北京大学学报（自然科学版）2019，Vol.55Issue(6)：1067-1077,11.DOI:10.13209/j.0479-8023.2019.106
基于多任务学习的高分辨率遥感影像建筑实例分割
Instance Segmentation of Buildings from High-Resolution Remote Sensing Images with Multitask Learning
摘要
Abstract
At present,building extraction from high-resolution remote sensing images using deep neural network is viewed as a binary classification problem,which divides the pixels into two categories,building and non-building,but it cannot distinguish individual buildings.To solve this problem,the U-Net modified with Xception module and multitask learning are combined to apply to the instance segmentation of buildings,which both acquires the binary classification and distinguishes the individual buildings.Inria aerial imagery is used as the research dataset to validate the algorithm.The results show that the binary classification performance of U-Net modified with Xception outperforms U-Net by about 1.4%.The multitask driven deep neural network not only accomplishes the instance segmentation of buildings,but also improves the accuracy by about 0.5%.关键词
多任务学习/建筑物提取/深度神经网络/实例分割Key words
multitask learning/building extraction/deep neural network/instance segmentation引用本文复制引用
惠健,秦其明,许伟,隋娟..基于多任务学习的高分辨率遥感影像建筑实例分割[J].北京大学学报（自然科学版）,2019,55(6):1067-1077,11.基金项目
国家重点研发计划(2017YFB0503905)资助 （2017YFB0503905）
