High-resolution image segmentation using fully parallel mean shift

Abstract

In this paper, we present a fast and effective method of image segmentation. Our design follows the bottom-up approach: first, the image is decomposed by nonparametric clustering; then, similar classes are joined by a merging algorithm that uses color, and adjacency information to obtain consistent image content. The core of the segmenter is a parallel version of the mean shift algorithm that works simultaneously on multiple feature space kernels. Our system was implemented on a many-core GPGPU platform in order to observe the performance gain of the data parallel construction. Segmentation accuracy has been evaluated on a public benchmark and has proven to perform well among other data-driven algorithms. Numerical analysis confirmed that the segmentation speed of the parallel algorithm improves as the number of utilized processors is increased, which indicates the scalability of the scheme. This improvement was also observed on real life, high-resolution images.

α-MeanShift++: Improving MeanShift++ for Image Segmentation

“…Future studies will focus on optimizing the proposed algorithm in terms of speed to make it more practical (e.g., implementing it in Cython or C/C++ [8] and parallelizing it to run on graphics processing units [28] or field-programmable gate arrays [7]. In addition, to overcome the limitations mentioned in Section IV-D, we plan to adjust α more precisely by analyzing the color distribution of images (e.g., using histogram entropy).…”

A Smartphone based Wound Assessment System for Patients with Diabetes using Accelerated Mean Shift Algorithm

“…It also supports different types of processors such as the CPU, GPU or DSP. In addition, a program may access to all of these features without having to write code to support different architectures or a different number of processing cores [35]. On the Nexus 4 Android smartphone, we implemented the mean shift based segmentation algorithm both on the Adreno 320 GPU and Quad-core Krait CPU using Renderscript.…”

“…The algorithm implementation flow is shown as in Figure 6 and is explained below. Our implementation scheme is similar to the ones used in [35] [36]. The processing steps Color space transformation, Color histogram generation and discretization, and Weight-map generation (these steps belongs to the mean shift filtering module introduced in Section II) are all implemented on the CPU.…”