arXiv subjects

Xin Zhong

Publications and source records attributed to Xin Zhong.

At least 73 records · Page 4Linked to original sources

arXiv2022

Foreign Object Debris Detection for Airport Pavement Images based on Self-supervised Localization and Vision Transformer

Supervised object detection methods provide subpar performance when applied to Foreign Object Debris (FOD) detection because FOD could be arbitrary objects according to the Federal Aviation Administration (FAA) specification. Current supervised object detection algorithms require datasets that contain annotated examples of every to-be-detected object. While a large and expensive dataset could be developed to include common FOD examples, it is infeasible to collect all possible FOD examples in the dataset representation because of the open-ended nature of FOD. Limitations of the dataset could cause FOD detection systems driven by those supervised algorithms to miss certain FOD, which can become dangerous to airport operations. To this end, this paper presents a self-supervised FOD localization by learning to predict the runway images, which avoids the enumeration of FOD annotation examples. The localization method utilizes the Vision Transformer (ViT) to improve localization performance. The experiments show that the method successfully detects arbitrary FOD in real-world runway situations. The paper also provides an extension to the localization result to perform classification; a feature that can be useful to downstream tasks. To train the localization, this paper also presents a simple and realistic dataset creation framework that only collects clean runway images. The training and testing data for this method are collected at a local airport using unmanned aircraft systems (UAS). Additionally, the developed dataset is provided for public use and further studies.

cs.CV↗

arXiv2022

Global strong solution for 3D compressible heat-conducting magnetohydrodynamic equations revisited

We revisit the 3D Cauchy problem of compressible heat-conducting magnetohydrodynamic equations with vacuum as far field density. By delicate energy method, we derive global existence and uniqueness of strong solutions provided that $(\|ρ_0\|_{L^\infty}+1)\big[\|ρ_0\|_{L^3}+ \|ρ_0\|_{L^\infty}+1)^2\big(\|\sqrt{ρ_0}u_0\|_{L^2}^2 +\|b_0\|_{L^2}^2\big)\big]\big[\|\nabla u_0\|_{L^2}^2+(\|ρ_0\|_{L^\infty}+1)\big(\|\sqrt{ρ_0}E_0\|_{L^2}^2+\|\nabla b_0\|_{L^2}^2\big)\big]$ is properly small. In particular, the smallness condition is independent of any norms of the initial data. This work improves our previous results [18, 19].

math.AP↗

arXiv2022

An Improved Normed-Deformable Convolution for Crowd Counting

In recent years, crowd counting has become an important issue in computer vision. In most methods, the density maps are generated by convolving with a Gaussian kernel from the ground-truth dot maps which are marked around the center of human heads. Due to the fixed geometric structures in CNNs and indistinct head-scale information, the head features are obtained incompletely. Deformable convolution is proposed to exploit the scale-adaptive capabilities for CNN features in the heads. By learning the coordinate offsets of the sampling points, it is tractable to improve the ability to adjust the receptive field. However, the heads are not uniformly covered by the sampling points in the deformable convolution, resulting in loss of head information. To handle the non-uniformed sampling, an improved Normed-Deformable Convolution (\textit{i.e.,}NDConv) implemented by Normed-Deformable loss (\textit{i.e.,}NDloss) is proposed in this paper. The offsets of the sampling points which are constrained by NDloss tend to be more even. Then, the features in the heads are obtained more completely, leading to better performance. Especially, the proposed NDConv is a light-weight module which shares similar computation burden with Deformable Convolution. In the extensive experiments, our method outperforms state-of-the-art methods on ShanghaiTech A, ShanghaiTech B, UCF\_QNRF, and UCF\_CC\_50 dataset, achieving 61.4, 7.8, 91.2, and 167.2 MAE, respectively. The code is available at https://github.com/bingshuangzhuzi/NDConv

cs.CV↗

arXiv2022

Entropy-bounded solutions to the 3D compressible heat-conducting magnetohydrodynamic equations with vacuum at infinity

