Superpixel Segmentation Based on Grid Point Density Peak Clustering

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.

Region-adaptive superpixel segmentation algorithm based on density clustering

“…They need to accurately reflect the characteristics of the initial superpixels, providing the initial feature basis for the subsequent pixel partitioning. Traditional superpixel segmentation algorithms often start by uniformly gridding the entire image [11] , selecting the grid centers as initial seed points. They then use a greedy algorithm to calculate pixel similarities, iteratively fitting the superpixel edges to the image edges until convergence, ultimately generating superpixels.…”

“…Using Equation (10), the color difference Dc between pixel i and pixel j is calculated, representing the color distance between pixels. Through Equation (11), the spatial distance Ds between pixel i and pixel j is computed. Equation (12) expresses the pixel distance between pixels i and j, indicating the similarity between pixels.…”

UAV formation method based on triposition positioning model

“…Two-station directional cross-location [13] is used to orientate targets at two or more stations by means of directional equipment with high accuracy [14] . At the same time, dual-station directional cross-location is a widely used passive positioning technique with a simple principle of action and easy operation [15] .…”

An Image Segmentation Method Based on the Law of Universal Gravitation and Adaptive Affinity Propagation Spectrum Clustering

“…e conventional clustering algorithms are the K-means algorithm and FCM algorithm, which generalize the K-means algorithm from the perspective of fuzzy set theory [8]. eir advantages are simple algorithms and fast execution, and the disadvantages are that they cannot guarantee global optimality, require manual input of the number of clustering categories, and are sensitive to noise and outliers.…”