Performance Analysis of Synthetic Events via Visual Object Trackers

Mohamad Alansari, Hamad AlRemeithi, Sara Alansari, Naoufel Werghi, Sajid Javed

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This study investigated the effectiveness of synthetic events in enhancing the accuracy of visual object trackers, particularly in scenarios where conventional RGB data encounters difficulties, such as with rapidly moving objects, motion blur, and varying lighting conditions, thereby highlighting the potential of event cameras in tracking applications. Synthetic events were generated from RGB Visual Object Tracking (VOT) datasets using the v2e toolbox and post processed in Inivation Dynamic Vision (DV) software. This post processed data was subsequently fused with traditional RGB data. Evaluation was conducted through the Pytracking library to measure potential tracking improvements. The results showed a notable increase in tracking efficacy upon the integration of post processed synthetic events with RGB data. Conclusively, synthetically generated events have the capacity to augment current state-of-the-art (SOTA) VOT frameworks with minimal Neural Network (NN) adjustments.

Original languageBritish English
Title of host publicationIntelligent Computing - Proceedings of the 2024 Computing Conference
EditorsKohei Arai
PublisherSpringer Science and Business Media Deutschland GmbH
Pages364-384
Number of pages21
ISBN (Print)9783031622687
DOIs
StatePublished - 2024
EventScience and Information Conference, SAI 2024 - London, United Kingdom
Duration: 11 Jul 202412 Jul 2024

Publication series

NameLecture Notes in Networks and Systems
Volume1018 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

ConferenceScience and Information Conference, SAI 2024
Country/TerritoryUnited Kingdom
CityLondon
Period11/07/2412/07/24

Keywords

  • Event cameras
  • Fusion technique
  • Neuromorphic vision
  • Visual object tracking (VOT)

Fingerprint

Dive into the research topics of 'Performance Analysis of Synthetic Events via Visual Object Trackers'. Together they form a unique fingerprint.

Cite this