1 /*M/////////////////////////////////////////////////////////////////////////////////////// 2 // 3 // IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING. 4 // 5 // By downloading, copying, installing or using the software you agree to this license. 6 // If you do not agree to this license, do not download, install, 7 // copy or use the software. 8 // 9 // 10 // License Agreement 11 // For Open Source Computer Vision Library 12 // 13 // Copyright (C) 2014, Beat Kueng (beat-kueng@gmx.net), Lukas Vogel, Morten Lysgaard 14 // Third party copyrights are property of their respective owners. 15 // 16 // Redistribution and use in source and binary forms, with or without modification, 17 // are permitted provided that the following conditions are met: 18 // 19 // * Redistribution's of source code must retain the above copyright notice, 20 // this list of conditions and the following disclaimer. 21 // 22 // * Redistribution's in binary form must reproduce the above copyright notice, 23 // this list of conditions and the following disclaimer in the documentation 24 // and/or other materials provided with the distribution. 25 // 26 // * The name of the copyright holders may not be used to endorse or promote products 27 // derived from this software without specific prior written permission. 28 // 29 // This software is provided by the copyright holders and contributors "as is" and 30 // any express or implied warranties, including, but not limited to, the implied 31 // warranties of merchantability and fitness for a particular purpose are disclaimed. 32 // In no event shall the Intel Corporation or contributors be liable for any direct, 33 // indirect, incidental, special, exemplary, or consequential damages 34 // (including, but not limited to, procurement of substitute goods or services; 35 // loss of use, data, or profits; or business interruption) however caused 36 // and on any theory of liability, whether in contract, strict liability, 37 // or tort (including negligence or otherwise) arising in any way out of 38 // the use of this software, even if advised of the possibility of such damage. 39 // 40 //M*/ 41 42 #ifndef __OPENCV_SEEDS_HPP__ 43 #define __OPENCV_SEEDS_HPP__ 44 #ifdef __cplusplus 45 46 #include <opencv2/core.hpp> 47 48 namespace cv 49 { 50 namespace ximgproc 51 { 52 53 //! @addtogroup ximgproc_superpixel 54 //! @{ 55 56 /** @brief Class implementing the SEEDS (Superpixels Extracted via Energy-Driven Sampling) superpixels 57 algorithm described in @cite VBRV14 . 58 59 The algorithm uses an efficient hill-climbing algorithm to optimize the superpixels' energy 60 function that is based on color histograms and a boundary term, which is optional. The energy 61 function encourages superpixels to be of the same color, and if the boundary term is activated, the 62 superpixels have smooth boundaries and are of similar shape. In practice it starts from a regular 63 grid of superpixels and moves the pixels or blocks of pixels at the boundaries to refine the 64 solution. The algorithm runs in real-time using a single CPU. 65 */ 66 class CV_EXPORTS_W SuperpixelSEEDS : public Algorithm 67 { 68 public: 69 70 /** @brief Calculates the superpixel segmentation on a given image stored in SuperpixelSEEDS object. 71 72 The function computes the superpixels segmentation of an image with the parameters initialized 73 with the function createSuperpixelSEEDS(). 74 */ 75 CV_WRAP virtual int getNumberOfSuperpixels() = 0; 76 77 /** @brief Calculates the superpixel segmentation on a given image with the initialized 78 parameters in the SuperpixelSEEDS object. 79 80 This function can be called again for other images without the need of initializing the 81 algorithm with createSuperpixelSEEDS(). This save the computational cost of allocating memory 82 for all the structures of the algorithm. 83 84 @param img Input image. Supported formats: CV_8U, CV_16U, CV_32F. Image size & number of 85 channels must match with the initialized image size & channels with the function 86 createSuperpixelSEEDS(). It should be in HSV or Lab color space. Lab is a bit better, but also 87 slower. 88 89 @param num_iterations Number of pixel level iterations. Higher number improves the result. 90 91 The function computes the superpixels segmentation of an image with the parameters initialized 92 with the function createSuperpixelSEEDS(). The algorithms starts from a grid of superpixels and 93 then refines the boundaries by proposing updates of blocks of pixels that lie at the boundaries 94 from large to smaller size, finalizing with proposing pixel updates. An illustrative example 95 can be seen below. 