Note: This video may require joining the NVIDIA Developer Program or login

GTC Silicon Valley-2019 ID:S9424:Video-Based Activity Forecasting for Construction Safety Monitoring Use Cases

Shuai Tang(University of Illinois at UrbanaChampaign)
We'll talk about applying an LSTM-based trajectory forecasting framework to the problem of construction workers and equipment safety management, a problem with applications to activity forecasting, AEC industries, and AI smart cities. Our talk will provide an overview of construction safety management, construction site visual data collection and pre-processing, and forecasting model architecture. We'll discuss our rationale for designing a final model based on characteristics of construction data, and show experimental results as well as ablation study results. We'll also show a demo or video of our safety-management software.

View the slides (pdf)