VQPy: An Object-Oriented Approach to Modern Video Analytics

TL;DR

VQPy introduces an object-oriented Python framework for simplifying and optimizing video analytics pipelines by modeling video objects and their interactions, demonstrated through its integration into Cisco's DeepVision.

Contribution

The paper presents VQPy, a novel object-oriented approach and framework for developing and optimizing video analytics pipelines, inspired by traditional object-oriented programming.

Findings

VQPy is implemented and open-sourced.

VQPy is integrated into Cisco's DeepVision.

VQPy simplifies expressing and optimizing video analytics workflows.

Abstract

Video analytics is widely used in contemporary systems and services. At the forefront of video analytics are video queries that users develop to find objects of particular interest. Building upon the insight that video objects (e.g., human, animals, cars, etc.), the center of video analytics, are similar in spirit to objects modeled by traditional object-oriented languages, we propose to develop an object-oriented approach to video analytics. This approach, named VQPy, consists of a frontend$\unicode{x2015}$a Python variant with constructs that make it easy for users to express video objects and their interactions$\unicode{x2015}$as well as an extensible backend that can automatically construct and optimize pipelines based on video objects. We have implemented and open-sourced VQPy, which has been productized in Cisco as part of its DeepVision framework.