Making Every Event Count: Balancing Data Efficiency and Accuracy in Event Camera Subsampling
This work addresses the problem of high event rates in event cameras for edge AI applications, providing insights for hardware-efficient subsampling strategies, though it is incremental in nature.
The paper tackles the challenge of balancing data efficiency and accuracy in event camera subsampling by systematically evaluating six hardware-friendly methods on event video classification tasks, finding that a simple causal density-based subsampling method improves classification accuracy in sparse regimes.
Event cameras offer high temporal resolution and power efficiency, making them well-suited for edge AI applications. However, their high event rates present challenges for data transmission and processing. Subsampling methods provide a practical solution, but their effect on downstream visual tasks remains underexplored. In this work, we systematically evaluate six hardware-friendly subsampling methods using convolutional neural networks for event video classification on various benchmark datasets. We hypothesize that events from high-density regions carry more task-relevant information and are therefore better suited for subsampling. To test this, we introduce a simple causal density-based subsampling method, demonstrating improved classification accuracy in sparse regimes. Our analysis further highlights key factors affecting subsampling performance, including sensitivity to hyperparameters and failure cases in scenarios with large event count variance. These findings provide insights for utilization of hardware-efficient subsampling strategies that balance data efficiency and task accuracy. The code for this paper will be released at: https://github.com/hesamaraghi/event-camera-subsampling-methods.