Contour-Based Object Detection Using Max-Margin Hough Transform

Author

Ahmadi, Maedeh ; Palhang, Maziar ; Gheissari, Niloofar

Author_Institution

Dept. of Electr. & Comput. Eng., Isfahan Univ. of Technol., Isfahan, Iran

fYear

2011

fDate

16-17 Nov. 2011

Firstpage

1

Lastpage

5

Abstract

In this paper, a contour-based object detection method based on Max-Margin Hough transform is proposed. We learn Implicit Shape Model using local contour features namely Pair of Adjacent Segments (PAS) features. A Max-Margin Hough transform (M²HT) [1] is then applied, where local parts generate weighted votes for possible object locations. Weights are learnt so that higher weights are assigned to parts which repeatedly appear in consistent locations. The achieved results on TUD cows reference dataset show that discriminative learning of weights improves the contour-based Hough detector.

Keywords

Hough transforms; feature extraction; learning (artificial intelligence); object detection; contour-based Hough detector; contour-based object detection; implicit shape model; local contour features; max-margin Hough transform; pair-of-adjacent segments feature; weight discriminative learning; Detectors; Feature extraction; Image segmentation; Object detection; Shape; Training; Transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Vision and Image Processing (MVIP), 2011 7th Iranian

Conference_Location

Tehran

Print_ISBN

978-1-4577-1533-4

Type

conf

DOI

10.1109/IranianMVIP.2011.6121585

Filename

6121585