Random walks based multi-image segmentation: Quasiconvexity results and GPU-based solutions

Abstract

We recast the Cosegmentation problem using Random Walker (RW) segmentation as the core segmentation algorithm, rather than the traditional MRF approach adopted in the literature so far. Our formulation is similar to previous approaches in the sense that it also permits Cosegmentation constraints (which impose consistency between the extracted objects from ≥ 2 images) using a nonparametric model. However, several previous nonparametric cosegmentation methods have the serious limitation that they require adding one auxiliary node (or variable) for every pair of pixels that are similar (which effectively limits such methods to describing only those objects that have high entropy appearance models). In contrast, our proposed model completely eliminates this restrictive dependence –the resulting improvements are quite significant. Our model further allows an optimization scheme exploiting quasiconvexity for model-based segmentation with no dependence on the scale of the segmented foreground. Finally, we show that the optimization can be expressed in terms of linear algebra operations on sparse matrices which are easily mapped to GPU architecture. We provide a highly specialized CUDA library for Cosegmentation exploiting this special structure, and report experimental results showing these advantages.

Confidence-driven image co-matting

“…It was first studied by Rother et al [18] and has gained considerable attention afterwards [19,20,21,22,23]. More recently, the concept has been generalized to 3D shape segmentation problem [24,25].…”

“…A viable alternative is to first partition the input image into foreground and background regions using binary segmentation, and then create a narrow band around the foreground boundary as the unknown region by applying morphological operations. Following this routine, we first use an existing co-segmentation technique [21] to perform joint binary image segmentation, and interactive scribbled-based segmentation refinement is only involved when the result is not satisfactory. After binary segmentation is done in each image, we then create a uniform unknown region using morphological operations.…”

Improving Building Change Detection in VHR Remote Sensing Imagery by Combining Coarse Location and Co-Segmentation

“…A weak supervised methodology was used for the global constraint of the co-segmentation model to effectively deal with the change characteristics of different targets [30][31][32]. In the present study, a weak supervised co-segmentation method is also used to extract individual buildings (foreground) from blocks and capture the common features of buildings.…”

Joint Inference in Weakly-Annotated Image Datasets via Dense Correspondence

“…Since then, numerous methods were proposed to improve and refine the co-segmentation (Mukherjee et al 2009;Hochbaum and Singh 2009;Batra et al 2010;Joulin et al 2010), many of which work in the context of a pair of images with the exact same object Mukherjee et al 2009;Hochbaum and Singh 2009) or require some form of user interaction (Batra et al 2010;Collins et al 2012).…”