An algorithm was developed for the segmentation and tracking of piglet
s and tested on a 200-image sequence of 10 piglets moving on a straw b
ackground. The image-capture rate was 1 image/140ms. The segmentation
method was a combination of image differencing with respect to a media
n background and a Laplacian operator. The features tracked were blob
edges in the segmented image. During tracking, the piglets were modell
ed as ellipses initialised on the blobs. Each piglet was tracked by se
arching for blob edges in an elliptical window about the piglet's posi
tion, which was predicted from its previous two positions.