duaa1985 Goto Github PK

lidar_for_ad_references

A list of references on lidar point cloud processing for autonomous driving

lidar_projection

3d lidar point cloud 2d image projection in python.

low_rank_forecasting_code

Code for "Low Rank Forecasting" paper.

machine_learning

Evaluation of refractive index is a non-trivial process for anisotropic and dispersive materials. Broadband and polarization-dependent reflectance and/or transmittance data obtained using a single sample is not adequate to solve this non-linear problem. Experiments need to be conducted on multiple samples either with different thicknesses or different substrates. If one tries to solve this numerical problem via a simple search algorithm with a typical personal computer, it probably takes weeks if not months. The aim of this work is accelerating this refractive index determination process via machine learning. To achieve this, first, a training set is created, which includes broadband optical reflectance from 40 different materials with various thicknesses assuming different excitation angles. Materials were chosen from different groups, i.e. metals, semiconductors, and dielectrics. Then, machine learning is used for two different purposes: classification and regression. With classification, the material type is determined so that an appropriate refractive index model can be incorporated, i.e. Lorentz-Drude model for metals, purely real refractive index for lossless dielectrics, and complex but smoothly changing index for the rest. Depending on the material type, either univariate or multivariate linear regression is used to determine the refractive index assuming the material is isotropic. An order of magnitude difference is observed between a typical search algorithm (i.e. fminsearch in Matlab) and developed method. Accuracy of the numerical results promises that machine learning techniques can indeed accelerate various techniques used in electromagnetics, optics, and geophysics.

machinelearning-optics

Machine learning applied to fiber-optic sensors

maskrcnn-benchmark

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

mfnet-pytorch

MFNet-pytorch, image semantic segmentation using RGB-Thermal images

ml-mfr

Machine Learning Techniques for Modulation Format Recognition

mmf-simulator

Basic MMF simulator

modal-dispersion-and-cross-talk-

multimediasignalprocessing

neontreeevaluation

Benchmark dataset for tree detection for airborne RGB, Hyperspectral and LIDAR imagery

neuralscenedecomposition

NSD: Neural Scene Decomposition for Human Motion Capture, CVPR 2019

nk

Refractive index collections for Octave & MATLAB thin film toolbox

nuscenes-devkit

The devkit of the nuScenes dataset.

object-detection-using-lidar

This repo detect objects automatically for LiDAR data

opticalmaterialspy

Python library with optical material properties.

osa-networks-hands-on-ml

Instructions and code used for the Hands-on Introduction to Data Analytics and Machine Learning in Optical Networks to be presented at the OSA Advanced Photonics Congress

photonics2

Notebooks for the Photonics 2 Lectures

plard

Progressive LiDAR Adaptation for Road Detection

posenet-pytorch

Implementation of PoseNet using pytorch

pythonrobotics

Python sample codes for robotics algorithms.

pytorch_segmentation

Semantic segmentation models, datasets and losses implemented in PyTorch.

ref_index

Refractive index of air, and vacuum-air wave length conversion.

refraction-index

refractiveindex

Complex refractive indices of ice, water, soot, or dust as a function of wavelength

refractiveindex.info

My works related to refractiveindex.info database. Database with python scripts allowing

refractiveindex.info-database

Database of optical constants

refractiveindex.info-scripts

Python scripts for refractiveindex.info database

robotics1