Automatic Representation and Segmentation of Video Sequences via a Novel Framework Based on the D-EVM and Kohonen Networks

Table 5

Size of the 3D-EVMs generated for every cluster associated with the traffic control video sequence under a SOM with 5 neurons and removal of the temporal component.

Class	Members	EVM size
0	369,462	28,872
1	211,473	34,846
2	707,381	56,644
3	11,028	5,490
4	5,736	1,410
Total	1,305,080	127,262