SHOT: Unique signatures of histograms for surface and texture description

• Published in: Computer vision and image understanding Vol. 125; pp. 251 - 264
• Main Authors: Salti, Samuele, Tombari, Federico, Di Stefano, Luigi
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Inc 01.08.2014; Elsevier
• Subjects: 3D descriptors; 3D reconstruction; Applied sciences; Artificial intelligence; Computer science; control theory; systems; Exact sciences and technology; Histograms; Object recognition; Pattern recognition. Digital image processing. Computational geometry; Proposals; Robustness; Sensors; Shot; Signatures; Surface matching; Texture; Three dimensional; 3D descriptors; 3D reconstruction; Object recognition; Surface matching; Availability; Computer vision; Histogram; Information integration; Stimulus; Image processing; Taxonomy; Pattern recognition; Texture; Color image; Depth of field; Image reconstruction; Computational geometry; Stimulus complexity; Tridimensional image; Robustness; Surface conditions; Frame of reference

•This paper presents a local 3D descriptor for surface matching dubbed SHOT.•Our proposal includes a repeatable local reference frame as well as a 3D descriptor.•It enables seamless description of shape and color data from RGB-D sensors.•It is validated in object recognition, 3D reconstruction and s...