Correcting Faulty Road Maps by Image Inpainting (2211.06544v3)
Abstract: As maintaining road networks is labor-intensive, many automatic 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 services. Hence, many services employ the two-step human-in-the-loop system to post-process the extracted road maps: error localization and automatic mending for faulty road maps. Our paper exclusively focuses on the latter step, introducing a novel image inpainting approach for fixing road maps with complex road geometries without custom-made heuristics, 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.
- G. Miller, “The huge, unseen operation behind the accuracy of google maps,” Wired, 2014.
- “Road recognition from remote sensing imagery using incremental learning,” IEEE trans. Intell. Transp. Syst., vol. 18, no. 11, pp. 2993–3005, 2017.
- “Survey of road extraction methods in remote sensing images based on deep learning,” PFG-J. Photogramm. Rem., vol. 90, no. 2, pp. 135–159, 2022.
- “A review on deep learning techniques applied to semantic segmentation,” arXiv preprint arXiv:1704.06857, 2017.
- “Improving road surface area extraction via semantic segmentation with conditional generative learning for deep inpainting operations,” ISPRS Int. J. Geo-Inf., vol. 11, no. 1, 2022.
- “A comparison and evaluation of map construction algorithms using vehicle tracking data,” GeoInformatica, 2015.
- “Extraction of road intersections from gps traces based on the dominant orientations of roads,” ISPRS International Journal of Geo-Information, vol. 6, no. 12, 2017.
- C. Sujatha and D. Selvathi, “Connected component-based technique for automatic extraction of road centerline in high resolution satellite images,” EURASIP JVIP, pp. 1–16, 2015.
- “A new approach to urban road extraction using high-resolution aerial image,” ISPRS Int. J. Geo-Inf., vol. 5, pp. 114, 2016.
- “Semi automatic road extraction from digital images,” The Egyptian Journal of Remote Sensing and Space Science, vol. 20, 03 2017.
- “Robust road detection from a single image using road shape prior,” in ICIP, 2013.
- “Deep learning approaches applied to remote sensing datasets for road extraction: A state-of-the-art review,” Remote Sensing, vol. 12, pp. 1444, 2020.
- V. Mnih and G. E. Hinton, “Learning to detect roads in high-resolution aerial images,” in ECCV, 2010.
- “Towards automatic extraction and updating of vgi-based road networks using deep learning,” Remote Sensing, vol. 11, no. 9, pp. 1012, 2019.
- S. Alamri, “Independent map enhancement for a spatial road network: Fundamental applications and opportunities,” ISPRS Int. J. Geo-Inf., vol. 10, no. 1, 2021.
- “Multiscale road centerlines extraction from high-resolution aerial imagery,” Neurocomputing, vol. 329, pp. 384–396, 2019.
- “Globally and locally consistent image completion,” ACM Trans. Graph., vol. 36, no. 4, pp. 107:1–107:14, 2017.
- “Free-form image inpainting with gated convolution,” in ICCV, 2019.
- “Repaint: Inpainting using denoising diffusion probabilistic models,” in CVPR, 2022.
- “Denoising diffusion probabilistic models,” in NeurIPS, 2020.
- “Deep learning face attributes in the wild.,” ICCV, 2015.
- “Perceptual losses for real-time style transfer and super-resolution,” in ECCV, 2016.
- “Deblurgan-v2: Deblurring (orders-of-magnitude) faster and better,” in ICCV, 2019.
- “Soup-gan: Super-resolution mri using generative adversarial networks,” MDPI Tomography, vol. 8, no. 2, pp. 905–919, 2022.
- V. Mnih, Machine Learning for Aerial Image Labeling, Ph.D. thesis, U. of Toronto, 2013.
- “Automatic intersection extraction method for urban road networks based on trajectory intersection points,” Applied Sciences, vol. 12, no. 12, 2022.
- “A model-driven-to-sample-driven method for rural road extraction,” Remote Sensing, vol. 13, no. 8, 2021.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.