ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream最新文献_第3页

Enhanced human behavior recognition using HMM and evaluative rectification 利用HMM和评价校正增强人类行为识别

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2010-10-29 DOI: 10.1145/1877868.1877880

N. Doulamis, A. Voulodimos, D. Kosmopoulos, T. Varvarigou

{"title":"Enhanced human behavior recognition using HMM and evaluative rectification","authors":"N. Doulamis, A. Voulodimos, D. Kosmopoulos, T. Varvarigou","doi":"10.1145/1877868.1877880","DOIUrl":"https://doi.org/10.1145/1877868.1877880","url":null,"abstract":"Human behavior recognition and real world environments monitoring constitute challenging research problems rapidly gaining momentum over the last years. Methods for time series classification like the Hidden Markov Models have been employed in the past for similar tasks, however in many challenging cases they fail, since some behaviors are much more difficult to model than others. This happens particularly in cases that there is scarcity of labelled data.\u0000 In this paper we introduce a novel re-adjustment framework of behavior recognition and classification by allowing the user incorporation in the learning process.\u0000 The proposed Evaluative Rectification approach aims at dynamically correcting erroneous classification results to enhance the behavior modeling and therefore the overall classification rates. We evaluate the performance of the examined approach in a challenging real-life industrial environment of an automobile manufacturer. Our experiments indicate a significant outperformance of the proposed Evaluative Rectification scheme compared with traditional classification frameworks, such as Hidden Markov Models.","PeriodicalId":360789,"journal":{"name":"ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128459561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 25

Real time illumination invariant motion change detection 实时照明不变运动变化检测

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2010-10-29 DOI: 10.1145/1877868.1877887

Konstantinos Avgerinakis, A. Briassouli, Y. Kompatsiaris

引用次数: 3

Dense spatio-temporal features for non-parametric anomaly detection and localization 用于非参数异常检测和定位的密集时空特征

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2010-10-29 DOI: 10.1145/1877868.1877877

Lorenzo Seidenari, M. Bertini, A. Bimbo

引用次数: 16

Human action recognition with MPEG-7 descriptors and architectures 使用MPEG-7描述符和体系结构的人类动作识别

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2010-10-29 DOI: 10.1145/1877868.1877885

Z. Moghaddam, M. Piccardi

引用次数: 4

Joint multitarget object tracking and interaction analysis by a probabilistic bio-inspired model 基于概率仿生模型的联合多目标跟踪与交互分析

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2010-10-29 DOI: 10.1145/1877868.1877874

Francesco Monti, S. Maludrottu, C. Regazzoni

引用次数: 0

Event-based unobtrusive authentication using multi-view image sequences 使用多视图图像序列的基于事件的非突兀身份验证

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2010-10-29 DOI: 10.1145/1877868.1877886

A. Drosou, K. Moustakas, D. Tzovaras

引用次数: 6