Search

In this paper, we propose a depth restoration method using a novel superpixel technique. Guided by a normal map reconstructed from the raw depth data, this technique over-segments RGB-D images into many small regions where their depth is assumed to be smooth. As the raw depth data is incomplete, we further introduce a depth confidence map to identify the regions which are more reliable. With the produced superpixels, we can restore the incomplete depth map using a per-superpixel linear regression. A multiresolution su-perpixel strategy is employed when some superpixels do not contain enough valid data. Experiments show that the proposed depth restoration method can effectively fill the wide gaps along depth discontinuities without blurring the object boundaries and the depth discontinuities.

We consider a monopoly Infrastructure-as-a-Service (IaaS) provider market with a set of Software-as-a-Service (SaaS) providers, where each SaaS provider lease the virtual machines (VMs) from the IaaS provider to provide cloud-based application services to its end-users. We investigate the problem of designing a joint pricing and capacity planning scheme from the IaaS provider's perspective. Specifically, we first study the SaaS providers' optimal decisions in terms of the amount of end-user requests to admit and the number of VMs to lease, given the resource price charged by the IaaS provider. Next, based on the best responses of the SaaS providers, we study joint pricing and capacity planning to maximize the IaaS provider's profit, which is determined by the revenue obtained through supplying the VMs and the energy cost for maintaining the active servers. By exploring the relationship between the optimal capacity and price, we simplify the original optimization problem into the a convex problem with respect to the price, and then we derive the expressions of the optimal solutions. Finally, the numerical results illustrate the efficacy of our proposed joint pricing and capacity planning scheme.