Package boofcv.abst.sfm.d3
Interface DepthVisualOdometry<Vis extends ImageBase<Vis>,Depth extends ImageGray<Depth>>
- Type Parameters:
Vis
- Visual camera sensorDepth
- Depth camera sensor
- All Superinterfaces:
VerbosePrint
,VisualOdometry<Se3_F64>
- All Known Implementing Classes:
PyramidDirectColorDepth_to_DepthVisualOdometry
,VisOdomPixelDepthPnP_to_DepthVisualOdometry
public interface DepthVisualOdometry<Vis extends ImageBase<Vis>,Depth extends ImageGray<Depth>>
extends VisualOdometry<Se3_F64>
Visual odometry that estimate the camera's ego-motion in Euclidean space using a camera image and a depth image. Camera motion is estimated relative to the first frame in the left camera's point of view.
The following is a set of assumptions and behaviors that all implementations of this interface must follow:
- Visual and depth images must be captured simultaneously
- Cameras must have a global shutter
- Calibration parameters can be changed at any time, but must be set at least once before processing an image.
- If process returns false then the motion could not be estimated and isFault() should be checked
- If isFault() is true then the reset() should be called since it can't estimate motion any more
- reset() puts back into its initial state
Optional interfaces are provided for accessing internal features.
-
Field Summary
Fields inherited from interface boofcv.abst.sfm.d3.VisualOdometry
VERBOSE_TRACKING
-
Method Summary
Modifier and TypeMethodDescriptionType of depth images it can process.Type of visual images it can process.boolean
Process the new image and update the motion estimate.void
setCalibration
(CameraPinholeBrown paramVisual, Point2Transform2_F32 visToDepth) Specifies the intrinsic parameters for the visual camera and the transform from visual to depth pixels.Methods inherited from interface org.ddogleg.struct.VerbosePrint
setVerbose
Methods inherited from interface boofcv.abst.sfm.d3.VisualOdometry
getCameraToWorld, getFrameID, isFault, reset
-
Method Details
-
setCalibration
Specifies the intrinsic parameters for the visual camera and the transform from visual to depth pixels.- Parameters:
paramVisual
- Intrinsic parameters for visual cameravisToDepth
- Transform from visual camera pixels into depth camera pixels
-
process
Process the new image and update the motion estimate. The return value must be checked to see if the estimate was actually updated. If false is returned thenVisualOdometry.isFault()
also needs to be checked to see if the pose estimate has been reset.- Parameters:
visual
- Image from visual cameradepth
- Image from depth sensor- Returns:
- true if the motion estimate has been updated and false if not
-
getVisualType
Type of visual images it can process.- Returns:
- The image type
-
getDepthType
Type of depth images it can process.- Returns:
- The image type
-