Event-based Batting Impact Estimation

2026-05-25

AI Summary

This work addresses the challenge of accurately estimating the precise moment of ball impact, a task hindered by the limited temporal resolution and motion blur of conventional RGB cameras as well as the invasiveness and insufficient accuracy of inertial measurement units (IMUs). To overcome these limitations, the authors propose a novel approach leveraging event cameras, which offer microsecond-level temporal resolution and high dynamic range. Their method detects impact timing through a weighted centroid distance metric, generates high-density event frames, and employs an optimized network that fuses bidirectional mask information. A new loss function is introduced to bridge the domain gap between event and RGB data. Evaluated on real-world datasets under challenging conditions such as low illumination and severe occlusion, the proposed method achieves approximately 63% lower mean absolute error compared to existing baselines.

Abstract

Estimating the precise timing of batting impact is crucial for understanding the rapid sensorimotor control. However, this task is challenging for RGB cameras due to insufficient temporal resolution and motion blur. Similarly, Inertial Measurement Units (IMUs) are impractical for actual matches due to sensor intrusiveness and their limited temporal precision. To overcome these limitations, we propose a novel framework leveraging event-based cameras, which offer microsecond resolution and high dynamic range, to estimate impact timing based on the weighted centroid distance between the detected ball and bat. To address the domain gap between event frames and RGB images that degrades segmentation accuracy, we generate high-density event frames. We then introduce a mask refinement network that leverages these frames and bidirectional mask information, optimized using a novel loss function. Experiments on real-world datasets demonstrate that our method achieves superior accuracy under challenging conditions, including low-light environments and severe occlusions, outperforming baselines by reducing the Mean Absolute Error by approximately 63%.

Problem

• batting impact estimation
• event-based cameras
• temporal resolution
• sensorimotor control
• impact timing

Innovation

• event-based camera
• impact timing estimation
• mask refinement network
• high-density event frames
• weighted centroid distance