Late Fusion in Part-based Person Re-identification
Aske R. Lejbølle, Kamal Nasrollahi, Thomas Baltzer Moeslund · 2017
In person re-identification, the purpose is to match persons across, typically, non-overlapping cameras. This introduces challenges such as occlusion and changes in view and lighting. In order to overcome these challenges, discriminative features are extracted and used in combination with a supervised metric learning algorithm. Most often, feature representations are created from the entire body, causing noisy features if certain parts are occluded. Therefore, we propose a system which applies the same learning algorithm separately on feature representations from different body parts and late fuses the outputs, to take advantage of situations in which features from certain body parts are more discriminative than other.