State-of-the-art object detectors typically use shape information as a low level feature representation to capture the local structure of an object. This paper shows that early fusion of shape and color, as is popular in image classification, leads to a significant drop in performance for object detection. Moreover, such approaches also yields suboptimal results for object categories with varying importance of color and shape. In this paper we propose the use of color attributes as an explicit color representation for object detection. Color attributes are compact, computationally efficient, and when combined with traditional shape features provide state-of-the-art results for object detection. Our method is tested on the PASCAL VOC 2007 and 2009 datasets and results clearly show that our method improves over state-of-the-art techniques despite its simplicity. We also introduce a new dataset consisting of cartoon character images in which color plays a pivotal role. On this dataset, our approach yields a significant gain of 14% in mean AP over conventional state-of-the-art methods.

Color attributes for object detection / Khan, Fahad Shahbaz; Anwer, Rao Muhammad; Van De Weijer, Joost; Bagdanov, Andrew D.; Vanrell, Maria; Lopez, Antonio M.. - STAMPA. - (2012), pp. 3306-3313. (Intervento presentato al convegno 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012 tenutosi a Providence, RI, usa nel 2012) [10.1109/CVPR.2012.6248068].

Color attributes for object detection

BAGDANOV, ANDREW DAVID;
2012

Abstract

State-of-the-art object detectors typically use shape information as a low level feature representation to capture the local structure of an object. This paper shows that early fusion of shape and color, as is popular in image classification, leads to a significant drop in performance for object detection. Moreover, such approaches also yields suboptimal results for object categories with varying importance of color and shape. In this paper we propose the use of color attributes as an explicit color representation for object detection. Color attributes are compact, computationally efficient, and when combined with traditional shape features provide state-of-the-art results for object detection. Our method is tested on the PASCAL VOC 2007 and 2009 datasets and results clearly show that our method improves over state-of-the-art techniques despite its simplicity. We also introduce a new dataset consisting of cartoon character images in which color plays a pivotal role. On this dataset, our approach yields a significant gain of 14% in mean AP over conventional state-of-the-art methods.
2012
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
Providence, RI, usa
2012
Khan, Fahad Shahbaz; Anwer, Rao Muhammad; Van De Weijer, Joost; Bagdanov, Andrew D.; Vanrell, Maria; Lopez, Antonio M.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1014812
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 263
  • ???jsp.display-item.citation.isi??? 176
social impact