96 97  98 */ 99 CV_WRAP virtual void iterate(InputArray img, int num_iterations=4) = 0; 100 101 /** @brief Returns the segmentation labeling of the image. 102 103 Each label represents a superpixel, and each pixel is assigned to one superpixel label. 104 105 @param labels_out Return: A CV_32UC1 integer array containing the labels of the superpixel 106 segmentation. The labels are in the range [0, getNumberOfSuperpixels()]. 107 108 The function returns an image with ssthe labels of the superpixel segmentation. The labels are in 109 the range [0, getNumberOfSuperpixels()]. 110 */ 111 CV_WRAP virtual void getLabels(OutputArray labels_out) = 0; 112 113 /** @brief Returns the mask of the superpixel segmentation stored in SuperpixelSEEDS object. 114 115 @param image Return: CV_8UC1 image mask where -1 indicates that the pixel is a superpixel border, 116 and 0 otherwise. 117 118 @param thick_line If false, the border is only one pixel wide, otherwise all pixels at the border 119 are masked. 120 121 The function return the boundaries of the superpixel segmentation. 122 123 @note 124 - (Python) A demo on how to generate superpixels in images from the webcam can be found at 125 opencv_source_code/samples/python2/seeds.py 126 - (cpp) A demo on how to generate superpixels in images from the webcam can be found at 127 opencv_source_code/modules/ximgproc/samples/seeds.cpp. By adding a file image as a command 128 line argument, the static image will be used instead of the webcam. 129 - It will show a window with the video from the webcam with the superpixel boundaries marked 130 in red (see below). Use Space to switch between different output modes. At the top of the 131 window there are 4 sliders, from which the user can change on-the-fly the number of 132 superpixels, the number of block levels, the strength of the boundary prior term to modify 133 the shape, and the number of iterations at pixel level. This is useful to play with the 134 parameters and set them to the user convenience. In the console the frame-rate of the 135 algorithm is indicated. 136 137  138 */ 139 CV_WRAP virtual void getLabelContourMask(OutputArray image, bool thick_line = false) = 0; 140 ~SuperpixelSEEDS()141 virtual ~SuperpixelSEEDS() {} 142 }; 143 144 /** @brief Initializes a SuperpixelSEEDS object. 145 146 @param image_width Image width. 147 @param image_height Image height. 148 @param image_channels Number of channels of the image. 149 @param num_superpixels Desired number of superpixels. Note that the actual number may be smaller 150 due to restrictions (depending on the image size and num_levels). Use getNumberOfSuperpixels() to 151 get the actual number. 152 @param num_levels Number of block levels. The more levels, the more accurate is the segmentation, 153 but needs more memory and CPU time. 154 @param prior enable 3x3 shape smoothing term if \>0. A larger value leads to smoother shapes. prior 155 must be in the range [0, 5]. 156 @param histogram_bins Number of histogram bins. 157 @param double_step If true, iterate each block level twice for higher accuracy. 158 159 The function initializes a SuperpixelSEEDS object for the input image. It stores the parameters of 160 the image: image_width, image_height and image_channels. It also sets the parameters of the SEEDS 161 superpixel algorithm, which are: num_superpixels, num_levels, use_prior, histogram_bins and 162 double_step. 163 164 The number of levels in num_levels defines the amount of block levels that the algorithm use in the 165 optimization. The initialization is a grid, in which the superpixels are equally distributed through 166 the width and the height of the image. The larger blocks correspond to the superpixel size, and the 167 levels with smaller blocks are formed by dividing the larger blocks into 2 x 2 blocks of pixels, 168 recursively until the smaller block level. An example of initialization of 4 block levels is 169 illustrated in the following figure. 170 171  172 */ 173 CV_EXPORTS_W Ptr<SuperpixelSEEDS> createSuperpixelSEEDS( 174 int image_width, int image_height, int image_channels, 175 int num_superpixels, int num_levels, int prior = 2, 176 int histogram_bins=5, bool double_step = false); 177 178 //! @} 179 180 } 181 } 182 #endif 183 #endif 184
