Researchers are developing perception algorithms that will learn, model, and track deformable poultry objects for robotic manipulation. The expected result of this work, a multi-year goal, is a system that can learn an object model and track that object in video while it is being manipulated, specifically demonstrated with a chicken breast and bird front half.
The envisioned full system will be capable of learning a new object model, and then use the model for detection and tracking the product throughout manipulation. Basically, the system will perform general object modeling (learning) with skeletal and shape components to identify key features specifically for deformable objects, allowing the tracking of those objects in real-time.
Project Contact: J. Michael Matthews