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

Table 1

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

Class	EVM size
0	28,968
1	1,528
2	24,674
3	6,308
4	18,650
Total	80,128