{"title":"One-Shot Any-Scene Crowd Counting With Local-to-Global Guidance.","authors":"Jiwei Chen, Zengfu Wang","doi":"10.1109/TIP.2024.3420713","DOIUrl":null,"url":null,"abstract":"<p><p>Due to different installation angles, heights, and positions of the camera installation in real-world scenes, it is difficult for crowd counting models to work in unseen surveillance scenes. In this paper, we are interested in accurate crowd counting based on the data collected by any surveillance camera, that is to count the crowd from any scene given only one annotated image from that scene. To this end, we firstly pose crowd counting as a one-shot learning task. Through the metric-learning, we propose a simple yet effective method that firstly estimates crowd characteristics and then transfers them to guide the model to count the crowd. Specifically, to fully capture these crowd characteristics of the target scene, we devise the Multi-Prototype Learner to learn the prototypes of foreground and density from the limited support image using the Expectation-Maximization algorithm. To learn the adaptation capability for any unseen scene, estimated multi prototypes are proposed to guide the crowd counting of query images in a local-to-global way. CNN is utilized to activate the local features. And transformer is introduced to correlate global features. Extensive experiments on three surveillance datasets suggest that our method outperforms the SOTA methods in the few-shot crowd counting.</p>","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TIP.2024.3420713","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Due to different installation angles, heights, and positions of the camera installation in real-world scenes, it is difficult for crowd counting models to work in unseen surveillance scenes. In this paper, we are interested in accurate crowd counting based on the data collected by any surveillance camera, that is to count the crowd from any scene given only one annotated image from that scene. To this end, we firstly pose crowd counting as a one-shot learning task. Through the metric-learning, we propose a simple yet effective method that firstly estimates crowd characteristics and then transfers them to guide the model to count the crowd. Specifically, to fully capture these crowd characteristics of the target scene, we devise the Multi-Prototype Learner to learn the prototypes of foreground and density from the limited support image using the Expectation-Maximization algorithm. To learn the adaptation capability for any unseen scene, estimated multi prototypes are proposed to guide the crowd counting of query images in a local-to-global way. CNN is utilized to activate the local features. And transformer is introduced to correlate global features. Extensive experiments on three surveillance datasets suggest that our method outperforms the SOTA methods in the few-shot crowd counting.
由于真实世界场景中摄像机安装的角度、高度和位置不同,人群计数模型很难在未见监控场景中工作。在本文中,我们感兴趣的是基于任意监控摄像机收集的数据进行精确的人群计数,即在仅有一张来自任意场景的注释图像的情况下,对该场景中的人群进行计数。为此,我们首先将人群计数假设为一次学习任务。通过度量学习,我们提出了一种简单而有效的方法,即首先估计人群特征,然后将这些特征用于指导模型对人群进行计数。具体来说,为了充分捕捉目标场景的人群特征,我们设计了多原型学习器,利用期望最大化算法从有限的支持图像中学习前景和密度的原型。为了学习对任何未见场景的适应能力,我们提出了估计多原型,以从局部到全局的方式指导查询图像的人群计数。利用 CNN 激活本地特征。并引入变换器来关联全局特征。在三个监控数据集上进行的大量实验表明,我们的方法在少镜头人群计数方面优于 SOTA 方法。