Single Run Action Detector over Video Stream - A Privacy Preserving Approach

Anbumalar Saravanan, Justin Sanchez, Hassan Ghasemzadeh, Aurelia Macabasco-O’Connell, Hamed Tabkhi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper takes initial strides at designing and evaluating a vision-based system for privacy ensured activity monitoring. The proposed technology utilizing Artificial Intelligence (AI)-empowered proactive systems offering continuous monitoring, behavioral analysis, and modeling of human activities. To this end, this paper presents Single Run Action Detector (S-RAD) which is a real-time privacy-preserving action detector that performs end-to-end action localization and classification. It is based on Faster-RCNN combined with temporal shift modeling and segment based sampling to capture the human actions. Results on UCF-Sports and UR Fall dataset present comparable accuracy to State-of-the-Art approaches with significantly lower model size and computation demand and the ability for real-time execution on edge embedded device (e.g. Nvidia Jetson Xavier).

Original languageEnglish (US)
Title of host publicationDeep Learning for Human Activity Recognition - 2nd International Workshop, DL-HAR 2020, Held in Conjunction with IJCAI-PRICAI 2020, Proceedings
EditorsXiaoli Li, Min Wu, Zhenghua Chen, Le Zhang
PublisherSpringer Science and Business Media Deutschland GmbH
Pages85-98
Number of pages14
ISBN (Print)9789811605741
DOIs
StatePublished - 2021
Externally publishedYes
Event2nd International Workshop on Deep Learning for Human Activity Recognition, DL-HAR 2020, held in conjunction with IJCAI-PRICAI 2020 - Virtual, Online
Duration: Jan 8 2021Jan 8 2021

Publication series

NameCommunications in Computer and Information Science
Volume1370
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference2nd International Workshop on Deep Learning for Human Activity Recognition, DL-HAR 2020, held in conjunction with IJCAI-PRICAI 2020
CityVirtual, Online
Period1/8/211/8/21

Keywords

  • Action detection
  • Deep learning
  • Edge computing
  • Real time
  • Spatial-temporal neural network

ASJC Scopus subject areas

  • Computer Science(all)
  • Mathematics(all)

Fingerprint

Dive into the research topics of 'Single Run Action Detector over Video Stream - A Privacy Preserving Approach'. Together they form a unique fingerprint.

Cite this