The mathematical analysis on the behavior of the entropy for viscous, compressible, and heat conducting magnetohydrodynamic flows near the vacuum region is a challenging problem as the governing equation for entropy is highly degenerate and singular in the vacuum region. In particular, it is unknown whether the entropy remains its boundedness. In the present paper, we investigate the Cauchy problem to the three-dimensional (3D) compressible heat-conducting magnetohydrodynamic equations with vacuum at infinity only. We show that the uniform boundedness of the entropy and the $L^2$ regularities of the velocity and temperature can be propagated provided that the initial density decays suitably slow at infinity. The main tools are based on singularly weighted energy estimates and De Giorgi type iteration techniques developed by Li and Xin (arXiv:2111.14057) for the 3D full compressible Navier-Stokes system. Some new mathematical techniques and useful estimates are developed to deduce the lower and upper bounds on the entropy.

math.AP↗

arXiv2022

Global well-posedness for three-dimensional compressible viscous micropolar and heat-conducting fluids with vacuum at infinity and large oscillations

We investigate global well-posedness to the Cauchy problem of three-dimensional compressible viscous and heat-conducting micropolar fluid equations with zero density at infinity. By delicate energy estimates, we establish global existence and uniqueness of strong solutions under some smallness condition depending only on the parameters appeared in the system and the initial mass. In particular, the initial mass can be arbitrarily large. This improves our previous work [23]. Moreover, we also generalize the result [13] to the case that vacuum is allowed at infinity.

math.AP↗

arXiv2022

FOD-A: A Dataset for Foreign Object Debris in Airports

Foreign Object Debris (FOD) detection has attracted increased attention in the area of machine learning and computer vision. However, a robust and publicly available image dataset for FOD has not been initialized. To this end, this paper introduces an image dataset of FOD, named FOD in Airports (FOD-A). FOD-A object categories have been selected based on guidance from prior documentation and related research by the Federal Aviation Administration (FAA). In addition to the primary annotations of bounding boxes for object detection, FOD-A provides labeled environmental conditions. As such, each annotation instance is further categorized into three light level categories (bright, dim, and dark) and two weather categories (dry and wet). Currently, FOD-A has released 31 object categories and over 30,000 annotation instances. This paper presents the creation methodology, discusses the publicly available dataset extension process, and demonstrates the practicality of FOD-A with widely used machine learning models for object detection.

cs.CV↗

arXiv2022

Local well-posedness to the 2D Cauchy problem of full compressible magnetohydrodynamic equations with vacuum at infinity

This paper concerns the Cauchy problem of two-dimensional (2D) full compressible magnetohydrodynamic (MHD) equations in the whole plane $\mathbb{R}^2$ with zero density at infinity. By spatial weighted energy method, we derive the local existence and uniqueness of strong solutions provided that the initial density and the initial magnetic field decay not too slowly at infinity. Note that the initial temperature does not need to decay slowly at infinity. In particular, vacuum states at both the interior domain and the far field are allowed.

math.AP↗

arXiv2021

Global well-posedness to the 2D Cauchy problem of nonhomogeneous heat conducting Navier-Stokes and magnetohydrodynamic equations with vacuum at infinity

We revisit the 2D Cauchy problem of nonhomogeneous heat conducting magnetohydrodynamic (MHD) equations in $\mathbb{R}^2$. For the initial density allowing vacuum at infinity, we derive the global existence and uniqueness of strong solutions provided that the initial density and the initial magnetic decay not too slowly at infinity. In particular, the initial data can be arbitrarily large. This improves our previous work where the initial density has non-vacuum states at infinity. The result could also be viewed as an extension of the study in L{ü}-Xu-Zhong for the inhomogeneous case to the full inhomogeneous situation. The method is based on delicate spatial weighted estimates and the structural characteristic of the system under consideration. As a byproduct, we get the global existence of strong solutions to the 2D Cauchy problem for nonhomogeneous heat conducting Navier-Stokes equations with vacuum at infinity.

math.AP↗

arXiv2021

Global well-posedness and exponential decay of 2D nonhomogeneous Navier-Stokes and magnetohydrodynamic equations with density-dependent viscosity and vacuum

We establish global well-posedness of strong solutions for the nonhomogeneous magnetohydrodynamic equations with density-dependent viscosity and initial density allowing vanish in two-dimensional (2D) bounded domains. Applying delicate energy estimates and Desjardins' interpolation inequality, we derive the global existence of a unique strong solution provided that $\|\nablaμ(ρ_0)\|_{L^q}$ is suitably small. Moreover, we also obtain exponential decay rates of the solution. In particular, there is no need to impose some compatibility condition on the initial data despite the presence of vacuum. As a direct application, it is shown that the similar result also holds for the nonhomogeneous Navier-Stokes equations with density-dependent viscosity.

