Generalized Shortest Path-based Superpixels for Accurate Segmentation of Spherical Images

Rémi Giraud (1, 2) , Rodrigo Borba Pinheiro (1) , Yannick Berthoumieu (2, 1)

1 Bordeaux INP - Institut Polytechnique de Bordeaux
2 IMS - Laboratoire de l'intégration, du matériau au système

Most of existing superpixel methods are designed to segment standard planar images as pre-processing for computer vision pipelines. Nevertheless, the increasing number of applications based on wide angle capture devices, mainly generating 360° spherical images, have enforced the need for dedicated superpixel approaches. In this paper, we introduce a new superpixel method for spherical images called SphSPS (for Spherical Shortest Path-based Superpixels). Our approach respects the spherical geometry and generalizes the notion of shortest path between a pixel and a superpixel center on the 3D spherical acquisition space. We show that the feature information on such path can be efficiently integrated into our clustering framework and jointly improves the respect of object contours and the shape regularity. To relevantly evaluate this last aspect in the spherical space, we also generalize a planar global regularity metric. Finally, the proposed SphSPS method obtains significantly better performances than both planar and spherical recent superpixel approaches on the reference 360° spherical panorama segmentation dataset.

Mots clés: Superpixels; Spherical images; Regularity

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement des images [eess.IV]

Rémi Giraud, Rodrigo Borba Pinheiro, Yannick Berthoumieu. Generalized Shortest Path-based Superpixels for Accurate Segmentation of Spherical Images. International Conference on Pattern Recognition (ICPR 2020), Jan 2021, Milan, Italy. ⟨hal-02539465⟩