Module rgbd 

RGB-Depth Processing

[kinfu_icp]

Modules

prelude

Structs

ColoredKinfu_ColoredKinFu

KinectFusion implementation

ColoredKinfu_Params

DepthCleaner

Object that can clean a noisy depth image

Dynafu_DynaFu

FastICPOdometry

A faster version of ICPOdometry which is used in KinectFusion implementation Partial list of differences:

ICPOdometry

Odometry based on the paper “KinectFusion: Real-Time Dense Surface Mapping and Tracking”, Richard A. Newcombe, Andrew Fitzgibbon, at al, SIGGRAPH, 2011.

Kinfu_Detail_PoseGraph

Kinfu_Intr

Kinfu_Intr_Projector

Projects camera space vector onto screen

Kinfu_Intr_Reprojector

Camera intrinsics Reprojects screen point to camera space given z coord.

Kinfu_KinFu

KinectFusion implementation

Kinfu_Params

Kinfu_Volume

Kinfu_VolumeParams

LargeKinfu

Large Scale Dense Depth Fusion implementation

LineMod_ColorGradient

\brief Modality that computes quantized gradient orientations from a color image.

LineMod_DepthNormal

\brief Modality that computes quantized surface normals from a dense depth map.

LineMod_Detector

\brief Object detector using the LINE template matching algorithm with any set of modalities.

LineMod_Feature

\brief Discriminant feature described by its location and label.

LineMod_Match

\brief Represents a successful template match.

LineMod_Modality

\brief Interface for modalities that plug into the LINE template matching representation.

LineMod_QuantizedPyramid

\brief Represents a modality operating over an image pyramid.

LineMod_Template

Odometry

Base class for computation of odometry.

OdometryFrame

Object that contains a frame data that is possibly needed for the Odometry. It’s used for the efficiency (to pass precomputed/cached data of the frame that participates in the Odometry processing several times).

Params

RgbdFrame

Object that contains a frame data.

RgbdICPOdometry

Odometry that merges RgbdOdometry and ICPOdometry by minimize sum of their energy functions.

RgbdNormals

Object that can compute the normals in an image. It is an object as it can cache data for speed efficiency The implemented methods are either:

RgbdOdometry

Odometry based on the paper “Real-Time Visual Odometry from Dense RGB-D Images”, F. Steinbucker, J. Strum, D. Cremers, ICCV, 2011.

RgbdPlane

Object that can compute planes in an image

Enums

DepthCleaner_DEPTH_CLEANER_METHOD

NIL method is from Modeling Kinect Sensor Noise for Improved 3d Reconstruction and Tracking by C. Nguyen, S. Izadi, D. Lovel

