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

Table 12

Size of the 3D-EVMs generated for every cluster associated with the Billiard Game Video Sequence under a SOM with 15 neurons, removal of the temporal component and unification of RGB components.

Class	Members	EVM size
0	206,717	8,288
1	44,117	6,288
2	11,638	4,048
3	8,596	2,282
4	47,503	10,082
5	47,525	11,804
6	332,658	58,154
7	381,654	39,536
8	46,984	11,182
9	53,709	8,540
10	116,704	19,198
11	41,066	11,092
12	60,888	13,880
13	249,839	46,318
14	155,394	30,236
Total	1,804,992	280,928