Edge/cloud Video Analytics

Location of Research: Remote

Live Video Analytics on IoT Edge provides a platform to build intelligent video applications that span the edge and the cloud. Edge computing is an emerging paradigm that distributes computing resources closer to end-users. The need for timely response arises in both human and machine to machine applications (e.g., gaming AR, VR, autonomous drones, and industrial machinery). The goal is to develop a platform that offers the capability to capture, record, and analyze live video along with publishing the results (video and/or video analytics) in real-time. Students will explore online adaptation of video analytics pipeline where the objective is to maximize accuracy under bandwidth and computational power constraints.

Lab: Wireless and Mobile Networking (WiMNet) Lab

Direct Supervisor: Mahshid Ghasemi Dehkordi

Position Dates: Spring 2021 & Summer 2021

Hours per Week: 10 - 20 hours

Paid Position: Yes

Credit: Yes

Number of positions: 1

Qualifications

  • Knowledge of networking
  • Programming knowledge: C/C++, Shell, Python
  • Deep learning, Computer vision, Reinforcement learning

Eligibility

  • Freshman, Sophomore, Junior, Senior, Master's 

Gil Zussman, Professor of Electrical Engineering, Columbia University
gil.zussman@columbia.edu