Lagrangian-Convolutional Networks for Video Classification

用于视频分类的拉格朗日卷积网络

• 批准号: 434160640
• 负责人: Professor Dr.-Ing. Thomas Sikora
• 金额: --
• 依托单位: Fachgebiet Nachrichtenübertragung
• 依托单位国家: 德国
• 项目类别: Research Grants
• 财政年份: 2019
• 资助国家: 德国
• 起止时间: 2018-12-31 至 2021-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/434160640?language=en
• 关键词: Lagrangian; Convolutional; Networks; Video; Classification

The amount of video data has rapidly increased throughout the last decades. This development rises the demand for effective methods to analyse video data beyond a single frame image-based analysis. Specifically the detection quantification and classification of dynamic motion information is a crucial aspect for processing time-dependent video data which yet needs to be fully exploited. With this project we request funding to develop a novel system for analysis and classification of video data based on a Lagrangian methodology. With our preliminary work we highlighted the innovative potential for video processing using such methods in combination with recent machine learning approaches. With this project we like to evolve and substantiate this approach and aim to develop a novel concept for video-level description and classification: the Lagrangian- Convolutional Neural Network (LaCNN). This concept takes advantage of recent in-depth understanding of motion signatures in a video sequence and exploits the capabilities of the Lagrangian methodology and the encoded motion information more effectively. In summary this novel concept will lead to a competitive effective and more transparent video classification system in comparison to existing state of the art methods.

在过去的几十年中，视频数据的数量迅速增加。这种开发增加了对分析视频数据的有效方法的需求，而不是基于单个帧图像的分析。具体来说，动态运动信息的检测量化和分类是处理时间依赖的视频数据的关键方面，但需要充分利用它。在这个项目中，我们要求资金开发出一种新型系统，以分析和基于拉格朗日方法的视频数据分类。通过我们的初步工作，我们强调了使用此类方法与最近的机器学习方法结合使用的视频处理的创新潜力。通过这个项目，我们希望发展并证实这种方法，并旨在为视频级别的描述和分类开发一个新颖的概念：拉格朗日 - 卷积神经网络（LACNN）。该概念利用了视频顺序中对运动特征的最深入了解，并利用拉格朗日方法论的能力和编码的运动信息。总而言之，与现有的最新方法相比，这个新颖的概念将导致有效，更透明的视频分类系统。