Peekaboo - Where are the Objects? Structure Adjusting Superpixels
This incremental improvement addresses image segmentation for computer vision applications, offering better performance without sacrificing speed.
The paper tackles the problem of fast and meaningful image segmentation by extending SLIC to dynamically adjust superpixel resolution based on image structure, resulting in improved boundary adherence and reduced undersegmentation error while maintaining linear runtime.
This paper addresses the search for a fast and meaningful image segmentation in the context of $k$-means clustering. The proposed method builds on a widely-used local version of Lloyd's algorithm, called Simple Linear Iterative Clustering (SLIC). We propose an algorithm which extends SLIC to dynamically adjust the local search, adopting superpixel resolution dynamically to structure existent in the image, and thus provides for more meaningful superpixels in the same linear runtime as standard SLIC. The proposed method is evaluated against state-of-the-art techniques and improved boundary adherence and undersegmentation error are observed, whilst still remaining among the fastest algorithms which are tested.