Table 3 Computational efficiency Comparison.

From: Multi-camera spatiotemporal deep learning framework for real-time abnormal behavior detection in dense urban environments

Method

Inference timestamp (ms/frame)

Overhead Reduction (%)

Proposed Model

9.2

50.2

Method [3]

21.4

0.0

Method [8]

18.9

11.7

Method [25]

15.3

28.5

Back to article page