基于多任务学习的行人重识别算法研究
Research on person re-identification algorithm based on multi-task learning
秘蓉新 1姚文文 1吴兵灏2
作者信息
- 1. 国家计算机网络应急技术处理协调中心,北京 100029
- 2. 北京邮电大学计算机学院,北京 100876
- 折叠
摘要
行人重识别(person re-identification,re-ID)在多摄像机之间进行跨镜检索以匹配目标行人图像,可以在人脸、指纹等生物特征失效的情况下实现行人关联,已成为智能视频监控系统的关键技术,对智能安防、智慧城市等领域的产业落地进行了有效赋能.传统的行人重识别算法通常采用表征学习或度量学习方法.基于多任务学习的机器学习模式,结合表征学习与度量学习方法,综合利用特征表示和距离度量两方面的优势,采用分类损失和三元组损失共同训练模型,使模型在特征提取和相似性度量上都得到充分的训练.实验结果表明,该方法在行人重识别任务中取得了更好的性能,验证了鲁棒性和在泛化能力方面的优越性.
Abstract
Person re-identification(re-ID)involves the cross-camera retrieval and matching of target pedestrian im-ages,facilitating pedestrian association in scenarios where biometric features such as faces and fingerprints may prove ineffective.It has become a pivotal technology in intelligent video surveillance systems,playing a crucial role in domains like smart security and smart cities.Traditional re-ID algorithms typically employ either representation learning or metric learning methods.A novel approach was proposed which combined representation learning and metric learning methods based on the multi-task learning machine learning paradigm.By capitalizing on the advan-tages of both feature representation and distance metric,and concurrently training the model using classification loss and triplet loss,comprehensive training for both feature extraction and similarity measurement was ensured.Experi-mental results validate the effectiveness of the proposed approach,demonstrating superior performance in re-ID tasks and underscoring the robustness and superior generalization capability.
关键词
行人重识别/智能视频监控/表征学习/度量学习/多任务学习Key words
person re-identification/intelligent video surveillance/representation learning/metric learning/multi-task learning引用本文复制引用
出版年
2024
NETL
NSTL
万方数据