计算机工程与科学2024，Vol.46Issue(7)：1256-1268,13.DOI:10.3969/j.issn.1007-130X.2024.07.014
基于度量学习的跨摄像头运动目标重定位方法研究
Transversal cameras relocation for moving object based on metric learning
摘要
Abstract
In recent years,the pollution from diesel vehicle exhaust emissions in China has become increasingly severe.In order to improve the atmospheric environment,it is necessary to monitor diesel vehicles emitting black smoke.However,in urban traffic road scenarios,the detection of black smoke vehicles is often difficult to determine through rear-view videos due to factors such as mutual obstruction between vehicles.Additionally,the severe lack of relevant data greatly limits the effectiveness of the da-ta.To address the above problems,this paper proposes a black smoke diesel vehicle re-identification model under the cross-camera scene.By introducing the IBN module to construct a feature extraction network,the adaptability of the network model to changes in the appearance of diesel vehicle images is enhanced.A loss function based on the Hausdorff distance metric learning is designed to measure the feature differences,increasing inter-class distance and reducing the impact of occluded samples during the optimization process.Then,benchmark datasets for diesel vehicle repositioning across multiple sce-narios are constructed,and the proposed method is experimented on this dataset.The experimental re-sults show that the proposed method achieves a relative accuracy of 83.79%,demonstrating high accu-racy.关键词
跨摄像头/黑烟车重定位/度量学习Key words
transversal cameras/black smoke vehicle re-identification/metric learning分类
信息技术与安全科学引用本文复制引用
康宇,史珂豪,陈佳艺,曹洋,许镇义..基于度量学习的跨摄像头运动目标重定位方法研究[J].计算机工程与科学,2024,46(7):1256-1268,13.基金项目
国家自然科学基金(62033012,62103124) （62033012,62103124）
安徽省重大科技专项(202003a07020009) （202003a07020009）
宿迁学院京东学院开放基金(2022JDXM14) （2022JDXM14）
安徽省工业互联网智能应用与安全工程研究中心开放基金(IASII22-03) （IASII22-03）
