paper-with-me

홈 › Papers

Polarimetric image augmentation

2020-05-22 · Marc Blanchon, Olivier Morel, Fabrice Meriaudeau, Ralph Seulin, Désiré Sidibé

Robotics applications in urban environments are subject to obstacles that exhibit specular reflections hampering autonomous navigation. On the other hand, these reflections are highly polarized and this extra information can successfully be used to segment the specular areas. In nature, polarized light is obtained by reflection or scattering. Deep Convolutional Neural Networks (DCNNs) have shown excellent segmentation results, but require a significant amount of data to achieve best performances. The lack of data is usually overcomed by using augmentation methods. However, unlike RGB images, polarization images are not only scalar (intensity) images and standard augmentation techniques cannot be applied straightforwardly. We propose to enhance deep learning models through a regularized augmentation procedure applied to polarimetric data in order to characterize scenes more effectively under challenging conditions. We subsequently observe an average of 18.1% improvement in IoU between non augmented and regularized training procedures on real world data.

📄 PDF Abstract BibTeX arXiv:2005.11044

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous NavigationImage Augmentation

Similar Papers 제목 키워드 기반

Physically-admissible polarimetric data augmentation for road-scene analysis

2022-06-15 · Cyprien Ruffino, Rachel Blin, Samia Ainouz, Gilles Gasso 외

Polarimetric imaging, along with deep learning, has shown improved performances on different tasks including scene analysis. However, its robustness may be questioned because of the small size of the training datasets. T…

Data Augmentationobject-detectionObject DetectionPedestrian Detection

Isometric Transformations for Image Augmentation in Mueller Matrix Polarimetry

2024-11-12 · Christopher Hahne, Omar Rodriguez-Nunez, Éléa Gros, Théotim Lucas 외

Mueller matrix polarimetry captures essential information about polarized light interactions with a sample, presenting unique challenges for data augmentation in deep learning due to its distinct structure. While augment…

Data AugmentationImage AugmentationSemantic Segmentation

Sparse Ellipsometry: Portable Acquisition of Polarimetric SVBRDF and Shape with Unstructured Flash Photography

2022-07-09 · Inseung Hwang, Daniel S. Jeon, Adolfo Muñoz, Diego Gutierrez 외

Ellipsometry techniques allow to measure polarization information of materials, requiring precise rotations of optical components with different configurations of lights and sensors. This results in cumbersome capture de…

Data AugmentationInverse Rendering

Polarimetric Convolutional Network for PolSAR Image Classification

2018-07-09 · Xu Liu, Licheng Jiao, Xu Tang, Qigong Sun 외

The approaches for analyzing the polarimetric scattering matrix of polarimetric synthetic aperture radar (PolSAR) data have always been the focus of PolSAR image classification. Generally, the polarization coherent matri…

ClassificationGeneral Classificationimage-classificationImage Classification

Fully Polarimetric SAR and Single-Polarization SAR Image Fusion Network

2021-07-18 · Liupeng Lin, Jie Li, Huanfeng Shen, Lingli Zhao 외

The data fusion technology aims to aggregate the characteristics of different data and obtain products with multiple data advantages. To solves the problem of reduced resolution of PolSAR images due to system limitations…