Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation

05/30/2020
by   Jianqiang Wan, et al.
7

Image segmentation is a fundamental vision task and a crucial step for many applications. In this paper, we propose a fast image segmentation method based on a novel super boundary-to-pixel direction (super-BPD) and a customized segmentation algorithm with super-BPD. Precisely, we define BPD on each pixel as a two-dimensional unit vector pointing from its nearest boundary to the pixel. In the BPD, nearby pixels from different regions have opposite directions departing from each other, and adjacent pixels in the same region have directions pointing to the other or each other (i.e., around medial points). We make use of such property to partition an image into super-BPDs, which are novel informative superpixels with robust direction similarity for fast grouping into segmentation regions. Extensive experimental results on BSDS500 and Pascal Context demonstrate the accuracy and efficency of the proposed super-BPD in segmenting images. In practice, the proposed super-BPD achieves comparable or superior performance with MCG while running at  25fps vs. 0.07fps. Super-BPD also exhibits a noteworthy transferability to unseen scenes. The code is publicly available at https://github.com/JianqiangWan/Super-BPD.

READ FULL TEXT

page 2

page 3

page 4

page 7

page 8

research
12/12/2016

Segmentation of large images based on super-pixels and community detection in graphs

Image segmentation has many applications which range from machine learni...
research
12/04/2016

A method for the segmentation of images based on thresholding and applied to vesicular textures

In image processing, a segmentation is a process of partitioning an imag...
research
02/22/2021

Direct Estimation of Appearance Models for Segmentation

Image segmentation algorithms often depend on appearance models that cha...
research
05/07/2015

Adaptive Nonparametric Image Parsing

In this paper, we present an adaptive nonparametric solution to the imag...
research
05/19/2016

Hierarchical Piecewise-Constant Super-regions

Recent applications in computer vision have come to heavily rely on supe...
research
05/06/2020

Probabilistic Color Constancy

In this paper, we propose a novel unsupervised color constancy method, c...
research
12/20/2017

Light Field Segmentation From Super-pixel Graph Representation

Efficient and accurate segmentation of light field is an important task ...

Please sign up or login with your details

Forgot password? Click here to reset