Application of Ghost-DeblurGAN to Fiducial Marker Detection

• URL: http://arxiv.org/abs/2109.03379v3
• Date: Mon, 14 Feb 2022 03:24:40 GMT
• Title: Application of Ghost-DeblurGAN to Fiducial Marker Detection
• Authors: Yibo Liu, Amaldev Haridevan, Hunter Schofield, Jinjun Shan
• Abstract summary: This paper develops a lightweight generative adversarial network, named Ghost-DeGAN, for real-time motion deblurring. A new large-scale dataset, YorkTag, is proposed that provides pairs of sharp/blurred images containing fiducial markers. With the proposed model trained and tested on YorkTag, it is demonstrated that when applied along with fiducial marker systems to motion-blurred images, Ghost-DeblurGAN improves the marker detection significantly.
• Score: 1.1470070927586016
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Feature extraction or localization based on the fiducial marker could fail due to motion blur in real-world robotic applications. To solve this problem, a lightweight generative adversarial network, named Ghost-DeblurGAN, for real-time motion deblurring is developed in this paper. Furthermore, on account that there is no existing deblurring benchmark for such task, a new large-scale dataset, YorkTag, is proposed that provides pairs of sharp/blurred images containing fiducial markers. With the proposed model trained and tested on YorkTag, it is demonstrated that when applied along with fiducial marker systems to motion-blurred images, Ghost-DeblurGAN improves the marker detection significantly. The datasets and codes used in this paper are available at: https://github.com/York-SDCNLab/Ghost-DeblurGAN.

Related papers

• YoloTag: Vision-based Robust UAV Navigation with Fiducial Markers [2.7855886538423182]
  We propose YoloTag, a real-time fiducial marker-based localization system. YoloTag uses a lightweight YOLO v8 object detector to accurately detect fiducial markers in images. The detected markers are then used by an efficient perspective-n-point algorithm to estimate UAV states.
  arXiv  Detail & Related papers  (2024-09-03T23:42:19Z)
• LABELMAKER: Automatic Semantic Label Generation from RGB-D Trajectories [59.14011485494713]
  This work introduces a fully automated 2D/3D labeling framework that can generate labels for RGB-D scans at equal (or better) level of accuracy. We demonstrate the effectiveness of our LabelMaker pipeline by generating significantly better labels for the ScanNet datasets and automatically labelling the previously unlabeled ARKitScenes dataset.
  arXiv  Detail & Related papers  (2023-11-20T20:40:24Z)
• A Locality-based Neural Solver for Optical Motion Capture [37.28597049192196]
  Given noisy marker data, we propose a new heterogeneous graph neural network which treats markers and joints as different types of nodes. We show that our method outperforms state-of-the-art methods in terms of prediction accuracy of occluded marker position error.
  arXiv  Detail & Related papers  (2023-09-01T12:40:17Z)
• An Unforgeable Publicly Verifiable Watermark for Large Language Models [84.2805275589553]
  Current watermark detection algorithms require the secret key used in the watermark generation process, making them susceptible to security breaches and counterfeiting during public detection. We propose an unforgeable publicly verifiable watermark algorithm named UPV that uses two different neural networks for watermark generation and detection, instead of using the same key at both stages.
  arXiv  Detail & Related papers  (2023-07-30T13:43:27Z)
• Omni-DETR: Omni-Supervised Object Detection with Transformers [165.4190908259015]
  We consider the problem of omni-supervised object detection, which can use unlabeled, fully labeled and weakly labeled annotations. Under this unified architecture, different types of weak labels can be leveraged to generate accurate pseudo labels. We have found that weak annotations can help to improve detection performance and a mixture of them can achieve a better trade-off between annotation cost and accuracy.
  arXiv  Detail & Related papers  (2022-03-30T06:36:09Z)
• E2ETag: An End-to-End Trainable Method for Generating and Detecting Fiducial Markers [0.8602553195689513]
  E2ETag is an end-to-end trainable method for designing fiducial markers and a complimentary detector. It learns to generate markers that can be detected and classified in challenging real-world environments using a fully convolutional detector network. Results demonstrate that E2ETag outperforms existing methods in ideal conditions.
  arXiv  Detail & Related papers  (2021-05-29T03:13:14Z)
• DeepTag: A General Framework for Fiducial Marker Design and Detection [1.2180122937388957]
  We propose a general deep learning based framework, DeepTag, for fiducial marker design and detection. DeepTag supports detection of a wide variety of existing marker families and makes it possible to design new marker families with customized local patterns. Experiments show that DeepTag well supports different marker families and greatly outperforms the existing methods in terms of both detection robustness and pose accuracy.
  arXiv  Detail & Related papers  (2021-05-28T10:54:59Z)
• Video-based Person Re-identification without Bells and Whistles [49.51670583977911]
  Video-based person re-identification (Re-ID) aims at matching the video tracklets with cropped video frames for identifying the pedestrians under different cameras. There exists severe spatial and temporal misalignment for those cropped tracklets due to the imperfect detection and tracking results generated with obsolete methods. We present a simple re-Detect and Link (DL) module which can effectively reduce those unexpected noise through applying the deep learning-based detection and tracking on the cropped tracklets.
  arXiv  Detail & Related papers  (2021-05-22T10:17:38Z)
• Detection of Binary Square Fiducial Markers Using an Event Camera [1.0781866671930855]
  Event cameras are a new type of image sensors that output changes in light intensity (events) instead of absolute intensity values. We propose a method to detect and decode binary square markers using an event camera.
  arXiv  Detail & Related papers  (2020-12-11T17:34:47Z)
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection [69.75559390700887]
  This paper explores a relatively less-studied methodology based on classification. We propose new techniques to push its frontier in two aspects. Experiments and visual analysis on large-scale public datasets for aerial images show the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-11-19T05:42:02Z)
• EHSOD: CAM-Guided End-to-end Hybrid-Supervised Object Detection with Cascade Refinement [53.69674636044927]
  We present EHSOD, an end-to-end hybrid-supervised object detection system. It can be trained in one shot on both fully and weakly-annotated data. It achieves comparable results on multiple object detection benchmarks with only 30% fully-annotated data.
  arXiv  Detail & Related papers  (2020-02-18T08:04:58Z)

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.