DocumentCode :
2963230
Title :
A Maximum Margin Segmentation Selection for Visual Object Detection
Author :
Yang, Yang ; Li, Shanping
Author_Institution :
Dept. of Comput. Sci., Zhejiang Univ., Hangzhou, China
Volume :
2
fYear :
2011
fDate :
28-29 March 2011
Firstpage :
344
Lastpage :
349
Abstract :
Visual object detection is to predict the bounding box and the label of each object from the target classes in realistic scenes. Previous detection algorithms focus on training models to fit pre-segmented local patches. However, the patches themselves are not always meaningful due to the unsupervised segmentation mistakes. In this paper, a maximum margin method is proposed to get the optimal patches and the corresponding models simultaneously. The learning task is formulated as a quadratic programming (QP) problem and implemented in its dual form. When testing, we compute multiple segmentations of each image and select one segmentation with the maximum margin to predict their labels. We evaluate the detection performance of our algorithm on Pascal VOC2007 challenge data set and show some improved results with other detection algorithms.
Keywords :
image segmentation; object detection; quadratic programming; Pascal VOC2007; feature extraction; maximum margin segmentation selection; quadratic programming problem; visual object detection; Feature extraction; Image color analysis; Image segmentation; Object segmentation; Support vector machines; Training; Visualization; classification; maxi-mum margin method; visual object detection;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Computation Technology and Automation (ICICTA), 2011 International Conference on
Conference_Location :
Shenzhen, Guangdong
Print_ISBN :
978-1-61284-289-9
Type :
conf
DOI :
10.1109/ICICTA.2011.370
Filename :
5750895
Link To Document :
بازگشت