 |
    |
SEEDS: Superpixels Extracted via Energy-Driven Sampling
Michael Van den Bergh1, Xavier Boix1, Gemma Roig1, Benjamin de Capitani1, and Luc Van Gool1, 2
1Computer Vision Lab, ETH Zurich, Switzerland
vamichae@vision.ee.ethz.ch
boxavier@vision.ee.ethz.ch
gemmar@vision.ee.ethz.ch
decapitb@ee.ethz.ch
vangool@vision.ee.ethz.ch
2KU Leuven, Belgium
Abstract. Superpixel algorithms aim to over-segment the image by grouping pixels that belong to the same object. Many state-of-the-art superpixel algorithms rely on minimizing objective functions to enforce color homogeneity. The optimization is accomplished by sophisticated methods that progressively build the superpixels, typically by adding cuts or growing superpixels. As a result, they are computationally too expensive for real-time applications. We introduce a new approach based on a simple hill-climbing optimization. Starting from an initial superpixel partitioning, it continuously refines the superpixels by modifying the boundaries. We define a robust and fast to evaluate energy function, based on enforcing color similarity between the boundaries and the superpixel color histogram. In a series of experiments, we show that we achieve an excellent compromise between accuracy and efficiency. We are able to achieve a performance comparable to the state-of-the-art, but in real-time on a single Intel i7 CPU at 2.8GHz.
Keywords: superpixels, segmentation
LNCS 7578, p. 13 ff.
lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012