Applications of Mueller polarimetry in the Fourier space for overlay characterization in microelectronics

Fallet, Clément; Manhas, Sandeep; Martino, A. De; Novikova, Tatiana

doi:10.1117/12.862976

Cited by 2 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For remote sensing, polarization has been shown to be useful for improving the contrast between polarized targets and background clutter, 1 improving robustness to poor visibility conditions in road scenes, 2,3 and surface defect characterization. [4][5][6] Conventional EO/IR techniques measure the intensity of reflected optical radiation over some wavelength, while polarimetric imaging techniques, instead, measure the polarization state of reflected optical radiation in a scene.…”

Section: Introductionmentioning

confidence: 99%

Deep learning approach to vehicle pose estimation from polarimetric image data

Siefring,

Ratliff,

Ballard

2023

Polarization Science and Remote Sensing XI

View full text Add to dashboard Cite

Object pose estimation is an important problem in the field of remote sensing that provides valuable information for target identification tasks. Polarization is a fundamental property of light that contains useful information about the physical properties of an object, such as shape and surface material properties. Polarization imaging has been shown to have advantages over conventional imaging techniques for object detection and feature extraction in a variety of challenging scenarios, including low light, high background clutter, and low visibility conditions. In this work, we investigate using polarimetric imaging to improve the performance of deep learning approaches to object pose estimation on a range of model target vehicles. We collect polarimetric imaging data and labeled ground truth pose data on the target vehicles in a controlled solar simulation laboratory environment under precise sensor, object, and solar source geometries. We first establish baseline performance of our approach by training our network using conventional visible RGB s0 images under favorable lighting conditions. We then make use of the full linear Stokes images for each color channel in various configurations, retrain our network, and compare performance. We furthermore propose an ensemble method to combine features obtained from convolutional neural networks trained on both conventional RGB and Stokes-vector images. These obtained ensemble features are then used to train a multi-layer perceptron. Experimental results demonstrate that combining polarization imaging with conventional imaging can improve feature extraction and the accuracy of deep learning-based approaches to pose estimation.

show abstract