Author Affiliations
Laboratory of Nanotechnology and Micro System, Army Engineering University, Shijiazhuang, Hebei 050003, Chinashow less
Fig. 1. Overall block diagram of algorithm
Fig. 2. Color feature extraction of multi-thresholds moving objects. (a) Original image; (b) PC; (c) SC1; (d) SC2; (e) SC3; (f) SC4
Fig. 3. Schematic of color and texture based multi-thresholds combined with motion compensation
Fig. 4. Compensation of color and texture combined foreground objects
Fig. 5. Flow chart of Canny edge detection method combined with Canny thoughts
Fig. 6. Ghost suppression effect in edge detection
Fig. 7. Moving objects detection results obtained by several algorithms under different scenes from CDNet2014 dataset
Fig. 8. P-R curves obtained by different algorithms under six scenes from CDNet2014 dataset. (a) Bus station; (b) badminton; (c) sidewalk; (d) sofa; (e) PETS2006; (f) wet snow
Fig. 9. Fm value in each test dataset for different algorithms
Fig. 10. Foreground and mistakenly detected pixels for the proposed algorithm under different scenes. (a) Bus station; (b) badminton; (c) sidewalk; (d) sofa; (e) PETS2006; (f) wet snow
Fig. 11. Experiment. (a) Experimental devices; (b) results of object detection obtained by each algorithm
Algorithm | fFPR | fFNR | fPWC | Re | Pr | Fm |
---|
DPGMM | 0.007 | 0.336 | 1.944 | 0.664 | 0.741 | 0.686 | LBP | 0.006 | 0.447 | 2.015 | 0.553 | 0.821 | 0.625 | MRF | 0.003 | 0.475 | 2.044 | 0.525 | 0.842 | 0.623 | ViBe | 0.020 | 0.298 | 3.083 | 0.702 | 0.627 | 0.619 | IMBS | 0.003 | 0.341 | 1.431 | 0.659 | 0.878 | 0.730 | Proposed | 0.004 | 0.307 | 1.784 | 0.694 | 0.868 | 0.754 |
|
Table 1. Overall average performance comparison for different algorithms under six scenes from CDNet2014 dataset
Algorithm | DPGMM | LBP | MRF | ViBe | IMBS | Proposed |
---|
Speed /(frame·s-1) | 29.8 | 2.69 | 17.3 | 23.6 | 21.7 | 28.4 |
|
Table 2. Processing speed comparison among different algorithms