Skip to main content

Advertisement

Table 4 Evaluation with dataset A

From: A hybrid framework combining background subtraction and deep neural networks for rapid person detection

Input size Precision Recall Accuracy
Person Non-person Person Non-person
(a) Full-set
 32 × 32 0.80 0.83 0.82 0.81 0.81
 64 × 64 0.83 0.83 0.81 0.84 0.83
 128 × 128 0.83 0.85 0.85 0.84 0.84
(b) Part-set
 32 × 32 0.82 0.82 0.82 0.81 0.82
 64 × 64 0.87 0.82 0.83 0.86 0.84
 128 × 128 0.86 0.84 0.84 0.86 0.85