Superpixel Benchmark
Superpixel benchmark, tools and algorithms.
|
CDepthTools::Camera | Represents basic intrinsic parameters used to project pixels into a point cloud |
CCCS_OpenCV | Wrapper for running CCS using OpenCV images |
CCIS_OpenCV | Wrapper for running CIS with OpenCV images |
CConnectedComponents | Efficient (multi-label) connected components algorithm |
CCRS_OpenCV | Wrapper for running CRS on OpenCV images |
CDASP_OpenCV | Wrapper for running DASP on OpenCV images |
CDepthTools | Tools for using depth information |
CERGC_OpenCV | Wrapper for running ERGC on OpenCV images |
CERS_OpenCV | Wrapper for running ERS on OpenCV images |
CETPS_OpenCV | Wrapper for running ETPS on OpenCV images |
CEvaluation | Provides measures to evaluate (over-) segmentations |
CEvaluationSummary::EvaluationMetrics | Available metrics, see evaluation.h |
CEvaluationSummary::EvaluationStatistics | Available statistics that may be computed for each metric |
CEvaluationSummary | Given a directory of superpixel segmentations and a directory of ground truth segmentations, this class is used to generate a CSV file of statistics of different metrics |
CFH_OpenCV | Wrapper for running FH on OpenCV images |
CGraphSegmentation | Implementation of graph based image segmentation as described in the paper by Felzenswalb and Huttenlocher |
▼CGraphSegmentationDistance | Interface to be implemented by a concerete distance. The distance defines how the weights between nodes in the image graph are computed. See the paper by Felzenswalb and Huttenlocher for details. Essentially, derived classes only need to overwrite the () operator |
CGraphSegmentationEuclideanRGB | Euclidean RGB distance |
CGraphSegmentationManhattenRGB | Manhatten (i.e. L1) distance |
▼CGraphSegmentationMagic | The magic part of the graph segmentation, i.e. s given two nodes decide whether to add an edge between them (i.e. merge the corresponding segments). See the paper by Felzenswalb and Huttenlocher for details |
CGraphSegmentationMagicThreshold | |
CImageEdge | Represents an edge between two pixels in an image. Each edge is characterized by a weight and the adjacent nodes |
CImageEdgeSorter | Class for sorting edges according to weight |
CImageGraph | Represents an image graph, consisting of one node per pixel which are 4-connected |
CImageNode | Represents a pixel in a video. Each pixel is represented by its color which is needed to compute the weights between pixels |
CIOUtil | I/O utilities |
CLSC_OpenCV | Wrapper for running LSC on OpenCV images |
CMSS_OpenCV | Wrapper for running MSS on OpenCV images |
CParameterOptimizationTool | Tool to guide parameter optimization using grid search |
CPB_OpenCV | Wrapper for running PB on OpenCV images |
CRobustnessTool | Tool evaluating the robustness for different filters/enhancement/transformations |
▼CRobustnessToolDriver | Driver for different filters/enhancements/transformations |
CBilateralFilterDriver | Bilateral filter driver |
CBlurDriver | Blur driver |
CGaussianBlurDriver | Gaussian blur filter |
CGaussianNoiseDriver | Additive Gaussian noise and Gaussian sampling error driver |
CMedianBlurDriver | Median blur driver |
CMotionBlurDriver | Motion blur driver |
CPoissonNoiseDriver | Poisson noise driver |
CRotationDriver | Rotation driver |
CSaltAndPepperNoiseDriver | Salt and pepper noise driver |
CShearDriver | Vertical and horizontal shear driver |
CTranslationDriver | Translation driver |
Cscost | |
CSLIC_OpenCV | Wrapper for running SLIC on OpenCV images |
CSuperpixelTools | Superpixel utilities |
CEvaluationSummary::SuperpixelVisualizations | Available superpixel visualizations, see visualization.h |
CTransformation | Utility class for image and ground truth transofmrations |
CVC_OpenCV | Wrapper for running VC on OpenCV images |
CVCCS_OpenCV_PCL | Wrapper for running PCL on OpenCV images given the point cloud as OpenCV image |
CVisualization | Some basic visualizations of superpixel segmentations |
CVLSLIC_OpenCV | Wrapper for running vlSLIC on OpenCV images |