A Human-Trustable Self-Improving Machine Learning Framework for Rapid Disaster Responses Using Satellite Sensor Imagery
人类可信的自我改进机器学习框架,利用卫星传感器图像快速响应灾难
基本信息
- 批准号:EP/X027732/1
- 负责人:
- 金额:$ 34.1万
- 依托单位:
- 依托单位国家:英国
- 项目类别:Research Grant
- 财政年份:2024
- 资助国家:英国
- 起止时间:2024 至 无数据
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
Due to the abrupt changes in Earth's climate and the dramatic global rise of urbanisation, natural disasters have become unpredictable and caused great social and economic devastation in recent years. According to one published study, between 2015-2019, there were a total of 1624 reported natural disasters, such as earthquakes, floods, landslides, etc., killing on average 60,000 people each year globally. Although humans cannot prevent natural disasters in most cases, timely responses can play a critical role in disaster relief and life-saving. Rapid and accurate building damage assessment (BDA) is required in humanitarian assistance and disaster response to carry out life-saving efforts. However, current BDAs are mostly based on manual inspection and documentation, which is time consuming and labour-intensive. Although high-resolution satellite sensor images (HRSSIs) such as GeoEye-1, WorldView-2 and 3, have become the major source of first-hand information for BDA, those images often present a mosaic of complex geometrical structures and spatial patterns. Automatic information extraction from HRSSIs of disaster-affected areas is imperative under time-critical situations, and has the potential to facilitate post-disaster assessment, speed up the life-saving rescue processes. However, this remains an extremely challenging task for the state-of-the-art machine learning (ML) algorithms. In practice, human experts have to manually interpret and examine the captured HRSSIs, which involves significant time and labour.Conventional ML-based BDA methods leverage mainstream classifiers, such as support vector machine, random forest, to generate a damage map based on hand-crafted features extracted from pre- and post- disaster images. However, the complexity and heterogeneity of HRSSIs hinder the applicability of conventional methods, making feature extraction extremely difficult. Besides, buildings often involve only a few pixels, leaving minimal structural information to exploit. Although conventional methods do not require a large volume of training images and are more interpretable, they fail easily on real scenes. On the other hand, deep learning techniques, particularly, deep convolutional neural networks (DCNNs) have reported significant achievements in the field of computer vision and pattern recognition. Some recent studies have explored the capability of DCNNs on BDA and reported promising outcomes under experimental conditions. DCNN-based methods have become increasingly popular and are currently the state-of-the-art in BDA research. However, DCNNs are often characterised as black boxes, and are computationally intensive and data-hungry. As the underlying mechanisms are different from humans and not understandable, DCNNs can fail easily in unfamiliar scenarios due to uncertainties and are often observed to exhibit unexpected behaviours. These disadvantages hinder the practical utilities of DCNN-based BDA methods in real-world scenarios. As a result, emergency management services (EMSs), e.g., the International Charter Space and Major Disasters, still rely on visual interpretation of HRSSIs to assess building damage due to the reliability. To make ML-based BDA methods reliable for real-world scenarios, this project aims to catalyse a step-change in artificial intelligence by developing highly innovative explainable ML (XML) techniques to automate the BDA processes based on post-disaster HRSSIs. The developed XML techniques will act as a framework for scene understanding, building segmentation and damage assessment on both scene-level and pixel-level in a joint fashion, and have the capacity to self-adapt to different application scenarios in real-time to address real-world uncertainties. By achieving a reliable automated solution to facilitate the highly challenging post-disaster BDA task, we ultimately aim to assist EMSs for faster post-disaster assessment, facilitating life-saving process.
