Learning deep structured active contours end-to-end
arXiv:1803.06329
Abstract
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.
To appear, CVPR 2018
References in corpus (12)
- Deep Residual Learning for Image Recognition
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- Fully Convolutional Networks for Semantic Segmentation
- Fully Connected Deep Structured Networks
- Semantic Instance Segmentation via Deep Metric Learning
- Instance-aware Semantic Segmentation via Multi-task Network Cascades
- Annotating Object Instances with a Polygon-RNN
- Deep Active Contours
- Deep Watershed Transform for Instance Segmentation
- Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs
- TorontoCity: Seeing the World with a Million Eyes
- Structured Prediction Energy Networks