Robust Impact Timing Estimation in Sports under Low-Light and Occluded Conditions

• Item type: SIG Technical Reports(1)
• 公開日: 2026-02-25
• タイトル / 言語: ja
• タイトル: Robust Impact Timing Estimation in Sports under Low-Light and Occluded Conditions
• タイトル / 言語: en
• タイトル: Robust Impact Timing Estimation in Sports under Low-Light and Occluded Conditions
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: 野球1
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Keio University
• 著者所属: Keio University
• 著者所属: Keio University
• 著者所属: NTT Communication Science Laboratories
• 著者所属: NTT Communication Science Laboratories
• 著者所属: Keio University
• 著者所属(英): en
• 著者所属(英): Keio University
• 著者所属(英): en
• 著者所属(英): Keio University
• 著者所属(英): en
• 著者所属(英): Keio University
• 著者所属(英): en
• 著者所属(英): NTT Communication Science Laboratories
• 著者所属(英): en
• 著者所属(英): NTT Communication Science Laboratories
• 著者所属(英): en
• 著者所属(英): Keio University
• 著者名: Ryotaro,Ishida; Wataru,Ikeda; Ryosei,Hara; Akemi,Kobayashi; Toshitaka,Kimura; Mariko,Isogawa
• 著者名(英): Ryotaro Ishida; Wataru Ikeda; Ryosei Hara; Akemi Kobayashi; Toshitaka Kimura; Mariko Isogawa
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: 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%.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: 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%.
• 書誌レコードID / 識別子タイプ: NCID
• 書誌レコードID / 関連識別子: AB00027484
• 書誌情報: 研究報告スポーツ情報学（SI）; 巻 2026-SI-4, 号 13, p. 1-6, 発行日 2026-02-25
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2759-4408
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会