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

Table 10

Size of the 3D-EVMs generated for every cluster associated with the traffic control video sequence under a SOM with 15 neurons, removal of the temporal component and unification of RGB components.

Class	Members	EVM size
0	101,659	41,200
1	8,090	1,544
2	75,412	27,546
3	20,303	4,132
4	39,248	19,346
5	100,466	44,756
6	141,671	54,886
7	50,004	26,708
8	32,365	13,120
9	237,961	62,432
10	29,493	8,780
11	25,558	7,496
12	190,047	62,248
13	186,832	52,542
14	65,971	33,238
Total	1,305,080	459,974