Section: New Results

Recognizing Pedestrians using Cross-Modal Convolutional Networks

Participants : Danut-Ovidiu Pop, Fawzi Nashashibi.

This year, we have continued our research, which is based on multi-modal image fusion schemes with deep learning classification methods. We propose four different learning patterns based on Cross-Modality deep learning of Convolutional Neural Networks:

(1) a Particular Cross-Modality Learning;

(2) a Separate Cross-Modality Learning;

(3) a Correlated Cross-Modality Learning and

(4) an Incremental CrossModality Learning model.

Moreover, we also design a new variation of a Lenet architecture, which improves the classification performance. Finally, we propose to learn this model with the incremental cross-modality approach using optimal learning settings, obtained with a K-fold Cross Validation pattern. This method outperforms the state-of-the-art classifier provided with Daimler datasets on both non-occluded and partially-occluded pedestrian tasks.