1. NCCU Academic Hub
  2. 學術產出
  3. College of Informatics
  4. Proceedings
  5. Item

學術產出-Proceedings

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 Pedestrian detection using covariance descriptor and on-line learning
作者 Liao, Wen-Hung;Huang, Ling-Wei
廖文宏
貢獻者 資科系
關鍵詞 Bayes Classifier; Covariance descriptor; Covariance features; Data sets; Flexible bodies; Object classification; Online learning; Pedestrian detection; Precision and recall; Still images; Test sets; Training conditions; Adaptive boosting; Artificial intelligence; Statistical tests; Support vector machines; E-learning
日期 2011-11
上傳時間 8-Apr-2015 17:34:07 (UTC+8)
摘要 Pedestrian detection is an important yet challenging problem in object classification due to flexible body pose, loose clothing and ever-changing illumination. In this paper, we employ covariance features and propose an on-line learning classifier which combines naïve Bayes classifier and cascade support vector machines (SVM) to improve the precision and recall rate of pedestrian detection in still images. Experimental results show that our strategy can significantly increase both precision and recall rates in some difficult situations. Furthermore, even under the same initial training condition, our method outperforms HOG + AdaBoost in USC Pedestrian Detection Test Set, INRIA Person dataset and Penn-Fudan Database for Pedestrian Detection and Segmentation. © 2011 IEEE.
關聯 Proceedings - 2011 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2011, 論文編號 6120740, 179-182
10.1109/TAAI.2011.38
資料類型 conference
DOI http://dx.doi.org/10.1109/TAAI.2011.38
dc.contributor 資科系
dc.creator (作者) Liao, Wen-Hung;Huang, Ling-Wei
dc.creator (作者) 廖文宏zh_TW
dc.date (日期) 2011-11
dc.date.accessioned 8-Apr-2015 17:34:07 (UTC+8)-
dc.date.available 8-Apr-2015 17:34:07 (UTC+8)-
dc.date.issued (上傳時間) 8-Apr-2015 17:34:07 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/74408-
dc.description.abstract (摘要) Pedestrian detection is an important yet challenging problem in object classification due to flexible body pose, loose clothing and ever-changing illumination. In this paper, we employ covariance features and propose an on-line learning classifier which combines naïve Bayes classifier and cascade support vector machines (SVM) to improve the precision and recall rate of pedestrian detection in still images. Experimental results show that our strategy can significantly increase both precision and recall rates in some difficult situations. Furthermore, even under the same initial training condition, our method outperforms HOG + AdaBoost in USC Pedestrian Detection Test Set, INRIA Person dataset and Penn-Fudan Database for Pedestrian Detection and Segmentation. © 2011 IEEE.
dc.format.extent 281 bytes-
dc.format.mimetype text/html-
dc.relation (關聯) Proceedings - 2011 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2011, 論文編號 6120740, 179-182
dc.relation (關聯) 10.1109/TAAI.2011.38
dc.subject (關鍵詞) Bayes Classifier; Covariance descriptor; Covariance features; Data sets; Flexible bodies; Object classification; Online learning; Pedestrian detection; Precision and recall; Still images; Test sets; Training conditions; Adaptive boosting; Artificial intelligence; Statistical tests; Support vector machines; E-learning
dc.title (題名) Pedestrian detection using covariance descriptor and on-line learning
dc.type (資料類型) conferenceen
dc.identifier.doi (DOI) 10.1109/TAAI.2011.38en_US
dc.doi.uri (DOI) http://dx.doi.org/10.1109/TAAI.2011.38en_US