Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Normalized Cuts and Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient Graph-Based Image Segmentation
International Journal of Computer Vision
Consistent Segmentation for Optical Flow Estimation
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Guiding Model Search Using Segmentation
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
TurboPixels: Fast Superpixels Using Geometric Flows
IEEE Transactions on Pattern Analysis and Machine Intelligence
Superpixels and supervoxels in an energy optimization framework
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Contour Detection and Hierarchical Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
International Journal of Computer Vision
Structure-sensitive superpixels via geodesic distance
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
SLIC Superpixels Compared to State-of-the-Art Superpixel Methods
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
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.