In the field of computer vision, velocity moments are weighted averages of the intensities of pixels in a sequence of images, similar to image moments but in addition to describing an object's shape also describe its motion through the sequence of images. Velocity moments can be used to aid automated identification of a shape in an image when information about the motion is significant in its description. There are currently two established versions of velocity moments: Cartesian and Zernike.
Cartesian velocity moments
Cartesian moments for single images
A Cartesian moment of a single image is calculated by where and are the dimensions of the image, is the intensity of the pixel at the point in the image, and is the basis function.
Cartesian velocity moments for sequences of images
Cartesian velocity moments are based on these Cartesian moments. A Cartesian velocity moment is defined by where and are again the dimensions of the image, is the number of images in the sequence, and is the intensity of the pixel at the point in image. is taken from Central moments, added so the equation is translation invariant, defined as where is the coordinate of the centre of mass for image, and similarly for. introduces velocity into the equation as where is the coordinate of the centre of mass for the previous image,, and again similarly for. After the Cartesian velocity moment is calculated, it can be normalised by where is the average area of the object, in pixels, and is the number of images. Now the value is not affected by the number of images in the sequence or the size of the object. As Cartesian moments are non-orthogonal, so are Cartesian velocity moments, so different moments can be closely correlated. These velocity moments do however provide translation and scale invariance.
Zernike velocity moments
Zernike moments for single images
A Zernike moment of a single image is calculated by where denotes the complex conjugate, is an integer between and, and is an integer such that is even and. For calculating Zernike moments, the image, or section of the image which is of interest is mapped to the unit disc, then is the intensity of the pixel at the point on the disc and is a restriction on values of and. The coordinates are then mapped to polar coordinates, and and are the polar coordinates of the point on the unit disc map. is derived from Zernike polynomials and is defined by
Zernike velocity moments for sequences of images
Zernike velocity moments are based on these Zernike moments. A Zernike velocity moment is defined by where is again the number of images in the sequence, and is the intensity of the pixel at the point on the unit disc mapped from image. introduces velocity into the equation in the same way as in the Cartesian velocity moments and is from the Zernike moments equation above. Like the Cartesian velocity moments, Zernike velocity moments can be normalised by where is the average area of the object, in pixels, and is the number of images. As Zernike velocity moments are based on the orthogonal Zernike moments, they produce less correlated and more compact descriptions than Cartesian velocity moments. Zernike velocity moments also provide translation and scale invariance.
