Heterogeneous Gray-Temperature Fusion-Based Deep Learning Architecture for Far Infrared Small Target Detection

Figure 8

Comparison of the detection results according to the normalization method. The same fusion method was used for the two temperature channels from (a)-(e). The image (a) was normalized to a previously calculated mean and standard deviation for a large dataset; (b) was normalized to an arbitrary value of 0.5; and (c) is a value between 0 and 1. In normalization, (d) is normalized to a value between -1 and 0, and (e) is normalized to a value between -1 and 1.

(a)

(b)

(c)

(d)

(e)