internet of Things Journal},
  keywords = {},
  topics = {sensing},
  pubstate = {published},
  tppubtype = {article}
}

IROS

Persistent Connected Power Constrained Surveillance with Unmanned Aerial Vehicles

Pradipta Ghosh, Paulo Tabuada, Ramesh Govindan, and 1 more author

In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Feb 2020

Bib

@inproceedings{ghosh2020iros,
  title = {Persistent Connected Power Constrained Surveillance with
  		  Unmanned Aerial Vehicles},
  author = {Ghosh, Pradipta and Tabuada, Paulo and Govindan, Ramesh and Sukhatme, Gaurav S},
  year = {2020},
  date = {2020-01-01},
  booktitle = {Proceedings of the IEEE/RSJ International Conference on
  		  Intelligent Robots and Systems (IROS)},
  keywords = {},
  pubstate = {published},
  topics = {sensing},
  tppubtype = {inproceedings}
}

Grab: Fast and Accurate Sensor Processing for Cashier-Free Shopping

Xiaochen Liu, Yurong Jiang, Kyu-Han Kim, and 1 more author

In , Feb 2020

Bib Link

@inproceedings{liu2020,
  title = {Grab: Fast and Accurate Sensor Processing for Cashier-Free
  		  Shopping},
  author = {Liu, Xiaochen and Jiang, Yurong and Kim, Kyu-Han and Govindan, Ramesh},
  year = {2020},
  date = {2020-01-07},
  publisher = {arXiv preprint arXiv:2001.01033},
  keywords = {},
  pubstate = {published},
  topics = {sensing},
  tppubtype = {inproceedings}
}

Rapid Top-Down Synthesis of Large-Scale IoT Networks

Pradipta Ghosh, Jonathan Bunton, Dimitrios Pylorof, and 6 more authors

In Proceedings of the IEEE International Conference on Computer Communications and Networks (ICCCN), Feb 2020

Bib Link

@inproceedings{ghosh2020rapid,
  title = {Rapid Top-Down Synthesis of Large-Scale IoT Networks},
  author = {Ghosh, Pradipta and Bunton, Jonathan and Pylorof, Dimitrios and Vieira, Marcos and Chan, Kevin and Govindan, Ramesh and Sukhatme, Gaurav and Tabuada, Paulo and Verma, Gunjan},
  year = {2020},
  date = {2020-01-01},
  booktitle = {Proceedings of the IEEE International Conference on
  		  Computer Communications and Networks (ICCCN)},
  keywords = {},
  pubstate = {published},
  topics = {sensing},
  tppubtype = {inproceedings}
}

Sensys

Caesar: Cross-camera Complex Activity Recognition

Xiaochen Liu, Pradipta Ghosh, Oytun Ulutan, and 3 more authors

Feb 2019

Bib Link

@conference{liu2019,
  title = {Caesar: Cross-camera Complex Activity Recognition},
  author = {Liu, Xiaochen and Ghosh, Pradipta and Ulutan, Oytun and Manjunath, B.S. and Chan, Kevin and Govindan, Ramesh},
  doi = {doi.org/10.1145/3356250.3360041},
  year = {2019},
  date = {2019-11-11},
  booktitle = {SenSys ’19: Conference on Embedded Networked Sensor
  		  Systems},
  publisher = {ACM},
  address = {New York, USA},
  pubstate = {published},
  tppubtype = {conference},
  topics = {sensing},
}

IoTDI

Kestrel: Video Analytics for Augmented Multi-Camera Vehicle Tracking

H Qiu, X Liu, S Rallapalli, and 5 more authors

In 2018 IEEE/ACM Third International Conference on Internet-of-Things Design and Implementation (IoTDI), Feb 2018

Bib

@inproceedings{qiu18c,
  title = {Kestrel: Video Analytics for Augmented Multi-Camera
  		  Vehicle Tracking},
  author = {Qiu, H and Liu, X and Rallapalli, S and Bency, A J and Chan, K and Urgaonkar, R and Manjunath, B S and Govindan, R},
  doi = {10.1109/IoTDI.2018.00015},
  year = {2018},
  date = {2018-04-01},
  booktitle = {2018 IEEE/ACM Third International Conference on
  		  Internet-of-Things Design and Implementation (IoTDI)},
  pages = {48-59},
  pubstate = {published},
  tppubtype = {inproceedings},
  topics = {vehicular,sensing},
}

ToN

Scalability and Satisfiability of Quality-of-Information in Wireless Networks

Scott T Rager, Ertugrul N Ciftcioglu, Ram Ramanathan, and 2 more authors

IEEE/ACM Trans. Netw., Feb 2018

Bib Link

@article{rager18a,
  title = {Scalability and Satisfiability of Quality-of-Information
  		  in Wireless Networks},
  author = {Rager, Scott T and Ciftcioglu, Ertugrul N and Ramanathan, Ram and Porta, Thomas F La and Govindan, Ramesh},
  url = {https://doi.org/10.1109/TNET.2017.2781202},
  doi = {10.1109/TNET.2017.2781202},
  issn = {1063-6692},
  year = {2018},
  date = {2018-01-01},
  journal = {IEEE/ACM Trans. Netw.},
  volume = {26},
  number = {1},
  pages = {398--411},
  publisher = {IEEE Press},
  address = {Piscataway, NJ, USA},
  keywords = {},
  pubstate = {published},
  topics = {sensing},
  tppubtype = {article}
}