Motion estimation is the process of determining the movement of blocks between adjacent video frames. This toolbox includes motion estimation algorithms, such as optical flow, block matching, and template matching. These algorithms create motion vectors, which relate to the whole image, blocks, arbitrary patches, or individual pixels. For block and template matching, the evaluation metrics for finding the best match include MSE, MAD, MaxAD, SAD, and SSD.
|Object for storing optical flow matrices|
|Estimate optical flow using Farneback method|
|Estimate optical flow using Horn-Schunck method|
|Estimate optical flow using Lucas-Kanade method|
|Estimate optical flow using Lucas-Kanade derivative of Gaussian method|
Estimate car motion using the Farneback algorithm.
Estimate car motion using the Lucas-Kanade derivative of Gaussian.
Estimate car motion using the Horn-Schunck method.
Plot the velocity of a moving object in a quiver plot.
This example shows how to use color information to detect and track road edges set in primarily residential settings where lane markings may not be present.
This example shows how to detect and track road lane markers in a video sequence and notifies the driver if they are moving across a lane.
This example shows how to detect and count cars in a video sequence using Gaussian mixture models (GMMs).
This example shows how to detect and track cars in a video sequence using optical flow estimation.