PROJECT TITLE :
Robust Rooftop Extraction From Visible Band Images Using Higher Order CRF
During this paper, we tend to propose a strong framework for building extraction in visible band pictures. We tend to initial get an initial classification of the pixels based mostly on an unsupervised presegmentation. Then, we have a tendency to develop a unique conditional random field (CRF) formulation to attain correct rooftops extraction, that incorporates pixel-level information and section-level data for the identification of rooftops. Comparing with the commonly used CRF model, the next order potential outlined on segment is added in our model, by exploiting region consistency and shape feature at segment level. Our experiments show that the proposed higher order CRF model outperforms the state-of-the-art strategies each at pixel and object levels on rooftops with complex structures and sizes in challenging environments.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here