Toward Robust Pedestrian Detection With Data Augmentation

Toward Robust Pedestrian Detection With Data Augmentation

In this article, the problem of creating a safe pedestrian detection model that can operate in the real world is tackled. While recent advances have led to significantly improved detection accuracy on various benchmarks, existing deep learning models are vulnerable to invisible to the human eye chan...

Full description

Bibliographic Details
Main Authors: Sebastian Cygert, Andrzej Czyzewski
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Convolutional neural network
pedestrian detection
robustness
style-transfer
data augmentation
uncertainty estimation
Online Access:https://ieeexplore.ieee.org/document/9146161/

Internet

https://ieeexplore.ieee.org/document/9146161/

Similar Items