Top-Down and Bottom-Up Cues Based Moving Object Detection for Varied Background Video Sequences

Table 5

Comparison of recall of proposed approaches.

Video name	Total Objects	Method 1	Method 2	Method 3	Method 4	Method 5	Method 6	Method 7	GMM [10]	KDE [15]
ATM	698	0.9327	0.7321	0.8553	0.8653	0.7736	0.8926	0.9656	0.6977	0.7206
Cam	4431	0.977	0.9068	0.9278	0.8996	0.8797	0.9429	0.9964	0.8497	0.8693
Campus_raw	1104	0.9909	0.8995	0.9248	0.8659	0.9031	0.9275	0.9508	0.7506	0.7837
EPC-200-day-bird	1100	0.9136	0.9036	0.8845	0.8991	0.8164	0.93	0.9955	0.8016	0.8370
HALLWAY_A	621	0.9758	0.8776	0.8148	0.7552	0.8229	0.9581	0.9973	0.7036	0.7773
highwayI_raw	410	0.9488	0.8	0.7268	0.7439	0.8293	0.9024	0.9887	0.5845	0.6844
person15_walking_d1_uncomp	705	0.9773	0.8539	0.8851	0.8468	0.8667	0.9390	0.9707	0.6976	0.5707
stair	678	0.9499	0.8525	0.8894	0.8732	0.9027	0.9292	0.9574	0.7376	0.7986
visor_1197284015696_07_fumogeno4	1995	0.985	0.9529	0.9514	0.9173	0.9624	0.9754	0.9975	0.8617	0.8802
Overall Recall		0.9612	0.8643	0.8733	0.8518	0.8619	0.9330	0.98	0.7427	0.7691