Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userGhost-DeblurGAN and Its Application to Fiducial Marker System
142
0
0.0
(
0
)
Added by
Yibo Liu
Publication date
2021
fields
Electronic Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Motion blur can impede marker detection and marker-based pose estimation, which is common in real-world robotic applications involving fiducial markers. To solve this problem, we propose a novel lightweight generative adversarial network (GAN), Ghost-DeblurGAN, for real-time motion deblurring. Furthermore, a new large-scale dataset, YorkTag, provides pairs of sharp/blurred images containing fiducial markers and is proposed to train and qualitatively and quantitatively evaluate our model. Experimental results demonstrate that when applied along with fudicual marker systems to motion-blurred images, Ghost-DeblurGAN improves the marker detection significantly and mitigates the rotational ambiguity problem in marker-based pose estimation.
rate research
Read More
Navigation using only one marker, which contains four artificial features, is a challenging task since camera pose estimation using only four coplanar points suffers from the rotational ambiguity problem in a real-world application. This paper presents a framework of vision-based navigation for a self-driving vehicle equipped with multiple cameras and a wheel odometer. A multiple camera setup is presented for the camera cluster which has 360-degree vision such that our framework solely requires one planar marker. A Kalman-Filter-based fusion method is introduced for the multiple-camera and wheel odometry. Furthermore, an algorithm is proposed to resolve the rotational ambiguity problem using the prediction of the Kalman Filter as additional information. Finally, the lateral and longitudinal controllers are provided. Experiments are conducted to illustrate the effectiveness of the theory.
In a deduction system with some propositions and some known relations among these propositions, people usually care about the minimum of propositions by which all other propositions can be deduced according to these known relations. Here we call it a minimizing deduction system. Its common solution is the guess and determine method. In this paper we propose a method of solving the minimizing deduction system based on MILP. Firstly, we introduce the conceptions of state variable, path variable and state copy, which enable us to characterize all rules by inequalities. Then we reduce the deduction problem to a MILP problem and solve it by the Gurobi optimizer. As its applications, we analyze the security of two stream ciphers SNOW2.0 and Enocoro-128v2 in resistance to guess and determine attacks. For SNOW 2.0, it is surprising that it takes less than 0.1s to get the best solution of 9 known variables in a personal Macbook Air(Early 2015, Double Intel Core i5 1.6GHZ, 4GB DDR3). For Enocoro-128v2, we get the best solution of 18 known variables within 3 minutes. Whats more, we propose two improvements to reduce the number of variables and inequalities which significantly decrease the scale of the MILP problem.
State-of-the-art 2D image compression schemes rely on the power of convolutional neural networks (CNNs). Although CNNs offer promising perspectives for 2D image compression, extending such models to omnidirectional images is not straightforward. First, omnidirectional images have specific spatial and statistical properties that can not be fully captured by current CNN models. Second, basic mathematical operations composing a CNN architecture, e.g., translation and sampling, are not well-defined on the sphere. In this paper, we study the learning of representation models for omnidirectional images and propose to use the properties of HEALPix uniform sampling of the sphere to redefine the mathematical tools used in deep learning models for omnidirectional images. In particular, we: i) propose the definition of a new convolution operation on the sphere that keeps the high expressiveness and the low complexity of a classical 2D convolution; ii) adapt standard CNN techniques such as stride, iterative aggregation, and pixel shuffling to the spherical domain; and then iii) apply our new framework to the task of omnidirectional image compression. Our experiments show that our proposed on-the-sphere solution leads to a better compression gain that can save 13.7% of the bit rate compared to similar learned models applied to equirectangular images. Also, compared to learning models based on graph convolutional networks, our solution supports more expressive filters that can preserve high frequencies and provide a better perceptual quality of the compressed images. Such results demonstrate the efficiency of the proposed framework, which opens new research venues for other omnidirectional vision tasks to be effectively implemented on the sphere manifold.
Purpose: Implanted fiducial markers are often used in radiotherapy to facilitate accurate visualization and localization of tumors. Typically, such markers are used to aid daily patient positioning and to verify the targets position during treatment. This work introduces a novel, automated method for identifying fiducial markers in planar x-ray imaging. Methods: In brief, the method consists of automated filtration and reconstruction steps that generate 3D templates of marker positions. The normalized cross-correlation was the used to identify fiducial markers in projection images. To quantify the accuracy of the technique, a phantom study was performed. 75 pre-treatment CBCT scans of 15 pancreatic cancer patients were analyzed to test the automated technique under real life conditions, including several challenging scenarios for tracking fiducial markers. Results: In phantom and patient studies, the method automatically tracked visible marker clusters in 100% of projection images. For scans in which a phantom exhibited 0D, 1D, and 3D motion, the automated technique showed median errors of 39 $mu$m, 53 $mu$m, and 93 $mu$m, respectively. Human precision was worse in comparison. Automated tracking was performed accurately despite the presence of other metallic objects. Additionally, transient differences in the cross-correlation score identified instances where markers disappeared from view. Conclusions: A novel, automated method for producing dynamic templates of fiducial marker clusters has been developed. Production of these templates automatically provides measurements of tumor motion that occurred during the CBCT scan that was used to produce them. Additionally, using these templates with intra-fractional images could potentially allow for more robust real-time target tracking in radiotherapy.
A new theoretical method is proposed to describe the ground and excited cluster states of atomic nuclei. The method utilizes the equation-of-motion of the Gaussian wave packets to generate the basis wave functions having various cluster configurations. The generated basis wave functions are superposed to diagonalize the Hamiltonian. In other words, this method uses the real time as the generator coordinate. The application to the $3alpha$ system as a benchmark shows that the new method works efficiently and yields the result consistent with or better than the other cluster models. Brief discussion on the structure of the excited $0^+$ and $1^-$ states is also made.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
