Hybrid optimisation for automatic large-scale video annotation

自动大规模视频标注的混合优化

• 批准号: DP130104567
• 负责人: Prof Richard Hartley
• 金额: $ 24.52万
• 依托单位: The Australian National University
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2013
• 资助国家: 澳大利亚
• 起止时间: 2013-01-01 至 2017-12-31
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP130104567
• 关键词: Hybrid; optimisation; automatic; large; scale

Optimization is the basis for solving many problems in Computer Vision, such as three-dimensional geometry recovery, image segmentation, scene labeling and object recognition. This project will develop new optimisation techniques and demonstrate their suitability for large-scale video annotation, which is key to visual data mining and scene understanding.

优化是解决三维几何恢复、图像分割、场景标注、目标识别等计算机视觉问题的基础。该项目将开发新的优化技术，并证明其适用于大规模视频注释，这是视觉数据挖掘和场景理解的关键。