arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2608.10790cs.CVcs.AI

MVTrack:基于压缩比特流的超高速无外观运动目标跟踪器

MVTrack: Ultrafast Appearance-Free Moving Object Tracking from Compressed Bitstreams

  • Universitat de Barcelona(巴塞罗那大学)
  • Computer Vision Center(计算机视觉中心)
  • Aalborg Universitet(奥尔堡大学)
  • Milestone Systems(里程碑系统公司)

机构由 AI 辅助整理,请以论文原文为准。

Iñaki Erregue, Kamal Nasrollahi, Sergio Escalera

AI总结:

针对RGB目标检测器计算成本高的问题,提出直接基于H.264比特流的MVTrack,结合MVDet与MVLink,在VIRAT上性能优于YOLO26n且参数量、FLOPs、延迟大幅降低,可实现高效监控跟踪。

AI中文摘要:

大规模部署现代视频跟踪器受限于基于RGB的目标检测器的计算成本。为此,我们提出MVTrack,一种直接在H.264比特流上运行的超高速运动目标跟踪器。MVTrack结合了用于运动矢量场的轻量型检测器MVDet,以及极简运动关联模块MVLink。在VIRAT数据集上,MVTrack的性能优于YOLO26n,同时参数数量减少60倍,浮点运算量(FLOPs)减少40倍,CPU延迟降低8.6倍。这些结果表明,仅压缩视频数据即可实现准确且可扩展的监控跟踪,从而无需进行像素重建。

英文摘要:

Deploying modern video trackers at scale is bottlenecked by the computational cost of RGB-based object detectors. To this end, we present MVTrack, an ultrafast tracker for moving objects that operates directly on H.264 bitstreams. MVTrack combines MVDet, a lightweight detector for motion vector fields, with MVLink, a minimalist kinematic association module. On VIRAT, MVTrack outperforms YOLO26n while using 60$\times$ fewer parameters, requiring 40$\times$ fewer FLOPs, and reducing CPU latency by 8.6$\times$. These results demonstrate that compressed video data alone can enable accurate and scalable surveillance tracking, thereby bypassing the need for pixel reconstruction.

补充信息

↑