Generalized Shortest Path-based Superpixels for 3D Spherical Image Segmentation
This work addresses the need for fast and accurate image analysis in computer vision for wide-angle capture devices, offering a domain-specific tool for 360-degree image segmentation.
The authors tackled the problem of segmenting wide-angle 360-degree spherical images by introducing a new superpixel method called SphSPS, which respects the 3D spherical geometry and generalizes shortest paths to improve clustering. Their method significantly outperformed existing planar and spherical approaches in segmentation accuracy, robustness to noise, and regularity on benchmark datasets.
The growing use of wide angle image capture devices and the need for fast and accurate image analysis in computer visions have enforced the need for dedicated under-representation approaches. Most recent decomposition methods segment an image into a small number of irregular homogeneous regions, called superpixels. Nevertheless, these approaches are generally designed to segment standard 2D planar images, i.e., captured with a 90o angle view without distortion. In this work, we introduce a new general superpixel method called SphSPS (for Spherical Shortest Path-based Superpixels)1 , dedicated to wide 360o spherical or omnidirectional images. Our method respects the geometry of the 3D spherical acquisition space and generalizes the notion of shortest path between a pixel and a superpixel center, to fastly extract relevant clustering features. We demonstrate that considering the geometry of the acquisition space to compute the shortest path enables to jointly improve the segmentation accuracy and the shape regularity of superpixels. To evaluate this regularity aspect, we also generalize a global regularity metric to the spherical space, addressing the limitations of the only existing spherical compactness measure. Finally, the proposed SphSPS method is validated on the reference 360o spherical panorama segmentation dataset and on synthetic road omnidirectional images. Our method significantly outperforms both planar and spherical state-of-the-art approaches in terms of segmentation accuracy,robustness to noise and regularity, providing a very interesting tool for superpixel-based applications on 360o images.