Fusion of Stereo Vision for Pedestrian Recognition using Convolutional Neural Networks

Abstract : Pedestrian detection is a highly debated issue in the scientific community due to its outstanding importance for a large number of applications, especially in the fields of automotive safety, robotics and surveillance. In spite of the widely varying methods developed in recent years, pedestrian detection is still an open challenge whose accuracy and robustness has to be improved. Therefore, in this paper, we focus on improving the classification component in the pedestrian detection task on the Daimler stereo vision data set by adopting two approaches: 1) by combining three image modalities (intensity, depth and flow) to feed a unique convolutional neural network (CNN) and 2) by fusing the results of three independent CNNs.
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-01501735
Contributor : Danut Ovidiu Pop <>
Submitted on : Tuesday, April 4, 2017 - 3:38:18 PM
Last modification on : Thursday, February 7, 2019 - 5:38:08 PM
Long-term archiving on : Wednesday, July 5, 2017 - 6:01:16 PM

File

ESANN.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01501735, version 1

Citation

Danut Ovidiu Pop, Alexandrina Rogozan, Fawzi Nashashibi, Abdelaziz Bensrhair. Fusion of Stereo Vision for Pedestrian Recognition using Convolutional Neural Networks. ESANN 2017 - 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2017, Bruges, Belgium. ⟨hal-01501735⟩

Share

Metrics

Record views

772

Files downloads

23247