Hierarchical Graph-Based Segmentation in Detection of Object-Related Regions

Object detection is an important task in computer vision. Recently, several unsupervised approaches have been proposed to cope with this problem in a category-independent manner. This work evaluates the adoption of a hierarchical graph-based segmentation along with an state-of-the-art method to detect object-related regions. A hierarchical segmentation approach produces a set of partitions at different detail levels, in a way that a coarser level can be obtained by a simple merge of finer ones. Experimental results show that our proposal obtains an increase of 11% in object detection rate.

[1]  ZissermanAndrew,et al.  The Pascal Visual Object Classes Challenge , 2015 .

[2]  Jean Cousty,et al.  Incremental Algorithm for Hierarchical Minimum Spanning Forests and Saliency of Watershed Cuts , 2011, ISMM.

[3]  Daniel P. Huttenlocher,et al.  Efficient Graph-Based Image Segmentation , 2004, International Journal of Computer Vision.

[4]  Jean Cousty,et al.  Erratum to “Hierarchizing graph-based image segmentation algorithms relying on region dissimilarity: the case of the Felzenszwalb-Huttenlocher method” , 2019, Math. Morphol. Theory Appl..

[5]  Hui Zhang,et al.  Image segmentation evaluation: A survey of unsupervised methods , 2008, Comput. Vis. Image Underst..

[6]  Hervé Le Men,et al.  Scale-Sets Image Analysis , 2005, International Journal of Computer Vision.

[7]  Cristian Sminchisescu,et al.  CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Xin Zhang,et al.  Object class detection: A survey , 2013, CSUR.

[9]  Thomas Deselaers,et al.  Measuring the Objectness of Image Windows , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Koen E. A. van de Sande,et al.  Segmentation as selective search for object recognition , 2011, 2011 International Conference on Computer Vision.

[11]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Jean Cousty,et al.  A Hierarchical Image Segmentation Algorithm Based on an Observation Scale , 2012, SSPR/SPR.

[13]  Derek Hoiem,et al.  Category-Independent Object Proposals with Diverse Ranking , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.