Sat2Graph: Road Graph Extraction Through Graph-Tensor Encoding

He, Songtao; Bastani, Favyen; Jagwani, Satvat; Alizadeh, Mohammad; Balakrishnan, Hari; Chawla, Sanjay; Elshrif, Mohamed M.; Madden, Samuel; Sadeghi, Maryam

doi:10.1007/978-3-030-58586-0_4

Cited by 61 publications

(31 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Directly predicting graphs from images is a challenging task, since graphs may have a variant number of vertices and the relationship between vertices (e.g., edges) is hard to formulate. There are some past works utilizing vector fields to achieve graph prediction [9], [19], [20]. Xue et al [19] aimed to predict line segments of an image.…”

Section: Graph-generation Methodsmentioning

confidence: 99%

“…Similarly, [20] proposed a new vector field to predict the polygon of buildings in satellite images. [9] is believed to be the first work that detects line-shaped objects in BEV images of this category of methods. In this paper, each pixel of the input image was encoded by a 19-length vector.…”

Section: Graph-generation Methodsmentioning

confidence: 99%

“…Like [9], our csBoundary belongs to the graph-generation method and it predicts the road-boundary graph without heuristic post-processing or iterative operations. csBoundary first predicts two probabilistic maps by the feature pyramid network (FPN) [22], including a keypoint map and a road-boundary segmentation map.…”

Section: A the Methods Overviewmentioning

confidence: 99%

“…Not like human pose estimation [23] and road network detection [9] that usually have clearly defined unique keypoints (e.g., joints for human skeleton and crossroad for road network), road boundaries are usually polylines without branches. Therefore, it is hard to find unique keypoints with clear semantic meanings.…”

Section: Fpn and Keypoint Mapmentioning

confidence: 99%

“…Even though this category of methods presents much better topology correctness, they suffer from the error accumulation issue and awful parallelization capability. To conquer the shortcomings of the aforementioned works, [9] first proposes to directly generate the graph of lineshaped objects by using a carefully designed graph encoding scheme.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

csBoundary: City-scale Road-boundary Detection in Aerial Images for High-definition Maps

Xu¹,

Liu²,

Gan³

et al. 2021

Preprint

View full text Add to dashboard Cite

High-Definition (HD) maps can provide precise geometric and semantic information of static traffic environments for autonomous driving. Road-boundary is one of the most important information contained in HD maps since it distinguishes between road areas and off-road areas, which can guide vehicles to drive within road areas. But it is labor-intensive to annotate road boundaries for HD maps at the city scale. To enable automatic HD map annotation, current work uses semantic segmentation or iterative graph growing for road-boundary detection. However, the former could not ensure topological correctness since it works at the pixel level, while the latter suffers from inefficiency and drifting issues. To provide a solution to the aforementioned problems, in this letter, we propose a novel system termed csBoundary to automatically detect road boundaries at the city scale for HD map annotation. Our network takes as input an aerial image patch, and directly infers the continuous road-boundary graph (i.e., vertices and edges) from this image. To generate the city-scale road-boundary graph, we stitch the obtained graphs from all the image patches. Our csBoundary is evaluated and compared on a public benchmark dataset. The results demonstrate our superiority. The accompanied demonstration video is available at our project page https://sites.google.com/view/csboundary/.

show abstract

Section: Graph-generation Methodsmentioning

confidence: 99%

Section: Graph-generation Methodsmentioning

confidence: 99%

Section: A the Methods Overviewmentioning

confidence: 99%

Section: Fpn and Keypoint Mapmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

csBoundary: City-scale Road-boundary Detection in Aerial Images for High-definition Maps

Xu¹,

Liu²,

Gan³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Modelling Satellite Data for Automobile Insurance Risk

Richardson¹,

Shao²,

Khartabil³

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Relationformer: A Unified Framework for Image-to-Graph Generation

Shit

Koner

Wittmann

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A comprehensive representation of an image requires understanding objects and their mutual relationship, especially in image-to-graph generation, e.g., road network extraction, blood-vessel network extraction, or scene graph generation. Traditionally, image-to-graph generation is addressed with a two-stage approach consisting of object detection followed by a separate relation prediction, which prevents simultaneous object-relation interaction. This work proposes a unified onestage transformer-based framework, namely Relationformer that jointly predicts objects and their relations. We leverage direct set-based object prediction and incorporate the interaction among the objects to learn an object-relation representation jointly. In addition to existing [obj]-tokens, we propose a novel learnable token, namely [rln]-token. Together with [obj]-tokens, [rln]-token exploits local and global semantic reasoning in an image through a series of mutual associations. In combination with the pair-wise [obj]-token, the [rln]-token contributes to a computationally efficient relation prediction. We achieve state-of-the-art performance on multiple, diverse and multi-domain datasets that demonstrate our approach's effectiveness and generalizability. 2 * equal contribution 2 code is available at https://github.com/suprosanna/relationformer

show abstract

Sat2Graph: Road Graph Extraction Through Graph-Tensor Encoding

Cited by 61 publications

References 29 publications

csBoundary: City-scale Road-boundary Detection in Aerial Images for High-definition Maps

csBoundary: City-scale Road-boundary Detection in Aerial Images for High-definition Maps

Modelling Satellite Data for Automobile Insurance Risk

Relationformer: A Unified Framework for Image-to-Graph Generation

Contact Info

Product

Resources

About