Promoting Connectivity of Network-Like Structures by Enforcing Region Separation
Promoting Connectivity of Network-Like Structures by Enforcing Region Separation
复制标题
DOI：
10.1109/tpami.2021.3074366
复制
发表时间：
2020-09
影响因子：
23.6
通讯作者：
Doruk Öner;M. Koziński;Leonardo Citraro;N. Dadap;A. Konings;P. Fua
中科院分区：
文献类型：
--
作者：
Doruk Öner;M. Koziński;Leonardo Citraro;N. Dadap;A. Konings;P. Fua
我们提出了一种新颖的、面向连接的损失函数，用于训练深度卷积网络，以从航空图像中重建类似网络的结构，如道路和灌溉渠。我们的损失背后的主要想法是表达道路或运河的连通性，通过它们在图像背景区域之间创建的断开。简单地说，预测道路上的一个缺口会导致两个背景区域在预测中接触，这两个背景区域位于基础真理道路的两侧。我们的损失函数旨在防止背景区域之间的不必要连接，从而缩小预测道路的差距。它还可以通过惩罚背景区域的不必要的断开来防止预测误报的道路和运河。为了捕捉更短的、没有尽头的路段，我们评估了小图像作物的损失。在两个标准道路基准和一个新的灌溉渠数据集的实验中，我们表明，用我们的损失函数训练的卷积神经网络可以很好地恢复道路连接，以至于足以概括它们的输出以生成最先进的地图。我们的方法的一个明显的优势是，损失可以插入到任何现有的训练设置，而无需进一步修改。
We propose a novel, connectivity-oriented loss function for training deep convolutional networks to reconstruct network-like structures, like roads and irrigation canals, from aerial images. The main idea behind our loss is to express the connectivity of roads, or canals, in terms of disconnections that they create between background regions of the image. In simple terms, a gap in the predicted road causes two background regions, that lie on the opposite sides of a ground truth road, to touch in prediction. Our loss function is designed to prevent such unwanted connections between background regions, and therefore close the gaps in predicted roads. It also prevents predicting false positive roads and canals by penalizing unwarranted disconnections of background regions. In order to capture even short, dead-ending road segments, we evaluate the loss in small image crops. We show, in experiments on two standard road benchmarks and a new data set of irrigation canals, that convnets trained with our loss function recover road connectivity so well that it suffices to skeletonize their output to produce state of the art maps. A distinct advantage of our approach is that the loss can be plugged in to any existing training setup without further modifications.