.png){kind=icon}
Return
High-efficiency sparse convolution operator for event-based cameras
.png){kind=icon}
OA
AI
DOI：10.3389/fnbot.2025.1537673.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Event-based cameras are bio-inspired vision sensors that mimic the sparse and asynchronous activation of the animal retina, offering advantages such as low latency and low computational load in various robotic applications. However, despite their inherent sparsity, most existing visual processing algorithms are optimized for conventional standard cameras and dense images captured from them, resulting in computational redundancy and high latency when applied to event-based cameras. To address this gap, we propose a sparse convolution operator tailored for event-based cameras. By selectively skipping invalid sub-convolutions and efficiently reorganizing valid computations, our operator reduces computational workload by nearly 90% and achieves almost 2x acceleration in processing speed, while maintaining the same accuracy as dense convolution operators. This innovation unlocks the potential of event-based cameras in applications such as autonomous navigation, real-time object tracking, and industrial inspection, enabling low-latency and high-efficiency perception in resource-constrained robotic systems.
Keywords:
event-based camera
sparse convolution
convolution operator
high-efficiency
low-latency
Journal
IF:
2.8
Papers:
178
Citations:
4.1K
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSave
View more