An Improved Deep Residual Network-Based Semantic Simultaneous Localization and Mapping Method for Monocular Vision Robot

Figure 12

The image matching results between a complete scene image and a part of the same scene image based on (a) SIFT, (b) SURF, (c) G-ORB, and (d) I-ORB.

(a)

(b)

(c)

(d)