High-Level Interpretation of Urban Road Maps Fusing Deep Learning-Based Pixelwise Scene Segmentation and Digital Navigation Maps

Figure 15

Dynamic obstacles (cyclist and vehicles) are effectively not considered as drivable by the CNN-based road segmentation system. The high-interpretation module maintains the actual structure of the road besides the dynamic obstacles.

(a) Input image

(b) Features detection

(c) CNN road classifier

(d) Map model