AW-GATCN: Adaptive Weighted Graph Attention Convolutional Network for Event Camera Data Joint Denoising and Object Recognition

TL;DR

This paper introduces AW-GATCN, a novel adaptive graph convolutional network that effectively denoises event camera data and improves object recognition accuracy by integrating adaptive segmentation, multifactorial edge weighting, and graph-based denoising.

Contribution

It presents a new adaptive graph-based framework that enhances noise removal and object recognition in event camera data, outperforming existing methods.

Findings

Achieves recognition accuracies up to 99.30% on challenging datasets.

Surpasses existing graph-based methods by up to 8.79% in accuracy.

Reduces noise by up to 19.57%, improving data quality for recognition.

Abstract

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.