Saved in:
Bibliographic Details
Main Authors: Yu, Shan, Zhu, Zhenting, Chen, Yu, Xu, Hanchen, Zhao, Pengzhan, Wang, Yang, Padmanabhan, Arthi, Latapie, Hugo, Xu, Harry
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2311.01623
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914821310513152
author Yu, Shan
Zhu, Zhenting
Chen, Yu
Xu, Hanchen
Zhao, Pengzhan
Wang, Yang
Padmanabhan, Arthi
Latapie, Hugo
Xu, Harry
author_facet Yu, Shan
Zhu, Zhenting
Chen, Yu
Xu, Hanchen
Zhao, Pengzhan
Wang, Yang
Padmanabhan, Arthi
Latapie, Hugo
Xu, Harry
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2311_01623
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle VQPy: An Object-Oriented Approach to Modern Video Analytics
Yu, Shan
Zhu, Zhenting
Chen, Yu
Xu, Hanchen
Zhao, Pengzhan
Wang, Yang
Padmanabhan, Arthi
Latapie, Hugo
Xu, Harry
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
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.
title VQPy: An Object-Oriented Approach to Modern Video Analytics
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2311.01623