直接在压缩视频流上追踪目标，速度提升3.7倍且精度损失仅4%。
See Without Decoding: Motion-Vector-Based Tracking in Compressed Video
- 利用压缩数据中的运动矢量和变换系数，跳过完整解码
- 在MOTS15/17/20上实现3.7倍加速，[email protected]仅降4%
- 适合大规模监控系统实时分析，节省算力
我们提出一种轻量级压缩域追踪模型，可直接在视频流上运行，无需完整解码为RGB视频。该模型利用压缩数据中的运动矢量和变换系数，跨帧传播目标边界框，在MOTS15/17/20数据集上相较RGB基线实现高达3.7倍的计算加速，仅导致4%的[email protected]下降。结果表明，编码器域运动建模在大规模监控系统的实时分析中具有高效性。
原文摘要 · Abstract (English)
We propose a lightweight compressed-domain tracking model that operates directly on video streams, without requiring full RGB video decoding. Using motion vectors and transform coefficients from compressed data, our deep model propagates object bounding boxes across frames, achieving a computational speed-up of order up to 3.7 with only a slight 4% [email protected] drop vs RGB baseline on MOTS15/17/20 datasets. These results highlight codec-domain motion modeling efficiency for real-time analytics in large monitoring systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。