From Recognition to Prediction: Analysis of Human Action and Trajectory Prediction in Video
This work highlights a critical challenge for autonomous driving, socially-aware robot assistants, and public safety monitoring, where accurate human behavior prediction is essential. It is an incremental step in improving existing prediction systems.
This paper addresses the challenge of predicting human trajectories and actions in video by emphasizing the need for systems to detect and analyze human activities and scene semantics. The authors argue that current systems often lack high-level semantic attributes, which hinders prediction performance across diverse domains and unseen scenarios.
With the advancement in computer vision deep learning, systems now are able to analyze an unprecedented amount of rich visual information from videos to enable applications such as autonomous driving, socially-aware robot assistant and public safety monitoring. Deciphering human behaviors to predict their future paths/trajectories and what they would do from videos is important in these applications. However, human trajectory prediction still remains a challenging task, as scene semantics and human intent are difficult to model. Many systems do not provide high-level semantic attributes to reason about pedestrian future. This design hinders prediction performance in video data from diverse domains and unseen scenarios. To enable optimal future human behavioral forecasting, it is crucial for the system to be able to detect and analyze human activities as well as scene semantics, passing informative features to the subsequent prediction module for context understanding.