Search

Superpixel is one of the most popular image over-segmentations with broad applications in the computer vision field to reduce their computations by replacing pixels as primitives. The main concerns of one superpixel generation algorithm are its accuracy and efficiency. One of the most important things in superpixel accuracy is to fit the image boundaries tightly with a few pixels as possible (namely minimal contour density, which is measured by the percent of superpixel contour pixels in the whole image). In this paper, we propose a new fast algorithm based on the clustering method to produce superpixels accurately with low contour density. First, we adopt the linear path from a pixel to one superpixel seed to define a regular term and propose a new distance measurement between them. In addition, we introduce the gradient and Local Binary Pattern (LBP) features and propose formulas of parameters in the proposed method adaptively. In this way, we can use the new distance measurement to group pixels as initial regions adaptively and produce the final superpixels by merging those small ones. Finally, we test the new algorithm on two public datasets and compare it with the state-of-the-art. Our method can generate superpixels with lower contour density while being competitive in accuracy and computational time. [ABSTRACT FROM AUTHOR]

Voronoi diagrams on triangulated surfaces based on the geodesic metric play a key role in many applications of computer graphics. Previous methods of constructing such Voronoi diagrams generally depended on having an exact geodesic metric. However, exact geodesic computation is time-consuming and has high memory usage, limiting wider application of geodesic Voronoi diagrams (GVDs). In order to overcome this issue, instead of using exact methods, we reformulate a graph method based on Steiner point insertion, as an effective way to obtain geodesic distances. Further, since a bisector comprises hyperbolic and line segments, we utilize Apollonius diagrams to encode complicated structures, enabling Voronoi diagrams to encode a medial-axis surface for a dense set of boundary samples. Based on these strategies, we present an approximation algorithm for efficient Voronoi diagram construction on triangulated surfaces. We also suggest a measure for evaluating similarity of our results to the exact GVD. Although our GVD results are constructed using approximate geodesic distances, we can get GVD results similar to exact results by inserting Steiner points on triangle edges. Experimental results on many 3D models indicate the improved speed and memory requirements compared to previous leading methods. [ABSTRACT FROM AUTHOR]

We introduce a code generator that converts unoptimized C++ code operating on sparse data into vectorized and parallel CPU or GPU kernels. Our approach unrolls the computation into a massive expression graph, performs redundant expression elimination, grouping, and then generates an architecture-specific kernel to solve the same problem, assuming that the sparsity pattern is fixed, which is a common scenario in many applications in computer graphics and scientific computing. We show that our approach scales to large problems and can achieve speedups of two orders of magnitude on CPUs and three orders of magnitude on GPUs, compared to a set of manually optimized CPU baselines. To demonstrate the practical applicability of our approach, we employ it to optimize popular algorithms with applications to physical simulation and interactive mesh deformation. [ABSTRACT FROM AUTHOR]

Adders are used to design the basic building blocks of very large scale integrated systems. Most of the computer arithmetic applications need highest degree of accuracy with good performance. In this paper a new efficient two step binary adder using carry substitution algorithm is proposed and it is implemented in digital FIR filter for filtering process. This adder architecture is very simple and efficient. Here two logic blocks namely half adder and carry substitution algorithm logic blocks are used. In the first step, the inputs are given to half adder logic block to generate the partial sum and carry bits. In the second step, carry substitution algorithm is used to compare the sum and carry bits generated by the adder logic to produce accurate final result. Here, the carry bits are not propagated from LSB to MSB. To study the effectiveness of the proposed two step binary adder, its performance is compared with the other existing parallel adders, parallel-prefix adders and approximate adders. These adders are coded in Verilog HDL and implemented in Xilinx FPGA. Simulation results show that FIR filter with the proposed adder is three times faster than FIR filter with parallel and parallel-prefix adders and two times faster than the FIR filter using approximate adders. Also the area of proposed method is 50% less and area delay product is 60% less compared to other designed FIR digital filters. [ABSTRACT FROM AUTHOR]

In recent times, there has been a tremendous progress in image dehazing for computer vision applications, while the sky region processed by these algorithms tends to degrade by noise and color distortion. In this paper, an improved dark channel prior algorithm is proposed which detects the sky region first and divides the image into sky region and non-sky region and then estimates the transmission of two parts separately, followed by combining with refining step. The proposed algorithm also accurately corrects the transmission of the sky region to avoid noise and color distortion. Experimental results show a greater quality improvement in the output images than the existing strategies. [ABSTRACT FROM AUTHOR]