Skip to main content

Advertisement

Table 5 Complexity and memory usage of our approach and a state-of-the-art object detection method (YOLO)

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

  Our CNN model YOLO
Input size \(64\times 64\) \(224 \times 224\)
# of conv. layers 2 24
# of parameters 209 K 66,000 K
Memory usage per image 1690 KB 53,606 KB