近年来,由于地球气候的突然变化和全球城市化的急剧上升,自然灾害变得不可预测,并造成了巨大的社会和经济破坏。根据一项已发表的研究,在2015-2019年期间,共有1624起自然灾害报告,如地震,洪水,山体滑坡等,全球每年平均有6万人死于此虽然人类在大多数情况下无法预防自然灾害,但及时应对可以在救灾和拯救生命方面发挥关键作用。在人道主义援助和灾害响应中,需要快速准确的建筑物损坏评估(BDA),以开展救生工作。然而,当前的BDA大多基于手动检查和记录,既耗时又劳动密集型。虽然GeoEye-1、WorldView-2和3等高分辨率卫星传感器图像已成为BDA第一手信息的主要来源,但这些图像往往呈现出复杂的几何结构和空间模式的马赛克。在时间紧迫的情况下,从受灾地区的HRSSI中自动提取信息势在必行,并且有可能促进灾后评估,加快救生救援过程。然而,对于最先进的机器学习(ML)算法来说,这仍然是一项极具挑战性的任务。传统的基于ML的BDA方法利用主流分类器(例如支持向量机、随机森林)来基于从灾前和灾后图像中提取的手工特征生成损害图。然而,HRSSI的复杂性和异质性阻碍了传统方法的适用性,使得特征提取非常困难。此外,建筑物通常只涉及几个像素,留下最少的结构信息可供利用。虽然传统的方法不需要大量的训练图像并且更易于解释,但是它们在真实的场景中容易失败。另一方面,深度学习技术,特别是深度卷积神经网络(DCNN)在计算机视觉和模式识别领域取得了重大成就。最近的一些研究探索了DCNN对BDA的能力,并在实验条件下报告了有希望的结果。基于DCNN的方法越来越受欢迎,是目前BDA研究的最新技术。然而,DCNN通常被描述为黑箱,并且是计算密集型和数据饥渴型的。由于其基本机制与人类不同且不可理解,DCNN在不熟悉的场景中很容易因不确定性而失败,并且经常被观察到表现出意想不到的行为。这些缺点阻碍了基于DCNN的BDA方法在现实世界场景中的实际效用。因此,紧急管理服务(EMS),例如,国际空间和重大灾害宪章,仍然依赖于视觉解释的HRSSI评估建筑物的损害,由于可靠性。为了使基于ML的BDA方法在现实世界中变得可靠,该项目旨在通过开发高度创新的可解释ML(XML)技术来促进人工智能的逐步变化,以基于灾后HRSSI自动化BDA流程。所开发的XML技术将作为一个框架,场景理解,建筑物分割和损坏评估的场景级和像素级的联合方式,并有能力自适应不同的应用场景中实时解决现实世界的不确定性。通过实现可靠的自动化解决方案,以促进极具挑战性的灾后BDA任务,我们的最终目标是帮助EMS更快地进行灾后评估,促进救生过程。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Xiaowei GU其他文献
Xiaowei GU的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
相似海外基金
Trustable AI generated Mapping (TAIM)
可信人工智能生成地图 (TAIM)
- 批准号:
10064920 - 财政年份:2023
- 资助金额:
$ 34.1万 - 项目类别:
Collaborative R&D
Hybrid Intelligence for Trustable Diagnosis And Patient Management of Prostate Cancer (HIT-PIRADS)
用于前列腺癌可信诊断和患者管理的混合智能 (HIT-PIRADS)
- 批准号:
10611212 - 财政年份:2023
- 资助金额:
$ 34.1万 - 项目类别:
Fast, Accurate, Compact, Trustable, low Cost and Power (FACTCoP) sub-THz/THz Dielectric Sensor for Ubiquitous Access
快速、准确、紧凑、可靠、低成本和低功耗 (FACTCoP) 亚太赫兹/太赫兹介电传感器,实现无处不在的接入
- 批准号:
2241337 - 财政年份:2023
- 资助金额:
$ 34.1万 - 项目类别:
Standard Grant
Trustable public transit through integrated multimodal transit networks and trip planning
通过综合多式联运网络和行程规划实现值得信赖的公共交通
- 批准号:
2601315 - 财政年份:2021
- 资助金额:
$ 34.1万 - 项目类别:
Studentship
REU Site: Trustable Embedded Systems Security Research
REU 网站:可信嵌入式系统安全研究
- 批准号:
1950600 - 财政年份:2020
- 资助金额:
$ 34.1万 - 项目类别:
Standard Grant
Building structured Knowledge Base for trustable NLP application systems by Resource by Collaborative Construction scheme
通过资源协同构建方案为可信赖的NLP应用系统构建结构化知识库
- 批准号:
20H00617 - 财政年份:2020
- 资助金额:
$ 34.1万 - 项目类别:
Grant-in-Aid for Scientific Research (A)
Trustable dexterous manipulation: morphologies and low-level control schemes for next-generation robot hand technologies
值得信赖的灵巧操作:下一代机器人手技术的形态和低级控制方案
- 批准号:
EP/R020833/1 - 财政年份:2018
- 资助金额:
$ 34.1万 - 项目类别:
Research Grant
REU Site: Trustable Embedded Systems Security Research
REU 网站:可信嵌入式系统安全研究
- 批准号:
1659764 - 财政年份:2017
- 资助金额:
$ 34.1万 - 项目类别:
Standard Grant
REU Site: Trustable Computing Systems Security Research
REU 站点:可信计算系统安全研究
- 批准号:
1359329 - 财政年份:2014
- 资助金额:
$ 34.1万 - 项目类别:
Standard Grant
REU Site: Trustable Computing Systems Security Research and Education
REU 站点:可信计算系统安全研究和教育
- 批准号:
1062962 - 财政年份:2011
- 资助金额:
$ 34.1万 - 项目类别:
Continuing Grant