Audio-visual learning in neural network for elderly surveillance

受子空间分析应用的启发，本项目提出了两组新方法：（1）用于图像分类的浅网络;（2）用于张量表示和分类的子空间。提出了新的表示，以保持空间结构，并保持快速的处理时间。同时给出了一种新的保持时间结构的方法，并在涉及人物检测、动作和手势表示的问题上对这些解决方案进行了评估。我们专注于视觉和声学数据的融合，以支持独居老人的安全生活。

Motivated by applications of subspace analysis, two new groups of methods were presented in this project: (1) Shallow networks for image classification; and (2) Subspaces for tensor representation and classification. New representations are proposed to preserve the spatial structure and maintain a fast processing time. A new method to keep the temporal structure was also given.These solutions were evaluated over problems involving person detection, action, and gesture representation. We focused on the fusion of visual and acoustic data to support the safe life of the elderly living alone.