分割
计算机科学
稳健性(进化)
边界(拓扑)
推论
深度学习
土地覆盖
遥感
图像分割
功能(生物学)
人工智能
边界对象
土地利用
数据挖掘
地图学
地理
土木工程
数学
工程类
数学分析
生物化学
化学
进化生物学
生物
基因
比例(比率)
作者
Jin Wang,Ning Ding,Guangjun He
标识
DOI:10.1080/01431161.2023.2224101
摘要
ABSTRACTWith the rapid development of UAV remote sensing, satellite remote sensing and computer vision, the semantic segmentation of remote sensing images has also developed rapidly and is widely used in research on land utilization classification, ecology, urban planning and other problems. Large differences in spatial and temporal scales, different image resolutions, insufficient model robustness to the data domain, and blurred object boundaries are the main problems for existing semantic segmentation models based on deep learning. This paper studies the problem of blurred target boundaries after semantic segmentation and propose a boundary enhancement loss function that highlights the importance of target edges. Compared to other models used in investigating higher boundary accuracy, the proposed model can be trained without boundary-labelled data, and no additional inference time is consumed. This loss function is applied to some other deep learning networks as a plug-and-play module on two different datasets and show that the IoU has an improvement of 2–5% with better clear boundary and continuity, which is more prominent on buildings and roads.KEYWORDS: Semantic segmentationboundary enhancement lossland utilization Additional informationFundingThis work was supported by the National Natural Science Foundation of China under (Grant No.41801291), Changzhou Municipal Science and Technology Bureau, China (Grant No. CE20205048) and scientific research foundation of Changzhou University (Grant No. ZMF21020364).
科研通智能强力驱动
Strongly Powered by AbleSci AI