Direct method for rotation estimation from spherical images using 3D mesh surfaces with SPHARM representation

Abstract : Since a large field of view obviously bears important advantages, the use of spherical images is becoming increasingly important in various computer vision and image processing applications. This paper presents a novel rotation estimation approach for spherical images based on 3D mesh representation of gray level intensity. Once the 3D meshes of the underlying spherical images are obtained, the 3D rotation can be estimated directly and efficiently, without feature extraction and matching process. Subsequently, we propose a direct method for 3D object rotation estimation using spherical harmonics representation with SVD decomposition and ICP algorithm for estimation refinement. Experimental results validate our approach and prove its suitability and robustness for rotation estimation. Moreover, it performs well against noisy images, brightness changes, image compression and occlusions. A comparative study of our proposed approach with four similar methods for 3D rotation estimation between spherical images, is realized to prove its effectiveness.
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01390671
Contributor : Frédéric Davesne <>
Submitted on : Wednesday, November 2, 2016 - 11:59:13 AM
Last modification on : Monday, October 28, 2019 - 10:50:22 AM

Identifiers

Citation

Houssem Eddine Benseddik, Hicham Hadj-Abdelkader, Cherki Brahim, Samia Bouchafa. Direct method for rotation estimation from spherical images using 3D mesh surfaces with SPHARM representation. Journal of Visual Communication and Image Representation, Elsevier, 2016, 40 (Part B), pp.708--720. ⟨10.1016/j.jvcir.2016.08.010⟩. ⟨hal-01390671⟩

Share

Metrics

Record views

217