Main Page   Class List   Function List   File List   Examples  

---

Motion2D.h File Reference

File included when using CMotion2DModel, CMotion2DPyramid, CMotion2DEstimator or CMotion2DWarping. More...

Go to the source code of this file.

Compounds
struct	TImageFloat
struct	TImageShort
Defines
#define	MAXCOEFSMODEL   13
Enumerations
enum	EIdModel {   NO_MDL, MDL_TX, MDL_TY, MDL_TR,   MDL_AFF_TX_DIV, MDL_AFF_TR_DIV, MDL_AFF_TR_ROT, MDL_AFF_TX_NULL,   MDL_AFF_TY_NULL, MDL_AFF_DIV_NULL, MDL_AFF_ROT_NULL, MDL_AFF_HYP1_NULL,   MDL_AFF_HYP2_NULL, MDL_AFF_TR_ROT_DIV, MDL_AFF_COMPLET, MDL_QUA_PAN_DIV,   MDL_QUA_PAN_TILT, MDL_QUA_PAN_TILT_DIV, MDL_QUA_2D, MDL_QUA_COMPLET }

---

Detailed Description

File included when using CMotion2DModel, CMotion2DPyramid, CMotion2DEstimator or CMotion2DWarping.

---

Define Documentation

#define MAXCOEFSMODEL   13

Maximal number of parameters for a given 2D polynomial motion model. This number is equal CMotion2DModel::MDL_NMAX_COEF + 1, to take into account global illumination changes.

---

Enumeration Type Documentation

enum EIdModel

The implemented 2D polynomial motion models. Using matrix notation, these models can always be stated in the general way by: which is linear with respect to the n motion parameters , and where denotes the spatial position of a point in , the flow vector modeled at point ; is a matrix, the form of wich depends on the chosen model, but the coefficients of which depend only on the point coordinates. Enumeration values: NO_MDL  No model is defined. MDL_TX  2D translation motion model along the axis with 1 parameter : MDL_TY  2D translation motion model along the axis with 1 parameter : MDL_TR  2D translation motion model with 2 parameters : MDL_AFF_TX_DIV  2D affine motion model with 2 parameters taking into account the translation along the axis and the 2D divergence: MDL_AFF_TR_DIV  2D affine motion model with 3 parameters taking into account the 2D translation and the 2D divergence: MDL_AFF_TR_ROT  2D affine motion model with 3 parameters taking into account the 2D translation and the 2D rotation: MDL_AFF_TX_NULL  2D affine motion model with 5 parameters with: If we express the parameter vector in another basis of elementary motion sub-fields with: , , and , this motion model has the particularity to consider the translation along the axis as null (ie. ) MDL_AFF_TY_NULL  2D affine motion model with 5 parameters with: If we express the parameter vector in another basis of elementary motion sub-fields with: , , and , this motion model has the particularity to consider the translation along the axis as null (ie. ) MDL_AFF_DIV_NULL  2D affine motion model with 5 parameters with: If we express the parameter vector in another basis of elementary motion sub-fields with: , , and , this motion model has the particularity to consider the divergence term at zero (ie. ) MDL_AFF_ROT_NULL  2D affine motion model with 5 parameters with: If we express the parameter vector in another basis of elementary motion sub-fields with: , , and , this motion model has the particularity to consider the curl term at zero (ie. ) MDL_AFF_HYP1_NULL  2D affine motion model with 5 parameters with: If we express the parameter vector in another basis of elementary motion sub-fields with: , , and , this motion model has the particularity to consider the first hyperbolic term at zero (ie. ). MDL_AFF_HYP2_NULL  2D affine motion model with 5 parameters with: If we express the parameter vector in another basis of elementary motion sub-fields with: , , and , this motion model has the particularity to consider the second hyperbolic term at zero (ie. ). MDL_AFF_TR_ROT_DIV  2D affine motion model with 4 parameters able to consider motion like 2D translation with 2D rotation and divergence: If we express the parameter vector in another basis of elementary motion sub-fields with: , , and , this motion model has the particularity to consider the hyperbolic terms at zero (ie. ). MDL_AFF_COMPLET  2D affine motion model with 6 parameters taking into account constant and affine parameters: This model is a good tradeoff between complexity and representativeness. It can take into account many kind of motion (translation, rotation, scaling, deformation), and even if a rigid 3D motion gives rise to a quadratic model in the image plane, the affine flow recovers the essential part. MDL_QUA_PAN_DIV  2D quadratic motion model with 4 parameters taking into account the translation along the axis, some affine and quadratic parameters: MDL_QUA_PAN_TILT  2D quadratic motion model with 4 parameters taking into account the 2D translation and some quadratic parameters: MDL_QUA_PAN_TILT_DIV  Quadratic 2D motion model with 5 parameters taking into account the 2D translation, some affine and quadratic parameters: MDL_QUA_2D  2D quadratic motion model with 8 parameters taking into account the constants, the linear and some quadratic parameters: MDL_QUA_COMPLET  2D quadratic motion model with 12 parameters taking into account the constants, the linear and all the quadratic parameters:

---