Block Matching

Estimate motion between images or video frames

Libraries:
Computer Vision Toolbox / Analysis & Enhancement

Description

The Block Matching block estimates motion between two images or two video frames by comparing blocks of pixels. The block matches the block of pixels between frames by moving the block of pixels over a search region.

Examples

Estimate Motion between Two Images

Use the Block Matching block to estimate motion between two images.

Open Script

Ports

Input

expand all

I/I1 — Image or video frame
scalar | vector | matrix

Image or video frame, specified as a scalar, vector, or matrix. If the Estimate motion between parameter is set to Two images, the name of this port changes to I1.

I2 — Image or video frame
scalar | vector | matrix

Image or video frame, specified as a scalar, vector, or matrix.

Dependencies

To enable this port, set the Estimate motion between parameter to Two images.

Output

expand all

|V|^2 — Velocity magnitudes
scalar | vector | matrix

Velocity magnitudes, returned as a scalar, vector, or matrix.

V — Velocity components in complex form
scalar | vector | matrix

Velocity components in complex form, returned as a scalar, vector, or matrix.

Dependencies

To expose this port, set the Velocity output parameter to Horizontal and vertical components in complex form.

Parameters

expand all

Main Tab

Estimate motion between — Estimate motion between images or frames
`Current frame and N-th frame back` (default) | `Two images`

Specify whether to estimate the motion between two images or two video frames. Select Two images to estimate the motion between two images. Select Current frame and N-th frame back to estimate the motion between two video frames that are N frames apart.

Dependencies

Set this parameter to Current frame and N-th frame back to expose the N parameter.

N — Number of frames
`1` (default) | scalar

Specify a scalar value that represents the number of frames between the reference frame and the current frame.

Dependencies

To enable this parameter, set the Estimate motion between parameter to Current frame and N-th frame back.

Search method — Block match search method
`Exhaustive` (default) | `Three-step`

Specify how the block locates the block of pixels in the current frame and the next frame that best matches the block of pixels.

Exhaustive — The block selects the location of the block of pixels in the next frame by moving the block over the search region one pixel at a time. This process is computationally expensive.
Three-step — The block searches for the block of pixels in the next frame that best matches the block of pixels in the current frame by using a steadily decreasing step size. The block begins with a step size approximately equal to half the maximum search range. In each step, the block compares the central point of the search region to eight search points located on the boundaries of the region and moves the central point to the search point whose values is the closest to that of the central point. The block then reduces the step size by half, and begins the process again. This option is less computationally expensive, though it might not find the optimal solution.

Block matching criteria — Block matching criteria
`Mean square error (MSE)` (default) | `Mean absolute difference (MAD)`

Specify how the block measures the similarity of the block of pixels in the current frame to the block of pixels in the next frame.

If you select Mean square error (MSE), the block estimates the displacement of the center pixel of the block as the $(d_{1}, d_{2})$ values that minimize this MSE equation:

$M S E (d_{1}, d_{2}) = \frac{1}{N_{1} \times N_{2}} \sum_{(n_{1}, n_{2}),} \sum_{\in B} {[s (n_{1}, n_{2}, k) - s (n_{1} + d_{1}, n_{2} + d_{2}, k + 1)]}^{2}$

In the previous equation, B is an $N_{1} \times N_{2}$ block of pixels, and s(x,y,k) denotes a pixel location at (x,y) in frame k.

If you select Mean absolute difference (MAD), the Block Matching block estimates the displacement of the center pixel of the block as the $(d_{1}, d_{2})$ values that minimize this MAD equation:

$M A D (d_{1}, d_{2}) = \frac{1}{N_{1} \times N_{2}} \sum_{(n_{1}, n_{2}),} \sum_{\in B} | s (n_{1}, n_{2}, k) - s (n_{1} + d_{1}, n_{2} + d_{2}, k + 1) |$

Block size [height width] — Block size
`[17 17]` (default) | two-element vector

Specify the size of the block of pixels.

Overlap size [r c] — Block overlap
`[0 0]` (default) | two-element vector

Specify the overlap (in pixels) of two subdivisions of the input image.

