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

Figure 5

Results of the high-level interpretation module.

(a) Input image

(b) Sensing result with road in grey, road markings in white, curbs in blue, obstacles in red, and vegetation areas in green

(c) Road model generated from the sensing results and the information from the digital navigation map. Road is painted in grey, lanes are delimited in white, and vegetation and obstacles are painted in green and red, respectively