Instance Segmentation of Event Camera Streams in Outdoor Monitoring Scenarios

Tobias Bolten, Regina Pohle-Fröhlich, Klaus Tönnies

2024

Abstract

Event cameras are a new type of image sensor. The pixels of these sensors operate independently and asynchronously from each other. The sensor output is a variable rate data stream that spatio-temporally encodes the detection of brightness changes. This type of output and sensor operating paradigm poses processing challenges for computer vision applications, as frame-based methods are not natively applicable. We provide the first systematic evaluation of different state-of-the-art deep learning based instance segmentation approaches in the context of event-based outdoor surveillance. For processing, we consider transforming the event output stream into representations of different dimensionalities, including point-, voxel-, and frame-based variants. We introduce a new dataset variant that provides annotations at the level of instances per output event, as well as a density-based preprocessing to generate regions of interest (RoI). The achieved instance segmentation results show that the adaptation of existing algorithms for the event-based domain is a promising approach.

Paper Citation

in Harvard Style

Bolten T., Pohle-Fröhlich R. and Tönnies K. (2024). Instance Segmentation of Event Camera Streams in Outdoor Monitoring Scenarios. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 452-463. DOI: 10.5220/0012369100003660

in Bibtex Style

@conference{visapp24,
author={Tobias Bolten and Regina Pohle-Fröhlich and Klaus Tönnies},
title={Instance Segmentation of Event Camera Streams in Outdoor Monitoring Scenarios},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={452-463},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012369100003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Instance Segmentation of Event Camera Streams in Outdoor Monitoring Scenarios
SN - 978-989-758-679-8
AU - Bolten T.
AU - Pohle-Fröhlich R.
AU - Tönnies K.
PY - 2024
SP - 452
EP - 463
DO - 10.5220/0012369100003660
PB - SciTePress