Kinfu_VolumeType

RgbdNormals_RGBD_NORMALS_METHOD

RgbdPlane_RGBD_PLANE_METHOD

Constants

DepthCleaner_DEPTH_CLEANER_NIL

Kinfu_VolumeType_COLOREDTSDF

Kinfu_VolumeType_HASHTSDF

Kinfu_VolumeType_TSDF

OdometryFrame_CACHE_ALL

OdometryFrame_CACHE_DST

OdometryFrame_CACHE_SRC

Odometry_RIGID_BODY_MOTION

Odometry_ROTATION

Odometry_TRANSLATION

RgbdNormals_RGBD_NORMALS_METHOD_FALS

RgbdNormals_RGBD_NORMALS_METHOD_LINEMOD

RgbdNormals_RGBD_NORMALS_METHOD_SRI

RgbdPlane_RGBD_PLANE_METHOD_DEFAULT

Traits

ColoredKinfu_ColoredKinFuTrait

Mutable methods for crate::rgbd::ColoredKinfu_ColoredKinFu

ColoredKinfu_ColoredKinFuTraitConst

Constant methods for crate::rgbd::ColoredKinfu_ColoredKinFu

ColoredKinfu_ParamsTrait

Mutable methods for crate::rgbd::ColoredKinfu_Params

ColoredKinfu_ParamsTraitConst

Constant methods for crate::rgbd::ColoredKinfu_Params

DepthCleanerTrait

Mutable methods for crate::rgbd::DepthCleaner

DepthCleanerTraitConst

Constant methods for crate::rgbd::DepthCleaner

Dynafu_DynaFuTrait

Mutable methods for crate::rgbd::Dynafu_DynaFu

Dynafu_DynaFuTraitConst

Constant methods for crate::rgbd::Dynafu_DynaFu

FastICPOdometryTrait

Mutable methods for crate::rgbd::FastICPOdometry

FastICPOdometryTraitConst

Constant methods for crate::rgbd::FastICPOdometry

ICPOdometryTrait

Mutable methods for crate::rgbd::ICPOdometry

ICPOdometryTraitConst

Constant methods for crate::rgbd::ICPOdometry

Kinfu_Detail_PoseGraphTrait

Mutable methods for crate::rgbd::Kinfu_Detail_PoseGraph

Kinfu_Detail_PoseGraphTraitConst

Constant methods for crate::rgbd::Kinfu_Detail_PoseGraph

Kinfu_KinFuTrait

Mutable methods for crate::rgbd::Kinfu_KinFu

Kinfu_KinFuTraitConst

Constant methods for crate::rgbd::Kinfu_KinFu

Kinfu_ParamsTrait

Mutable methods for crate::rgbd::Kinfu_Params

Kinfu_ParamsTraitConst

Constant methods for crate::rgbd::Kinfu_Params

Kinfu_VolumeParamsTrait

Mutable methods for crate::rgbd::Kinfu_VolumeParams

Kinfu_VolumeParamsTraitConst

Constant methods for crate::rgbd::Kinfu_VolumeParams

Kinfu_VolumeTrait

Mutable methods for crate::rgbd::Kinfu_Volume

Kinfu_VolumeTraitConst

Constant methods for crate::rgbd::Kinfu_Volume

LargeKinfuTrait

Mutable methods for crate::rgbd::LargeKinfu

LargeKinfuTraitConst

Constant methods for crate::rgbd::LargeKinfu

LineMod_ColorGradientTrait

Mutable methods for crate::rgbd::LineMod_ColorGradient

LineMod_ColorGradientTraitConst

Constant methods for crate::rgbd::LineMod_ColorGradient

LineMod_DepthNormalTrait

Mutable methods for crate::rgbd::LineMod_DepthNormal

LineMod_DepthNormalTraitConst

Constant methods for crate::rgbd::LineMod_DepthNormal

LineMod_DetectorTrait

Mutable methods for crate::rgbd::LineMod_Detector

LineMod_DetectorTraitConst

Constant methods for crate::rgbd::LineMod_Detector

LineMod_MatchTrait

Mutable methods for crate::rgbd::LineMod_Match

LineMod_MatchTraitConst

Constant methods for crate::rgbd::LineMod_Match

LineMod_ModalityTrait

Mutable methods for crate::rgbd::LineMod_Modality

LineMod_ModalityTraitConst

Constant methods for crate::rgbd::LineMod_Modality

LineMod_QuantizedPyramidTrait

Mutable methods for crate::rgbd::LineMod_QuantizedPyramid

LineMod_QuantizedPyramidTraitConst

Constant methods for crate::rgbd::LineMod_QuantizedPyramid

LineMod_TemplateTrait

Mutable methods for crate::rgbd::LineMod_Template

LineMod_TemplateTraitConst

Constant methods for crate::rgbd::LineMod_Template

OdometryFrameTrait

Mutable methods for crate::rgbd::OdometryFrame

OdometryFrameTraitConst

Constant methods for crate::rgbd::OdometryFrame

OdometryTrait

Mutable methods for crate::rgbd::Odometry

OdometryTraitConst

Constant methods for crate::rgbd::Odometry

ParamsTrait

Mutable methods for crate::rgbd::Params

ParamsTraitConst

Constant methods for crate::rgbd::Params

RgbdFrameTrait

Mutable methods for crate::rgbd::RgbdFrame

RgbdFrameTraitConst

Constant methods for crate::rgbd::RgbdFrame

RgbdICPOdometryTrait

Mutable methods for crate::rgbd::RgbdICPOdometry

RgbdICPOdometryTraitConst

Constant methods for crate::rgbd::RgbdICPOdometry

RgbdNormalsTrait

Mutable methods for crate::rgbd::RgbdNormals

RgbdNormalsTraitConst

Constant methods for crate::rgbd::RgbdNormals

RgbdOdometryTrait

Mutable methods for crate::rgbd::RgbdOdometry

RgbdOdometryTraitConst

Constant methods for crate::rgbd::RgbdOdometry

RgbdPlaneTrait

Mutable methods for crate::rgbd::RgbdPlane

RgbdPlaneTraitConst

Constant methods for crate::rgbd::RgbdPlane

Functions

colormap

\brief Debug function to colormap a quantized image for viewing.

depth_to3d

Converts a depth image to an organized set of 3d points. The coordinate system is x pointing left, y down and z away from the camera

depth_to3d_def

Converts a depth image to an organized set of 3d points. The coordinate system is x pointing left, y down and z away from the camera

depth_to3d_sparse

Parameters

draw_features

\brief Debug function to draw linemod features

draw_features_def

\brief Debug function to draw linemod features

get_default_line

\brief Factory function for detector using LINE algorithm with color gradients.

get_default_linemod

\brief Factory function for detector using LINE-MOD algorithm with color gradients and depth normals.

is_valid_depth

Checks if the value is a valid depth. For CV_16U or CV_16S, the convention is to be invalid if it is a limit. For a float/double, we just check if it is a NaN

is_valid_depth_1

is_valid_depth_2

is_valid_depth_3

is_valid_depth_4

is_valid_depth_5

make_volume

register_depth

Registers depth data to an external camera Registration is performed by creating a depth cloud, transforming the cloud by the rigid body transformation between the cameras, and then projecting the transformed points into the RGB camera.

register_depth_def

Registers depth data to an external camera Registration is performed by creating a depth cloud, transforming the cloud by the rigid body transformation between the cameras, and then projecting the transformed points into the RGB camera.

rescale_depth

If the input image is of type CV_16UC1 (like the Kinect one), the image is converted to floats, divided by depth_factor to get a depth in meters, and the values 0 are converted to std::numeric_limits::quiet_NaN() Otherwise, the image is simply converted to floats

rescale_depth_def

If the input image is of type CV_16UC1 (like the Kinect one), the image is converted to floats, divided by depth_factor to get a depth in meters, and the values 0 are converted to std::numeric_limits::quiet_NaN() Otherwise, the image is simply converted to floats

warp_frame

Warp the image: compute 3d points from the depth, transform them using given transformation, then project color point cloud to an image plane. This function can be used to visualize results of the Odometry algorithm.

warp_frame_def

Warp the image: compute 3d points from the depth, transform them using given transformation, then project color point cloud to an image plane. This function can be used to visualize results of the Odometry algorithm.

Type Aliases

Dynafu_Params

Backwards compatibility for old versions