Improving Pedestrian Recognition using Incremental Cross Modality Deep Learning

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.
Complete list of metadatas

https://hal.inria.fr/hal-02115319
Contributor : Danut Ovidiu Pop <>
Submitted on : Tuesday, April 30, 2019 - 11:03:50 AM
Last modification on : Friday, May 3, 2019 - 1:16:36 AM

File

ESANN_2019.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02115319, version 1

Citation

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⟩

Share

Metrics

Record views

53

Files downloads

66