Enhanced 3D Point Cloud Reconstruction for Light Field Microscopy Using U-Net-Based Convolutional Neural Networks

This article describes a novel approach for enhancing the three-dimensional(3D)point cloud reconstruction for light field microscopy(LFM)using U-net architecture-based fully convolutional neural network(CNN).Since the directional view of the LFM is limited,noise and artifacts make it difficult to reconstruct the exact shape of 3D point clouds.The existing methods suffer from these problems due to the self-occlusion of the model.This manuscript proposes a deep fusion learning(DL)method that combines a 3D CNN with a U-Net-based model as a feature extractor.The sub-aperture images obtained from the light field microscopy are aligned to form a light field data cube for preprocessing.A multi-stream 3D CNNs and U-net architecture are applied to obtain the depth feature fromthe directional sub-aperture LF data cube.For the enhancement of the depthmap,dual iteration-based weighted median filtering(WMF)is used to reduce surface noise and enhance the accuracy of the reconstruction.Generating a 3D point cloud involves combining two key elements:the enhanced depth map and the central view of the light field image.The proposed method is validated using synthesized Heidelberg Collaboratory for Image Processing(HCI)and real-world LFM datasets.The results are compared with different state-of-the-art methods.The structural similarity index(SSIM)gain for boxes,cotton,pillow,and pens are 0.9760,0.9806,0.9940,and 0.9907,respectively.Moreover,the discrete entropy(DE)value for LFM depth maps exhibited better performance than other existing methods.

A Systematic Approach for Exploring Underground Environment Using LiDAR-Based System

Agricultural projects in different parts of the world depend on underground water wells.Recently,there have been many unfortunate incidents inwhich children have died in abandoned undergroundwells.Providing topographical information for these wells is a prerequisite to protecting people from the dangers of falling into them,especially since most of these wells become buried over time.Many solutions have been developed recently,most with the aimof exploring these well areas.However,these systems suffer fromseveral limitations,including high complexity,large size,or inefficiency.This paper focuses on the development of a smart exploration unit that is able to investigate underground well areas,build a 3D map,search for persons and animals,and determine the levels of oxygen and other gases.The exploration unit has been implemented and validated through several experiments using various experiment testbeds.The results proved the efficiency of the developed exploration unit,in terms of 3D modeling,searching,communication,and measuring the level of oxygen.The average accuracy of the 3D modeling function is approximately 95.5%.A benchmark has been presented for comparing our results with related works,and the comparison has proven the contributions and novelty of the proposed system’s results.