math.AP↗

arXiv2021

DeepGOMIMO: Deep Learning-Aided Generalized Optical MIMO with CSI-Free Blind Detection

Generalized optical multiple-input multiple-output (GOMIMO) techniques have been recently shown to be promising for high-speed optical wireless communication (OWC) systems. In this paper, we propose a novel deep learning-aided GOMIMO (DeepGOMIMO) framework for GOMIMO systems, where channel state information (CSI)-free blind detection can be enabled by employing a specially designed deep neural network (DNN)-based MIMO detector. The CSI-free blind DNN detector mainly consists of two modules: one is the pre-processing module which is designed to address both the path loss and channel crosstalk issues caused by MIMO transmission, and the other is the feed-forward DNN module which is used for joint detection of spatial and constellation information by learning the statistics of both the input signal and the additive noise. Our simulation results clearly verify that, in a typical indoor 4 $\times$ 4 MIMO-OWC system using both generalized optical spatial modulation (GOSM) and generalized optical spatial multiplexing (GOSMP) with unipolar non-zero 4-ary pulse amplitude modulation (4-PAM) modulation, the proposed CSI-free blind DNN detector achieves near the same bit error rate (BER) performance as the optimal joint maximum-likelihood (ML) detector, but with much reduced computational complexity. Moreover, since the CSI-free blind DNN detector does not require instantaneous channel estimation to obtain accurate CSI, it enjoys the unique advantages of improved achievable data rate and reduced communication time delay in comparison to the CSI-based zero-forcing DNN (ZF-DNN) detector.

eess.SP↗

arXiv2021

A Deep Learning-based Audio-in-Image Watermarking Scheme

This paper presents a deep learning-based audio-in-image watermarking scheme. Audio-in-image watermarking is the process of covertly embedding and extracting audio watermarks on a cover-image. Using audio watermarks can open up possibilities for different downstream applications. For the purpose of implementing an audio-in-image watermarking that adapts to the demands of increasingly diverse situations, a neural network architecture is designed to automatically learn the watermarking process in an unsupervised manner. In addition, a similarity network is developed to recognize the audio watermarks under distortions, therefore providing robustness to the proposed method. Experimental results have shown high fidelity and robustness of the proposed blind audio-in-image watermarking scheme.

cs.MM↗

arXiv2021

Global well-posedness and large time behavior for compressible non-isothermal nematic liquid crystal flows with vacuum at infinity

We investigate the Cauchy problem of three-dimensional compressible non-isothermal nematic liquid crystal flows in $\mathbb{R}^3$. We derive the global existence and uniqueness of strong solutions with both interior and far field vacuum states provided that the initial data are of small total energy. This improves our previous work in the sense that the initial data allow possibly large oscillations. The key analysis is based on delicate energy estimates and the structural characteristic of the system under consideration. Moreover, we also show the algebraic decay estimates of the solution. The results could be viewed as an extension of the studies in Li-Xu-Zhang for the isothermal case to the non-isothermal situation.

math.AP↗

arXiv2021

Deep Learning-Aided OFDM-Based Generalized Optical Quadrature Spatial Modulation

In this paper, we propose an orthogonal frequency division multiplexing (OFDM)-based generalized optical quadrature spatial modulation (GOQSM) technique for multiple-input multiple-output optical wireless communication (MIMO-OWC) systems. Considering the error propagation and noise amplification effects when applying maximum likelihood and maximum ratio combining (ML-MRC)-based detection, we further propose a deep neural network (DNN)-aided detection for OFDM-based GOQSM systems. The proposed DNN-aided detection scheme performs the GOQSM detection in a joint manner, which can efficiently eliminate the adverse effects of both error propagation and noise amplification. The obtained simulation results successfully verify the superiority of the deep learning-aided OFDM-based GOQSM technique for high-speed MIMO-OWC systems.

eess.SP↗

arXiv2021

Integrative Use of Computer Vision and Unmanned Aircraft Technologies in Public Inspection: Foreign Object Debris Image Collection

