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

Table 2

Size of the 3D-EVMs generated for every cluster associated with the traffic control video sequence under a SOM with 15 neurons.

Class	EVM size
0	176
1	38,826
2	8,560
3	15,116
4	3,070
5	23,346
6	1,408
7	8,352
8	33,272
9	45,096
10	496
11	0
12	0
13	4,796
14	23,626
Total	206,140