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

Table 9

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

Class	Members	EVM size
0	236,870	44,890
1	60,893	6,106
2	273,111	39,546
3	628,234	60,900
4	105,972	17,420
Total	1,305,080	168,862