Maximum displacement [r c] — Maximum displacement
`[7 7]` (default) | two-element vector

Specify the maximum number of pixels any center pixel in a block of pixels might move from image to image or frame to frame. The block uses this value to determine the size of the search region.

Velocity output — Velocity output
`Magnitude-squared` (default) | `Horizontal and vertical components in complex form`

Specify the output. If you select Magnitude-squared, the block outputs an optical flow matrix where each element is in the form u²+v². If you select Horizontal and vertical components in complex form, the block outputs an optical flow matrix where each element is in the form $u + j v$ . The real part of each value is the horizontal velocity component and the imaginary part of each value is the vertical velocity component.

Data Types Tab

For details on the fixed-point block parameters, see Specify Fixed-Point Attributes for Blocks (DSP System Toolbox).

Block Characteristics

Data Types	`double` \| `fixed point` \| `integer` \| `single`
Multidimensional Signals	`no`
Variable-Size Signals	`no`

Algorithms

expand all

Block Matching Search

Suppose the input to the block is frame k. The block performs the following steps:

Subdivide the frame using the values for the Block size [height width] and Overlap size [r c] parameters. For this example, Overlap size [r c] equals [0 0].
For each subdivision or block in frame k+1, a search region is established based on the value of the Maximum displacement [r c] parameter.
Search for the new block location using either the Exhaustive or Three-step search method.

Extended Capabilities

C/C++ Code Generation
Generate C and C++ code using Simulink® Coder™.

Fixed-Point Conversion
Design and simulate fixed-point systems using Fixed-Point Designer™.

Version History

Introduced before R2006a

Block Matching

Description

Examples

Estimate Motion between Two Images

Ports

Input

I/I1 — Image or video frame scalar | vector | matrix

I2 — Image or video frame scalar | vector | matrix

Dependencies

Output

|V|^2 — Velocity magnitudes scalar | vector | matrix

V — Velocity components in complex form scalar | vector | matrix

Dependencies

Parameters

Estimate motion between — Estimate motion between images or frames Current frame and N-th frame back (default) | Two images

Dependencies

N — Number of frames 1 (default) | scalar

Dependencies

Search method — Block match search method Exhaustive (default) | Three-step

Block matching criteria — Block matching criteria Mean square error (MSE) (default) | Mean absolute difference (MAD)

Block size [height width] — Block size [17 17] (default) | two-element vector

Overlap size [r c] — Block overlap [0 0] (default) | two-element vector

Maximum displacement [r c] — Maximum displacement [7 7] (default) | two-element vector

Velocity output — Velocity output Magnitude-squared (default) | Horizontal and vertical components in complex form

Block Characteristics

Algorithms

Block Matching Search

Extended Capabilities

C/C++ Code Generation Generate C and C++ code using Simulink® Coder™.

Fixed-Point Conversion Design and simulate fixed-point systems using Fixed-Point Designer™.

Version History

See Also

I/I1 — Image or video frame
scalar | vector | matrix

I2 — Image or video frame
scalar | vector | matrix

|V|^2 — Velocity magnitudes
scalar | vector | matrix

V — Velocity components in complex form
scalar | vector | matrix

Estimate motion between — Estimate motion between images or frames
`Current frame and N-th frame back` (default) | `Two images`

N — Number of frames
`1` (default) | scalar

Search method — Block match search method
`Exhaustive` (default) | `Three-step`

Block matching criteria — Block matching criteria
`Mean square error (MSE)` (default) | `Mean absolute difference (MAD)`

Block size [height width] — Block size
`[17 17]` (default) | two-element vector

Overlap size [r c] — Block overlap
`[0 0]` (default) | two-element vector

Maximum displacement [r c] — Maximum displacement
`[7 7]` (default) | two-element vector

Velocity output — Velocity output
`Magnitude-squared` (default) | `Horizontal and vertical components in complex form`

C/C++ Code Generation
Generate C and C++ code using Simulink® Coder™.

Fixed-Point Conversion
Design and simulate fixed-point systems using Fixed-Point Designer™.