Automatic Traffic State Recognition Based on Video Features Extracted by an Autoencoder

Table 1

Design of crossover tests.

Input data dimension	Dimension-reduced data dimension	Number of hidden layers	Model number.
32 × 32	3–6, step length: 1	6–10, step length: 2	1–12
64 × 64	3–6, step length: 1	6–10, step length: 2	13–24
128 × 128	3–6, step length: 1	6–10, step length: 2	25–36