IEEE Transactions on Pattern Analysis and Machine Intelligence
SLIC Superpixels Compared to State-of-the-Art Superpixel Methods
✓ Free legal copy found
Preprint, hosted by École Polytechnique Fédérale de Lausanne (infoscience.epfl.ch)
This is the authors’ own version from before peer review, so it may differ from the published paper.
Read it free at infoscience.epfl.ch →Other free copies
Abstract
Computer vision applications have come to rely increasingly on superpixels in recent years, but it is not always clear what constitutes a good superpixel algorithm. In an effort to understand the benefits and drawbacks of existing methods, we empirically compare five state-of-the-art superpixel algorithms for their ability to adhere to image boundaries, speed, memory efficiency, and their impact on segmentation performance. We then introduce a new superpixel algorithm, simple linear iterative clustering (SLIC), which adapts a k-means clustering approach to efficiently generate superpixels. Despite its simplicity, SLIC adheres to boundaries as well as or better than previous methods. At the same time, it is faster and more memory efficient, improves segmentation performance, and is straightforward to extend to supervoxel generation.
DOI: 10.1109/tpami.2012.120 · Publisher: Institute of Electrical and Electronics Engineers (IEEE)