EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Dong, Yiting, He, Xiang, Shen, Guobin, Zhao, Dongcheng, Li, Yang, Zeng, Yi
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909490197037056
author Dong, Yiting
He, Xiang
Shen, Guobin
Zhao, Dongcheng
Li, Yang
Zeng, Yi
author_facet Dong, Yiting
He, Xiang
Shen, Guobin
Zhao, Dongcheng
Li, Yang
Zeng, Yi
contents Dynamic Vision Sensors (DVS) capture event data with high temporal resolution and low power consumption, presenting a more efficient solution for visual processing in dynamic and real-time scenarios compared to conventional video capture methods. Event data augmentation serve as an essential method for overcoming the limitation of scale and diversity in event datasets. Our comparative experiments demonstrate that the two factors, spatial integrity and temporal continuity, can significantly affect the capacity of event data augmentation, which are guarantee for maintaining the sparsity and high dynamic range characteristics unique to event data. However, existing augmentation methods often neglect the preservation of spatial integrity and temporal continuity. To address this, we developed a novel event data augmentation strategy EventZoom, which employs a temporal progressive strategy, embedding transformed samples into the original samples through progressive scaling and shifting. The scaling process avoids the spatial information loss associated with cropping, while the progressive strategy prevents interruptions or abrupt changes in temporal information. We validated EventZoom across various supervised learning frameworks. The experimental results show that EventZoom consistently outperforms existing event data augmentation methods with SOTA performance. For the first time, we have concurrently employed Semi-supervised and Unsupervised learning to verify feasibility on event augmentation algorithms, demonstrating the applicability and effectiveness of EventZoom as a powerful event-based data augmentation tool in handling real-world scenes with high dynamics and variability environments.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18880
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision
Dong, Yiting
He, Xiang
Shen, Guobin
Zhao, Dongcheng
Li, Yang
Zeng, Yi
Computer Vision and Pattern Recognition
Dynamic Vision Sensors (DVS) capture event data with high temporal resolution and low power consumption, presenting a more efficient solution for visual processing in dynamic and real-time scenarios compared to conventional video capture methods. Event data augmentation serve as an essential method for overcoming the limitation of scale and diversity in event datasets. Our comparative experiments demonstrate that the two factors, spatial integrity and temporal continuity, can significantly affect the capacity of event data augmentation, which are guarantee for maintaining the sparsity and high dynamic range characteristics unique to event data. However, existing augmentation methods often neglect the preservation of spatial integrity and temporal continuity. To address this, we developed a novel event data augmentation strategy EventZoom, which employs a temporal progressive strategy, embedding transformed samples into the original samples through progressive scaling and shifting. The scaling process avoids the spatial information loss associated with cropping, while the progressive strategy prevents interruptions or abrupt changes in temporal information. We validated EventZoom across various supervised learning frameworks. The experimental results show that EventZoom consistently outperforms existing event data augmentation methods with SOTA performance. For the first time, we have concurrently employed Semi-supervised and Unsupervised learning to verify feasibility on event augmentation algorithms, demonstrating the applicability and effectiveness of EventZoom as a powerful event-based data augmentation tool in handling real-world scenes with high dynamics and variability environments.
title EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.18880