PROJECT TITLE :
Context-aware part-based people detection for video monitoring
A novel approach for part-based mostly folks detection in pictures that uses contextual information is proposed. 2 sources of context are distinguished regarding the local (neighbour) info and also the relative importance of the parts in the model. Native context determines part visibility which comes from the spatial location of static objects in the scene and from the relation between scales of research and detection window sizes. Experimental results over various datasets show that the proposed use of context outperforms the related state-of-the-art.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here