Superpixel Segmentation Based on Grid Point Density Peak Clustering.

Xianyi Chen,Xiafu Peng,Sun’An Wang

doi:10.3390/s21196374

Xianyi Chen, Xiafu Peng + Show 1 more

Open Access

https://doi.org/10.3390/s21196374

Copy DOI

Abstract

Superpixel segmentation is one of the key image preprocessing steps in object recognition and detection methods. However, the over-segmentation in the smoothly connected homogenous region in an image is the key problem. That would produce redundant complex jagged textures. In this paper, the density peak clustering will be used to reduce the redundant superpixels and highlight the primary textures and contours of the salient objects. Firstly, the grid pixels are extracted as feature points, and the density of each feature point will be defined. Secondly, the cluster centers are extracted with the density peaks. Finally, all the feature points will be clustered by the density peaks. The pixel blocks, which are obtained by the above steps, are superpixels. The method is carried out in the BSDS500 dataset, and the experimental results show that the Boundary Recall (BR) and Achievement Segmentation Accuracy (ASA) are 95.0% and 96.3%, respectively. In addition, the proposed method has better performance in efficiency (30 fps). The comparison experiments show that not only do the superpixel boundaries have good adhesion to the primary textures and contours of the salient objects, but they can also effectively reduce the redundant superpixels in the homogeneous region.

Highlights

Superpixel segmentation is one of the key image preprocessing steps in object recognition and detection methods
Since the superpixel is used for image preprocessing by Ren [5], many well-known superpixel segmentation methods have been proposed by scholars
The regular superpixels are segmented by the SLIC and LSC, and the irregular superpixels are produced by the ERS and SEEK

Summary

The Feature Point and Color Feature Extraction

The color and brightness features are always different among the different scenes in images. The parameters R, G, B and L, a, b are the pixel values in RGB and Lab color space, respectively. The pixels which meet the Formula (4) will be extracted as initial feature points. The parameters h, w and r, c are the row and column coordinates of the feature points and pixels in the image. The values of the color and brightness of the feature points can be computed with the Formulas (5). Li,j , ai,j and bi,j are the pixel values in the Lab color space, and i and j are the row and column coordinates of the pixels, which is an R × R region around the feature points.

The Feature Point Density

Superpixel Segmentation with Density Peak-Based Clustering

Discussion

Findings

Methods

Conclusions