Superpixel Hierarchy
This addresses a bottleneck in computer vision applications requiring multi-scale image segmentation, offering a practical solution for real-time processing.
The paper tackles the lack of a real-time method for generating accurate superpixel hierarchies across all scales by proposing the Super Hierarchy (SH) algorithm, which matches state-of-the-art accuracy while being 1-2 orders of magnitude faster and can integrate with efficient edge detectors to outperform in segmentation accuracy.
Superpixel segmentation is becoming ubiquitous in computer vision. In practice, an object can either be represented by a number of segments in finer levels of detail or included in a surrounding region at coarser levels of detail, and thus a superpixel segmentation hierarchy is useful for applications that require different levels of image segmentation detail depending on the particular image objects segmented. Unfortunately, there is no method that can generate all scales of superpixels accurately in real-time. As a result, a simple yet effective algorithm named Super Hierarchy (SH) is proposed in this paper. It is as accurate as the state-of-the-art but 1-2 orders of magnitude faster. The proposed method can be directly integrated with recent efficient edge detectors like the structured forest edges to significantly outperforms the state-of-the-art in terms of segmentation accuracy. Quantitative and qualitative evaluation on a number of computer vision applications was conducted, demonstrating that the proposed method is the top performer.