INVENTION

EVEREST - FAST DEEP VIDEO ANALYTICS

Everest – Fast Deep Video Analytics​

Principal Investigator

Professor Eric LO

Associate Professor

Department of Computer Science and Engineering

The Chinese University of Hong Kong

Dr. Eric Lo is an Associate Professor of Computer Science and Engineering (CSE) at the Chinese University of Hong Kong (CUHK). Professor Eric Lo’s research mainly focuses on video analytics, supercomputing, database, distributed systems, and data science.

About

Everest – Fast Deep Video Analytics​

Everest is a video analytics system based on deep learning. Different from other applications, Everest is programmable and can support different usages. This technology uses sophistical techniques to accelerate processing such that it enables interactive video analytics.

A Lightning-Fast Solution

Everest is a cutting-edge video analytics system that offers lightning-fast results at a fraction of the cost of traditional systems. Unlike other video analytics solutions, Everest leverages deep computer vision models in a smart and efficient way, enabling it to deliver results up to 10-20x faster (or equivalently, at 10-20x lower cost) than comparable systems that rely on GPUs.

One-click Programmable Controller

Everest has a wide range of use cases, including lost and found tracking for quickly locating misplaced items, sports analytics for real-time tactic reports during games, and traffic planning for analyzing large volumes of traffic footage. Unlike traditional video analytics solutions, Everest is fully programmable and can be customized for a variety of tasks, eliminating the need for separate systems for different tasks.

Best Demo Paper Runner Up Everest: A Top-K Deep Video Analytics System