Fast Autofocusing using Tiny Networks for Digital Holographic Microscopy

• URL: http://arxiv.org/abs/2203.07772v1
• Date: Tue, 15 Mar 2022 10:52:58 GMT
• Title: Fast Autofocusing using Tiny Networks for Digital Holographic Microscopy
• Authors: St\'ephane Cuenat, Louis Andr\'eoli, Antoine N. Andr\'e, Patrick Sandoz, Guillaume J. Laurent, Rapha\"el Couturier and Maxime Jacquot
• Abstract summary: A deep learning (DL) solution is proposed to cast the autofocusing as a regression problem and tested over both experimental and simulated holograms. Experiments show that the predicted focusing distance $Z_RmathrmPred$ is accurately inferred with an accuracy of 1.2 $mu$m. Models reach state of the art inference time on CPU, less than 25 ms per inference.
• Score: 0.5057148335041798
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The numerical wavefront backpropagation principle of digital holography confers unique extended focus capabilities, without mechanical displacements along z-axis. However, the determination of the correct focusing distance is a non-trivial and time consuming issue. A deep learning (DL) solution is proposed to cast the autofocusing as a regression problem and tested over both experimental and simulated holograms. Single wavelength digital holograms were recorded by a Digital Holographic Microscope (DHM) with a 10$\mathrm{x}$ microscope objective from a patterned target moving in 3D over an axial range of 92 $\mu$m. Tiny DL models are proposed and compared such as a tiny Vision Transformer (TViT), tiny VGG16 (TVGG) and a tiny Swin-Transfomer (TSwinT). The experiments show that the predicted focusing distance $Z_R^{\mathrm{Pred}}$ is accurately inferred with an accuracy of 1.2 $\mu$m in average in comparison with the DHM depth of field of 15 $\mu$m. Numerical simulations show that all tiny models give the $Z_R^{\mathrm{Pred}}$ with an error below 0.3 $\mu$m. Such a prospect would significantly improve the current capabilities of computer vision position sensing in applications such as 3D microscopy for life sciences or micro-robotics. Moreover, all models reach state of the art inference time on CPU, less than 25 ms per inference.

Related papers

• A Cranial-Feature-Based Registration Scheme for Robotic Micromanipulation Using a Microscopic Stereo Camera System [3.931620400433609]
  The study introduces a microscopic stereo camera system (MSCS) enhanced by the linear model for depth perception. A precise registration scheme is developed for the partially exposed mouse cranial surface, employing a CNN-based constrained and colorized registration strategy. These methods are integrated with the MSCS for robotic micromanipulation tasks.
  arXiv  Detail & Related papers  (2024-10-24T10:40:38Z)
• VFMM3D: Releasing the Potential of Image by Vision Foundation Model for Monocular 3D Object Detection [80.62052650370416]
  monocular 3D object detection holds significant importance across various applications, including autonomous driving and robotics. In this paper, we present VFMM3D, an innovative framework that leverages the capabilities of Vision Foundation Models (VFMs) to accurately transform single-view images into LiDAR point cloud representations.
  arXiv  Detail & Related papers  (2024-04-15T03:12:12Z)
• Sparse Points to Dense Clouds: Enhancing 3D Detection with Limited LiDAR Data [68.18735997052265]
  We propose a balanced approach that combines the advantages of monocular and point cloud-based 3D detection. Our method requires only a small number of 3D points, that can be obtained from a low-cost, low-resolution sensor. The accuracy of 3D detection improves by 20% compared to the state-of-the-art monocular detection methods.
  arXiv  Detail & Related papers  (2024-04-10T03:54:53Z)
• W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibration [57.37135310143126]
  Previous methods for 3D motion recovery from monocular images often fall short due to reliance on camera coordinates. We introduce W-HMR, a weak-supervised calibration method that predicts "reasonable" focal lengths based on body distortion information. We also present the OrientCorrect module, which corrects body orientation for plausible reconstructions in world space.
  arXiv  Detail & Related papers  (2023-11-29T09:02:07Z)
• Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image [85.91935485902708]
  We show that the key to a zero-shot single-view metric depth model lies in the combination of large-scale data training and resolving the metric ambiguity from various camera models. We propose a canonical camera space transformation module, which explicitly addresses the ambiguity problems and can be effortlessly plugged into existing monocular models. Our method enables the accurate recovery of metric 3D structures on randomly collected internet images.
  arXiv  Detail & Related papers  (2023-07-20T16:14:23Z)
• DIME-Net: Neural Network-Based Dynamic Intrinsic Parameter Rectification for Cameras with Optical Image Stabilization System [16.390775530663618]
  We propose a novel neural network-based approach that estimates pose estimation or 3D reconstruction in real-time. We name the proposed Dynamic Intrinsic pose estimation network as DIME-Net and have it implemented and tested on three different mobile devices. In all cases, DIME-Net can reduce reprojection error by at least $64$% indicating that our design is successful.
  arXiv  Detail & Related papers  (2023-03-20T17:45:12Z)
• Monocular 3D Object Detection with Depth from Motion [74.29588921594853]
  We take advantage of camera ego-motion for accurate object depth estimation and detection. Our framework, named Depth from Motion (DfM), then uses the established geometry to lift 2D image features to the 3D space and detects 3D objects thereon. Our framework outperforms state-of-the-art methods by a large margin on the KITTI benchmark.
  arXiv  Detail & Related papers  (2022-07-26T15:48:46Z)
• Newton-PnP: Real-time Visual Navigation for Autonomous Toy-Drones [15.075691719756877]
  Perspective-n-Point problem aims to estimate the relative pose between a calibrated monocular camera and a known 3D model. We suggest an algorithm that runs on weak IoT in real-time but still provides provable guarantees for both running time and correctness. Our main motivation was to turn the popular DJI's Tello Drone into an autonomous drone that navigates in an indoor environment with no external human/laptop/sensor.
  arXiv  Detail & Related papers  (2022-03-05T09:00:50Z)
• Light-field microscopy with correlated beams for extended volumetric imaging at the diffraction limit [0.0]
  We propose and experimentally demonstrate a light-field microscopy architecture based on light intensity correlation. We demonstrate the effectiveness of our technique in refocusing three-dimensional test targets and biological samples out of the focused plane.
  arXiv  Detail & Related papers  (2021-10-02T13:54:11Z)
• Soft Expectation and Deep Maximization for Image Feature Detection [68.8204255655161]
  We propose SEDM, an iterative semi-supervised learning process that flips the question and first looks for repeatable 3D points, then trains a detector to localize them in image space. Our results show that this new model trained using SEDM is able to better localize the underlying 3D points in a scene.
  arXiv  Detail & Related papers  (2021-04-21T00:35:32Z)
• DeepFocus: a Few-Shot Microscope Slide Auto-Focus using a Sample Invariant CNN-based Sharpness Function [6.09170287691728]
  Autofocus (AF) methods are extensively used in biomicroscopy, for example to acquire timelapses. Current hardware-based methods require modifying the microscope and image-based algorithms. We propose DeepFocus, an AF method we implemented as a Micro-Manager plugin.
  arXiv  Detail & Related papers  (2020-01-02T23:29:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.