即時人類動作預測之演算法與架構設計

Abstract

The ultimate goal of computer vision is to help computing devices understand the real world, process visual information efficiently, and even have semantic understandings like humans do. Nowadays, computer vision algorithms progressed rapidly, and developed plenty innovative applications. For example, intelligent environmental surveillances of the future are capable of monitoring real environments, including objects and people. Rather than still images, videos including spatial-temporal information imply richer knowledge. Therefore, human action recognition becomes a basic application that can be implemented in the vision of robots. The fact that different variations in videos increases the difficulty of analysis, leading many researchers to develop better algorithms aiming at raising the recognition accuracy on datasets. However, the computation complexity of feature extraction and template matching in videos is still too complicated to be real-time in past researches. In the thesis, we first introduce several applications of computer vision. Then, we introduce the challenge and background knowledge of the action prediction system. Furthermore, we review the related algorithms and proposed a novel learning scheme for action prediction system. Last, we adapt our prediction system for real-world streaming scenario and explore the hardware-oriented optimization for such system.