Hierarchical Piecewise-Constant Super-regions
نویسندگان
چکیده
Recent applications in computer vision have come to heavily rely on superpixel over-segmentation as a preprocessing step for higher level vision tasks, such as object recognition, image labelling or image segmentation. Here we present a new superpixel algorithm called Hierarchical Piecewise-Constant Super-regions (HPCS), which not only obtains superpixels comparable to the state-of-the-art, but can also be applied hierarchically to form what we call n-th order super-regions. In essence, a Markov Random Field (MRF)-based anisotropic denoising formulation over the quantized feature space is adopted to form piecewiseconstant image regions, which are then combined with a graph-based split & merge post-processing step to form superpixels. The graph and quantized feature based formulation of the problem allows us to generalize it hierarchically to preserve boundary adherence with fewer superpixels. Experimental results show that, despite the simplicity of our framework, it is able to provide high quality superpixels, and to hierarchically apply them to form layers of oversegmentation, each with a decreasing number of superpixels, while maintaining the same desired properties (such as adherence to strong image edges). The algorithm is also memory efficient and has a low computational cost. Keywords— superpixels, super-regions, hierarchy, segmentation, image
منابع مشابه
Complicated superstable periodic behavior in piecewise constant circuits with impulsive excitation
Abstract—This paper studies piecewise constant circuits with an impulsive switch. Since vector field of the circuit equation is piecewise constant, the trajectories are piecewise linear : it is well suited for precise analysis. First, we consider the autonomous case. The switch is controlled by a state and the circuits can exhibit chaotic behavior. Second, we consider the non-autonomous case. T...
متن کاملPlanelet Transform: A New Geometrical Wavelet for Compression of Kinect-like Depth Images
With the advent of cheap indoor RGB-D sensors, proper representation of piecewise planar depth images is crucial toward an effective compression method. Although there exist geometrical wavelets for optimal representation of piecewise constant and piecewise linear images (i.e. wedgelets and platelets), an adaptation to piecewise linear fractional functions which correspond to depth variation ov...
متن کاملHYBRID FUNCTIONS APPROACH AND PIECEWISE CONSTANT FUNCTION BY COLLOCATION METHOD FOR THE NONLINEAR VOLTERRA-FREDHOLM INTEGRAL EQUATIONS
In this work, we will compare two approximation method based on hybrid Legendre andBlock-Pulse functions and a computational method for solving nonlinear Fredholm-Volterraintegral equations of the second kind which is based on replacement of the unknown functionby truncated series of well known Block-Pulse functions (BPfs) expansion
متن کاملImage segmentation by optimal and hierarchical piecewise constant approximations
In terms of deductive Descriptive approach [3, 7] the preliminary stage of image transformation from the original form into a recognizable form is considered in the report. For this purpose, the piecewise constant image approximations are studied. According to the formal quality assessment the optimal approximations are the best, since they minimally differs from the image in the values of tota...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1605.05937 شماره
صفحات -
تاریخ انتشار 2016