arXiv:2411.18314cs.CV2024-11被引 8

用CNN实现实时目标跟踪,提升复杂场景下的精度与稳定性。

Real-time Video Target Tracking Algorithm Utilizing Convolutional Neural Networks (CNN)

  • 结合目标检测与在线学习,动态更新目标模型以适应外观变化。
  • 在快速运动、部分遮挡和复杂背景下成功率更高,失败率更低。
  • 适合视频监控与智能交通等需要高实时性的应用。

本文研究并实现了一种基于卷积神经网络(CNN)的实时视频目标跟踪算法,旨在提升复杂场景下目标跟踪的准确性和鲁棒性。针对传统跟踪算法在处理目标遮挡、形态变化及背景干扰时的局限性,该方法融合目标检测与跟踪策略,并通过在线学习机制持续更新目标模型,以适应目标外观的变化。实验结果表明,在面对快速运动、部分遮挡和复杂背景的情况下,所提算法相比多种主流跟踪算法展现出更高的跟踪成功率和更低的失败率。本研究成功将CNN应用于实时视频目标跟踪,既提升了算法的准确性与稳定性,又保持了较高的处理速度,满足实时应用需求。该算法有望为视频监控与智能交通领域的目标跟踪任务提供新解决方案。

原文摘要 · Abstract (English)

Thispaperaimstoresearchandimplementa real-timevideotargettrackingalgorithmbasedon ConvolutionalNeuralNetworks(CNN),enhancingthe accuracyandrobustnessoftargettrackingincomplex scenarios.Addressingthelimitationsoftraditionaltracking algorithmsinhandlingissuessuchastargetocclusion,morphologicalchanges,andbackgroundinterference,our approachintegratestargetdetectionandtrackingstrategies.It continuouslyupdatesthetargetmodelthroughanonline learningmechanismtoadapttochangesinthetarget's appearance.Experimentalresultsdemonstratethat,when dealingwithsituationsinvolvingrapidmotion,partial occlusion,andcomplexbackgrounds,theproposedalgorithm exhibitshighertrackingsuccessratesandlowerfailurerates comparedtoseveralmainstreamtrackingalgorithms.This studysuccessfullyappliesCNNtoreal-timevideotarget tracking,improvingtheaccuracyandstabilityofthetracking algorithmwhilemaintaininghighprocessingspeeds,thus meetingthedemandsofreal-timeapplications.Thisalgorithm isexpectedtoprovidenewsolutionsfortargettrackingtasksin videosurveillanceandintelligenttransportationdomains.

目标跟踪CNN实时系统视频分析

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。