Saved in:
Bibliographic Details
Main Authors: Li, Haiyu, Abhayaratne, Charith
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.11232
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912394358292480
author Li, Haiyu
Abhayaratne, Charith
author_facet Li, Haiyu
Abhayaratne, Charith
contents Event cameras, which capture brightness changes with high temporal resolution, inherently generate a significant amount of redundant and noisy data beyond essential object structures. The primary challenge in event-based object recognition lies in effectively removing this noise without losing critical spatial-temporal information. To address this, we propose an Adaptive Graph-based Noisy Data Removal framework for Event-based Object Recognition. Specifically, our approach integrates adaptive event segmentation based on normalized density analysis, a multifactorial edge-weighting mechanism, and adaptive graph-based denoising strategies. These innovations significantly enhance the integration of spatiotemporal information, effectively filtering noise while preserving critical structural features for robust recognition. Experimental evaluations on four challenging datasets demonstrate that our method achieves superior recognition accuracies of 83.77%, 76.79%, 99.30%, and 96.89%, surpassing existing graph-based methods by up to 8.79%, and improving noise reduction performance by up to 19.57%, with an additional accuracy gain of 6.26% compared to traditional Euclidean-based techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11232
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AW-GATCN: Adaptive Weighted Graph Attention Convolutional Network for Event Camera Data Joint Denoising and Object Recognition
Li, Haiyu
Abhayaratne, Charith
Computer Vision and Pattern Recognition
Event cameras, which capture brightness changes with high temporal resolution, inherently generate a significant amount of redundant and noisy data beyond essential object structures. The primary challenge in event-based object recognition lies in effectively removing this noise without losing critical spatial-temporal information. To address this, we propose an Adaptive Graph-based Noisy Data Removal framework for Event-based Object Recognition. Specifically, our approach integrates adaptive event segmentation based on normalized density analysis, a multifactorial edge-weighting mechanism, and adaptive graph-based denoising strategies. These innovations significantly enhance the integration of spatiotemporal information, effectively filtering noise while preserving critical structural features for robust recognition. Experimental evaluations on four challenging datasets demonstrate that our method achieves superior recognition accuracies of 83.77%, 76.79%, 99.30%, and 96.89%, surpassing existing graph-based methods by up to 8.79%, and improving noise reduction performance by up to 19.57%, with an additional accuracy gain of 6.26% compared to traditional Euclidean-based techniques.
title AW-GATCN: Adaptive Weighted Graph Attention Convolutional Network for Event Camera Data Joint Denoising and Object Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.11232