Camera as a Service

Bringing cloud-scale and machine learning to software-defined cameras and IoT devices

Camera as a Service

Research overview

Intelligent cameras such as video doorbells and CCTV are abundant today, yet only used for a single-purpose, privacy-invasive and bandwidth-heavy streaming.

Nokia Bell Labs has developed a software solution that transforms intelligent cameras with automated machine learning operations (MLOps), enabling them to provide a range of services, including traffic flow, pedestrian analysis, asset tracking, or even facial recognition. With robust security controls and privacy-preserving query serving, the data is kept safe and anonymized.

By running multiple machine learning (ML) models that can be updated over the air, these cameras become agile, multi-functional, and upgradable devices as new algorithms enable different capabilities to be added on demand.

APA style publications

Chulhong Min, Akhil Mathur, Alessandro Montanari, and Fahim Kawsar, “SensiX: A System for Best-effort Inference of Machine Learning Models in Multi-device Environments,” in IEEE Transactions on Mobile Computing, 2022doi: 10.1109/TMC.2022.3173914. (Link)
Utku Günay Acer, Marc van den Broeck, Chulhong Min, Mallesham Dasari, and Fahim Kawsar. 2022. “The City as a Personal Assistant: Turning Urban Landmarks into Conversational Agents for Serving Hyper Local Information,” in Proc. ACM Interactive, Mobile, Wearable and Ubiquitous Technologies. 6, 2, Article 40 (July 2022), 31 pages. (Link)
Alessandro Montanari, Manuja Sharma, Dainius Jenkus, Mohammed Alloulah, Lorena Qendro, and Fahim Kawsar. 2020. ePerceptive: energy reactive embedded intelligence for batteryless sensors. In Proceedings of the 18th Conference on Embedded Networked Sensor Systems (SenSys '20). Association for Computing Machinery, New York, NY, USA, 382–394. (Link)