Robust and Explainable 3D Computer Vision

稳健且可解释的 3D 计算机视觉

• 批准号: FT210100268
• 负责人: Prof Ajmal Mian
• 金额: $ 79.71万
• 依托单位: The University of Western Australia
• 依托单位国家: 澳大利亚
• 项目类别: ARC Future Fellowships
• 财政年份: 2022
• 资助国家: 澳大利亚
• 起止时间: 2022-03-28 至 2026-03-27
• 项目状态: 未结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/FT210100268
• 关键词: Robust; Explainable; 3D; Computer; Vision

Computer vision is increasingly relying on deep learning which is fragile, opaque and fails catastrophically without warning. This project aims to address these problems by developing new theory in graph representation of 3D geometric and image data, hierarchical graph simplification and novel modules designed specifically for deep learning over geometric graphs. Using these modules, it aims to design graph convolutional network architectures for self-supervised learning that are robust to failures and provide explainable decisions for object detection and scene segmentation. The outcomes are expected to advance theory in robust deep learning and benefit 3D mapping, surveying, infrastructure monitoring, transport and robotics industries.

计算机视觉越来越依赖于深度学习，而深度学习是脆弱的、不透明的，并且会在没有警告的情况下发生灾难性的失败。该项目旨在通过开发 3D 几何和图像数据的图表示、层次图简化以及专为几何图深度学习而设计的新颖模块的新理论来解决这些问题。使用这些模块，它的目标是设计用于自监督学习的图卷积网络架构，该架构对故障具有鲁棒性，并为对象检测和场景分割提供可解释的决策。研究结果预计将推进强大的深度学习理论的发展，并使 3D 测绘、测量、基础设施监控、运输和机器人行业受益。