摘要
针对行人重识别在损坏场景下训练集和测试集分布差距过大、背景复杂度过高和噪声种类过多导致识别性能过低的问题,提出基于相机感知的域自适应行人重识别模型,引入并充分利用相机信息,在训练阶段对齐不同摄像机的图像分布,在测试阶段利用时序信息进行排序优化,减少训练集和测试集分布差异带来的影响,有效应对背景复杂度和噪声种类的问题.模型不仅从数据集处理角度有效减轻损坏图像的影响,还对排序优化进行二次加权,显著提高其在损坏场景中的性能.在Market-1501、DukeMTMC-reID、CUHK03数据集上的实验表明文中模型的有效性.
To solve the problem of low performance in person re-identification caused by large distribution differences between the training and testing sets in corruption scenarios,high background complexity and excessive noise types,a domain adaptive person re-identification model based on camera perception is proposed.The model aligns the image distribution of different cameras during the training phase by introducing and fully utilizing camera information.During the testing phase,temporal information is employed for ranking optimization,reducing the impact of distribution differences between the training and testing sets.The issues of background complexity and noise types are effectively addressed.The model not only effectively mitigates the impact of damaged images from the perspective of dataset processing but also significantly improves the performance of the model in corruption scenarios through quadratic weighting of sorting optimization.Experiments on Market-1501,DukeMTMC-reID and CUHK03 datasets demonstrate the effectiveness of the proposed algorithm.
作者
杨章静
吴数立
黄璞
杨国为
YANG Zhangjing;WU Shuli;HUANG Pu;YANG Guowei(School of Computer Science,Nanjing Audit University,Nanjing 211815)
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2024年第5期383-397,共15页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金项目(No.62172229)
江苏省自然科学基金项目(No.BK20221349)资助。
关键词
行人重识别
损坏场景
时序信息
批量标准化
Person Re-identification
Corruption Scenario
Temporal Information
Batch Normalization
