Learning a two-stage CNN model for multi-sized building detection in remote sensing images
Learning a two-stage CNN model for multi-sized building detection in remote sensing images
复制标题
DOI：
10.1080/2150704x.2018.1528398
复制
发表时间：
2019-02-01
影响因子：
2.3
通讯作者：
Li, Weihong
中科院分区：
文献类型：
--
作者：
Chen, Chaoyue;Gong, Weiguo;Li, Weihong
尽管在建筑物识别方面取得了巨大进步，但处理多尺寸建筑物是所有建筑物检测管道的基础。我们探讨了检测多尺寸建筑物时出现问题的原因，并发现大多数基于卷积神经网络（CNN）的识别方法都旨在实现尺度不变。识别 3 像素高的建筑物的线索与识别 300 像素高的建筑物的线索根本不同。为了解决这个问题，我们设计了一种新颖的两阶段建筑物检测模型，其中包含区域提议阶段和分类阶段。在区域提案阶段，我们提出了一种新颖的多尺寸融合区域提案网络（MFRPN），用于提取各种尺寸构建的特征并生成宽尺寸范围的区域提案。在分类阶段，使用深度 CNN 模型来区分生成的区域提案是否是构建区域。为了获得更好的性能，我们通过引入动态加权策略提出了一种改进的块投票算法，可以获得更鲁棒的分类结果，提高区域提案的分类精度。我们将此归因于具有挑战性的 VHR 数据集上的稳健实验结果表明我们的模型具有出色的性能。
Though tremendous strides have been made in building recognition, to handle multi-sized buildings is fundamental for all building detection pipelines. We explore the reason of the problem in detecting the multi-sized buildings and find that most convolutional neural network (CNN) based recognition approaches aim to be scale-invariant. The cues for recognizing a 3 pixels tall building are fundamentally different than those for recogjnizing a 300 pixels tall building. To tackle this problem, we design a novel two-stage building detection model which contains the region proposal stage and the classification stage. In the region proposal stage, we propose a novel Multi-size Fusion Region Proposal Network (MFRPN) for extracting the feature of various size building and generating wide size range of region proposals. In the classification stage, a deep CNN model is used to distinguish whether the generated region proposals are building regions or not. In order to achieve better performance, we present an improved block voting algorithm by introducing a dynamic weighting strategy which can obtain a more robust classification result increasing the classification accuracy of the region proposals. We attribute this to robust Experimental results on the challenging VHR dataset indicate that our model has a great performance.