View's dependency and low‐rank background‐guided compressed sensing for multi‐view image joint reconstruction. Issue 12 (17th September 2019)

• Record Type: Journal Article
• Authors: Fei, Xuan; Li, Lei; Cao, Heling; Miao, Jianyu; Yu, Renping
• Is Part Of: IET image processing. Volume 13:Issue 12(2019)
• Page Start: 2294
• Page End: 2303
• Publication Date: 2019-09-17
• Subjects: iterative methods -- cameras -- optimisation -- image reconstruction -- convex programming -- compressed sensing; distributed CS networks -- multicamera network reconstructions -- unsatisfied joint reconstruction results -- multiple view geometry -- CS joint reconstruction method -- spatial correlation -- low‐rank background constraints -- competitive reconstruction methods -- low‐rank background‐guided -- multiview image joint reconstruction -- compressed sensing multicamera network reconstruction; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2019.0295
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Compressed sensing (CS) multi‐camera network reconstruction has attracted much attention in the field of distributed CS networks. However, many multi‐camera network reconstructions based on CS usually recover every image separately; the view's dependency and geometrical structure among these multi‐view images could be rarely considered in this way, which will result in some unsatisfied joint reconstruction results. Here, the authors introduce to extract the multiple view geometry from multi‐view images to construct the view's dependency observation model. Based on the proposed parametric transformation observation model, they propose a novel CS joint reconstruction method of multi‐view image that guided by the spatial correlation and low‐rank background constraints. The eventual optimisation model could be relaxed to a series of convex optimisation problems, which could be efficiently solved by combining the variable splitting and alternate iteration technique. The extended experimental results indicate that they proposed method has achieved a remarkable improvement in both objective criterion and visual fidelity compared with other competitive reconstruction methods.