Out of the Room: Generalizing Event-Based Dynamic Motion Segmentation for Complex Scenes

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Georgoulis, Stamatios, Ren, Weining, Bochicchio, Alfredo, Eckert, Daniel, Li, Yuanyou, Gawel, Abel
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909131434098688
author Georgoulis, Stamatios
Ren, Weining
Bochicchio, Alfredo
Eckert, Daniel
Li, Yuanyou
Gawel, Abel
author_facet Georgoulis, Stamatios
Ren, Weining
Bochicchio, Alfredo
Eckert, Daniel
Li, Yuanyou
Gawel, Abel
contents Rapid and reliable identification of dynamic scene parts, also known as motion segmentation, is a key challenge for mobile sensors. Contemporary RGB camera-based methods rely on modeling camera and scene properties however, are often under-constrained and fall short in unknown categories. Event cameras have the potential to overcome these limitations, but corresponding methods have only been demonstrated in smaller-scale indoor environments with simplified dynamic objects. This work presents an event-based method for class-agnostic motion segmentation that can successfully be deployed across complex large-scale outdoor environments too. To this end, we introduce a novel divide-and-conquer pipeline that combines: (a) ego-motion compensated events, computed via a scene understanding module that predicts monocular depth and camera pose as auxiliary tasks, and (b) optical flow from a dedicated optical flow module. These intermediate representations are then fed into a segmentation module that predicts motion segmentation masks. A novel transformer-based temporal attention module in the segmentation module builds correlations across adjacent 'frames' to get temporally consistent segmentation masks. Our method sets the new state-of-the-art on the classic EV-IMO benchmark (indoors), where we achieve improvements of 2.19 moving object IoU (2.22 mIoU) and 4.52 point IoU respectively, as well as on a newly-generated motion segmentation and tracking benchmark (outdoors) based on the DSEC event dataset, termed DSEC-MOTS, where we show improvement of 12.91 moving object IoU.
format Preprint
id arxiv_https___arxiv_org_abs_2403_04562
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Out of the Room: Generalizing Event-Based Dynamic Motion Segmentation for Complex Scenes
Georgoulis, Stamatios
Ren, Weining
Bochicchio, Alfredo
Eckert, Daniel
Li, Yuanyou
Gawel, Abel
Computer Vision and Pattern Recognition
Rapid and reliable identification of dynamic scene parts, also known as motion segmentation, is a key challenge for mobile sensors. Contemporary RGB camera-based methods rely on modeling camera and scene properties however, are often under-constrained and fall short in unknown categories. Event cameras have the potential to overcome these limitations, but corresponding methods have only been demonstrated in smaller-scale indoor environments with simplified dynamic objects. This work presents an event-based method for class-agnostic motion segmentation that can successfully be deployed across complex large-scale outdoor environments too. To this end, we introduce a novel divide-and-conquer pipeline that combines: (a) ego-motion compensated events, computed via a scene understanding module that predicts monocular depth and camera pose as auxiliary tasks, and (b) optical flow from a dedicated optical flow module. These intermediate representations are then fed into a segmentation module that predicts motion segmentation masks. A novel transformer-based temporal attention module in the segmentation module builds correlations across adjacent 'frames' to get temporally consistent segmentation masks. Our method sets the new state-of-the-art on the classic EV-IMO benchmark (indoors), where we achieve improvements of 2.19 moving object IoU (2.22 mIoU) and 4.52 point IoU respectively, as well as on a newly-generated motion segmentation and tracking benchmark (outdoors) based on the DSEC event dataset, termed DSEC-MOTS, where we show improvement of 12.91 moving object IoU.
title Out of the Room: Generalizing Event-Based Dynamic Motion Segmentation for Complex Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.04562