Learning Deep Structured Active Contours End-to-End

The world is covered with millions of buildings, and precisely knowing each instance's position and extents is vital to a multitude of applications. Recently, automated building footprint segmentation models have shown superior detection accuracy thanks to the usage of Convolutional Neural Netw...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition s. 8877 - 8885
Hlavní autoři: Zhang, Lisa, Bai, Min, Liao, Renjie, Urtasun, Raquel, Marcos, Diego, Tuia, Devis, Kellenberger, Benjamin
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2018
Témata:
Active contours
Buildings
Force
Image segmentation
Inference algorithms
Semantics
Training
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The world is covered with millions of buildings, and precisely knowing each instance's position and extents is vital to a multitude of applications. Recently, automated building footprint segmentation models have shown superior detection accuracy thanks to the usage of Convolutional Neural Networks (CNN). However, even the latest evolutions struggle to precisely delineating borders, which often leads to geometric distortions and inadvertent fusion of adjacent building instances. We propose to overcome this issue by exploiting the distinct geometric properties of buildings. To this end, we present Deep Structured Active Contours (DSAC), a novel framework that integrates priors and constraints into the segmentation process, such as continuous boundaries, smooth edges, and sharp corners. To do so, DSAC employs Active Contour Models (ACM), a family of constraint- and prior-based polygonal models. We learn ACM parameterizations per instance using a CNN, and show how to incorporate all components in a structured output model, making DSAC trainable end-to-end. We evaluate DSAC on three challenging building instance segmentation datasets, where it compares favorably against state-of-the-art. Code will be made available on https://github.com/dmarcosg/DSAC.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00925