Improving Pedestrian Recognition using Incremental Cross Modality Deep Learning - Archive ouverte HAL Access content directly
Conference Papers Year :

Improving Pedestrian Recognition using Incremental Cross Modality Deep Learning

(1, 2, 3) , (2) , (1) , (2)
1
2
3

Abstract

Late fusion schemes with deep learning classification patterns set up with multi-modality images have an essential role in pedestrian protection systems since they have achieved prominent results in the pedestrian recognition task. In this paper, the late fusion scheme merged with Convolutional Neural Networks (CNN) is investigated for pedestrian recognition based on the Daimler stereo vision data sets. An independent CNN-based classifier for each imaging modality (Intensity, Depth, and Optical Flow) is handled before the fusion of its probabilistic output scores with a Multi-Layer Perceptron which provides the recognition decision. In this paper, we set out to prove that the incremental cross-modality deep learning approach enhances pedestrian recognition performances. It also outperforms state-of-the-art pedestrian classifiers on the Daimler stereo-vision data sets.
Fichier principal
Vignette du fichier
ESANN_2019.pdf (251.17 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02115319 , version 1 (30-04-2019)

Identifiers

  • HAL Id : hal-02115319 , version 1

Cite

Danut Ovidiu Pop, Alexandrina Rogozan, Fawzi Nashashibi, Abdelaziz Bensrhair. Improving Pedestrian Recognition using Incremental Cross Modality Deep Learning. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2019, Bruges, Belgium. ⟨hal-02115319⟩
114 View
145 Download

Share

Gmail Facebook Twitter LinkedIn More