Whole image understanding by convolutions on graphs

通过图上的卷积来理解整个图像

• 批准号: DP160103710
• 负责人: Prof Anton van den Hengel
• 金额: $ 21.02万
• 依托单位: The University of Adelaide
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2016
• 资助国家: 澳大利亚
• 起止时间: 2016-01-01 至 2019-06-30
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP160103710
• 关键词: Whole; image; understanding; convolutions; graphs

This project seeks to develop technologies that will help computer vision interpret the whole visible scene, rather than just some of the objects therein. Existing automated methods for understanding images perform well at recognising specific objects in canonical poses, but the problem of whole image interpretation is far more challenging. Convolutional neural networks (CNN) have underpinned recent progress in object recognition, but whole-image understanding cannot be tackled similarly because the number of possible combinations of objects is too large. The project thus proposes a graph-based generalisation of the CNN approach which allows scene structure to be learned explicitly. This would represent an important step towards providing computers with robust vision, allowing them to interact with their environment.

该项目旨在开发技术，帮助计算机视觉解释整个可见场景，而不仅仅是其中的一些对象。现有的理解图像的自动化方法在识别规范姿势的特定对象方面表现良好，但整个图像解释的问题更具挑战性。卷积神经网络（CNN）支持了对象识别的最新进展，但由于对象的可能组合数量太大，因此无法类似地处理整个图像的理解。因此，该项目提出了一种基于图的CNN方法的推广，该方法允许明确地学习场景结构。这将是为计算机提供强大视觉的重要一步，使它们能够与环境进行交互。