System and method for tactical behavior recognition

A system for tactical behavior recognition, the system comprising:

• an object module configured to receive image data of general objects associated with a surrounding environment of an ego object and identify a reactive object and an inert object from the surrounding environment based on the image data;
• a graph module configured to generate an ego reactive graph for the reactive object based on a reactive feature of the reactive object and a reactive position vector of the reactive object relative to the general objects, and generate an ego inert graph for the inert object based on an inert feature of the inert object and an inert distance between the inert object and the ego object;
• a fusion module configured to perform interaction modeling based on the ego reactive graphs and the ego inert graphs to generate updated features and performing temporal modeling on the updated features;
• and
• a behavior recognition module configured to determine an egocentric representation of a tactical driver behavior based at least in part on the updated features.

A non-transitory computer readable storage medium storing instructions that when executed by a computer, which includes a processor perform a method, the method comprising:

• receiving image data associated with a surrounding environment of an ego object, wherein the surrounding environment includes general objects;
• identifying a reactive object and an inert object from the general objects based on the image data;
• generating an ego reactive graph for the reactive object based on a reactive feature of the reactive object and a reactive position vector of the reactive object relative to the general objects;
• generating an ego inert graph for the inert object based on an inert feature of the inert object and an inert distance between the inert object and the ego object;
• performing interaction modeling based on the ego reactive graphs and the ego inert graphs to generate updated features;
• performing temporal modeling on the updated features;
• and
• determining an egocentric representation of a tactical driver behavior based at least in part on the updated features.