Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · 2018 · 110 citations · 37 references
Artificial IntelligenceEngineeringMachine LearningMachine Learning ToolAi FoundationHumanitarian ApplicationsDisaster DetectionHumanitarian TechnologyRemote-sensing DataRefugee Settlement MappingGeospatial MappingData SciencePattern RecognitionRobot LearningMachine VisionFeature LearningMachine Learning ModelGeographyHumanitarian ReliefComputer ScienceData-centric AiDeep LearningComputer VisionLand Cover MapHumanitarian AidMachine Learning ApproachesRemote SensingCover Mapping
Humanitarian relief coordination is hampered by data scarcity, but remote‑sensing imagery from satellites or drones can provide critical situational awareness, damage assessment, human‑rights monitoring, and population estimates in hard‑to‑reach areas. The authors review machine‑learning methods for automating such remote‑sensing tasks and present a case study applying deep learning to count structures in refugee settlements across Africa and the Middle East. They evaluate deep‑learning models trained on multispectral imagery to detect and count buildings, comparing performance across different sensors and regions. The study shows that while high accuracy is achievable, performance varies with sensor type and region, and that machine‑learning augmentation of human analysts can improve efficiency and quality control despite limited pixel data. This article appears in the discussion‑meeting issue “The growing ubiquity of algorithms in society: implications, impacts and innovations.”.
The coordination of humanitarian relief, e.g. in a natural disaster or a conflict situation, is often complicated by a scarcity of data to inform planning. Remote sensing imagery, from satellites or drones, can give important insights into conditions on the ground, including in areas which are difficult to access. Applications include situation awareness after natural disasters, structural damage assessment in conflict, monitoring human rights violations or population estimation in settlements. We review machine learning approaches for automating these problems, and discuss their potential and limitations. We also provide a case study of experiments using deep learning methods to count the numbers of structures in multiple refugee settlements in Africa and the Middle East. We find that while high levels of accuracy are possible, there is considerable variation in the characteristics of imagery collected from different sensors and regions. In this, as in the other applications discussed in the paper, critical inferences must be made from a relatively small amount of pixel data. We, therefore, consider that using machine learning systems as an augmentation of human analysts is a reasonable strategy to transition from current fully manual operational pipelines to ones which are both more efficient and have the necessary levels of quality control.This article is part of a discussion meeting issue 'The growing ubiquity of algorithms in society: implications, impacts and innovations'.
37
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 214.9K citations · Full text
Image Classification, Deep Neural Networks, Machine Vision +14
Kaiming He, Georgia Gkioxari, Piotr Dollár et al. · 2017 · 27.9K citations
Object Instance Segmentation, Scene Analysis, Machine Vision +13
Kaiming He, Georgia Gkioxari, Piotr Dollár et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2018 · 3.3K citations
Object Instance Segmentation, Convolutional Neural Network, Image Analysis +13