VQPy: An Object-Oriented Approach to Modern Video Analytics
This work addresses the problem of making video analytics more accessible and efficient for users in systems and services, though it appears incremental by applying object-oriented programming concepts to an existing domain.
The authors tackled the challenge of developing video queries for object detection in video analytics by proposing VQPy, an object-oriented approach that simplifies user expression of video objects and interactions, resulting in a system that has been productized in Cisco's DeepVision framework.
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.