4D implicit shape model for rotation invariant contour-based object detection
Autor: | Niloofar Gheissari, Maedeh Ahmadi, Maziar Palhang |
---|---|
Rok vydání: | 2017 |
Předmět: |
Implicit Shape Model
business.industry Computer science media_common.quotation_subject Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Image segmentation 01 natural sciences Object detection Voting 0103 physical sciences Fourth Dimension 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence Invariant (mathematics) 010306 general physics business ComputingMethodologies_COMPUTERGRAPHICS media_common |
Zdroj: | 2017 10th Iranian Conference on Machine Vision and Image Processing (MVIP). |
DOI: | 10.1109/iranianmvip.2017.8342330 |
Popis: | In this paper, we present a rotation invariant contour-based object detection method. An Implicit Shape Model (ISM) is learnt utilizing local contour features. As opposed to the original ISM, in which voting is performed in a 3D location-scale voting space, we propose a 4D ISM which estimates the in-plane rotation angle of an object as the fourth dimension of the voting space in addition to its location and scale. Experimental results on a data set containing rotated objects demonstrate the capability of our proposed approach in localizing rotated objects. |
Databáze: | OpenAIRE |
Externí odkaz: |