Scholarlink

The exponential growth of video data necessitates more efficient video analysis systems. Many prior studies focused on accelerating video analysis, and one representative method among them is frame filtering. However, traditional frame filtering methods focus on the temporal domain, neglecting the spatial domain. We introduce SDFMD, a lightweight system that filters frames spatially, enhancing processing speed over models like DETR. SDFMD operates in three stages: spatial frame filtering, feature extraction via a Transformer encoder, and analysis using a Transformer decoder to output categories and detection boxes. Experiments indicate SDFMD doubles the encoding and decoding speed of videos, increases video analysis throughput by 9.43%, at a sacrifice of less than 20% reduction in video analysis accuracy.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

SDFMD: Spatial Domain Filtering for Accelerating Video Analysis

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Hebin Sun,
  • Liu Wei,
  • Meizhao Liu,
  • Yingcheng Gu,
  • Fei Xia,
  • Kai Liu,
  • Yu Song,
  • Huanyu Cheng,
  • Lei Tang,
  • Sheng Zhang

摘要

The exponential growth of video data necessitates more efficient video analysis systems. Many prior studies focused on accelerating video analysis, and one representative method among them is frame filtering. However, traditional frame filtering methods focus on the temporal domain, neglecting the spatial domain. We introduce SDFMD, a lightweight system that filters frames spatially, enhancing processing speed over models like DETR. SDFMD operates in three stages: spatial frame filtering, feature extraction via a Transformer encoder, and analysis using a Transformer decoder to output categories and detection boxes. Experiments indicate SDFMD doubles the encoding and decoding speed of videos, increases video analysis throughput by 9.43%, at a sacrifice of less than 20% reduction in video analysis accuracy.