Correcting Faulty Road Maps by Image Inpainting

• Published in: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 2710 - 2714
• Main Authors: Hong, Soojung, Choi, Kwanghee
• Format: Conference Proceeding
• Language: English
• Published: IEEE 14-04-2024
• Subjects: Generative Adversarial Networks; Geometry; Image In- painting; Machine learning algorithms; Predictive models; Road Geometry Construction; Roads; Satellite images; Signal processing; Signal processing algorithms
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP48485.2024.10446744

As maintaining road networks is labor-intensive, many au- tomatic road extraction approaches have been introduced to solve this real-world problem, fueled by the abundance of large-scale high-resolution satellite imagery and advances in computer vision. However, their performance is limited for fully automating the road map extraction in real-world ser- vices. Hence, many services employ the two-step human-in- the-loop system to post-process the extracted road maps: er- ror localization and automatic mending for faulty road maps. Our paper exclusively focuses on the latter step, introduc- ing a novel image inpainting approach for fixing road maps with complex road geometries without custom-made heuris- tics, yielding a method that is readily applicable to any road geometry extraction model. We demonstrate the effectiveness of our method on various real-world road geometries, such as straight and curvy roads, T-junctions, and intersections.