Unmanned Aircraft Systems (UAS) have become an important resource for public service providers and smart cities. The purpose of this study is to expand this research area by integrating computer vision and UAS technology to automate public inspection. As an initial case study for this work, a dataset of common foreign object debris (FOD) is developed to assess the potential of light-weight automated detection. This paper presents the rationale and creation of this dataset. Future iterations of our work will include further technical details analyzing experimental implementation. At a local airport, UAS and portable cameras are used to collect the data contained in the initial version of this dataset. After collecting these videos of FOD, they were split into individual frames and stored as several thousand images. These frames are then annotated following standard computer vision format and stored in a folder-structure that reflects our creation method. The dataset annotations are validated using a custom tool that could be abstracted to fit future applications. Initial detection models were successfully created using the famous You Only Look Once algorithm, which indicates the practicality of the proposed data. Finally, several potential scenarios that could utilize either this dataset or similar methods for other public service are presented.

cs.CV↗

arXiv2021

Global well-posedness and exponential decay to the Cauchy problem of nonhomogeneous Navier-Stokes equations with density-dependent viscosity and vacuum in $\mathbb{R}^2$

We study global well-posedness of strong solutions for the nonhomogeneous Navier-Stokes equations with density-dependent viscosity and initial density allowing vanish in $\mathbb{R}^2$. Applying a logarithmic interpolation inequality and delicate energy estimates, we show the global existence of a unique strong solution provided that $\|\nablaμ(ρ_0)\|_{L^q}$ is suitably small, which improves the previous result of Huang and Wang [SIAM J. Math. Anal. 46, 1771--1788 (2014)] to the whole space case. Moreover, we also derive exponential decay rates of the solution. In particular, there is no need to require additional initial compatibility condition despite the presence of vacuum.

math.AP↗

arXiv2020

DLWIoT: Deep Learning-based Watermarking for Authorized IoT Onboarding

The onboarding of IoT devices by authorized users constitutes both a challenge and a necessity in a world, where the number of IoT devices and the tampering attacks against them continuously increase. Commonly used onboarding techniques today include the use of QR codes, pin codes, or serial numbers. These techniques typically do not protect against unauthorized device access-a QR code is physically printed on the device, while a pin code may be included in the device packaging. As a result, any entity that has physical access to a device can onboard it onto their network and, potentially, tamper it (e.g.,install malware on the device). To address this problem, in this paper, we present a framework, called Deep Learning-based Watermarking for authorized IoT onboarding (DLWIoT), featuring a robust and fully automated image watermarking scheme based on deep neural networks. DLWIoT embeds user credentials into carrier images (e.g., QR codes printed on IoT devices), thus enables IoT onboarding only by authorized users. Our experimental results demonstrate the feasibility of DLWIoT, indicating that authorized users can onboard IoT devices with DLWIoT within 2.5-3sec.

cs.CR↗

arXiv2020

An Automated and Robust Image Watermarking Scheme Based on Deep Neural Networks

Digital image watermarking is the process of embedding and extracting a watermark covertly on a cover-image. To dynamically adapt image watermarking algorithms, deep learning-based image watermarking schemes have attracted increased attention during recent years. However, existing deep learning-based watermarking methods neither fully apply the fitting ability to learn and automate the embedding and extracting algorithms, nor achieve the properties of robustness and blindness simultaneously. In this paper, a robust and blind image watermarking scheme based on deep learning neural networks is proposed. To minimize the requirement of domain knowledge, the fitting ability of deep neural networks is exploited to learn and generalize an automated image watermarking algorithm. A deep learning architecture is specially designed for image watermarking tasks, which will be trained in an unsupervised manner to avoid human intervention and annotation. To facilitate flexible applications, the robustness of the proposed scheme is achieved without requiring any prior knowledge or adversarial examples of possible attacks. A challenging case of watermark extraction from phone camera-captured images demonstrates the robustness and practicality of the proposal. The experiments, evaluation, and application cases confirm the superiority of the proposed scheme.

cs.MM↗

arXiv2020

Global well-posedness to three-dimensional full compressible magnetohydrodynamic equations with vacuum

This paper studies the Cauchy problem for three-dimensional viscous, compressible, and heat conducting magnetohydrodynamic equations with vacuum as far field density. We prove the global existence and uniqueness of strong solutions provided that the quantity $\|ρ_0\|_{L^\infty}+\|b_0\|_{L^3}$ is suitably small and the viscosity coefficients satisfy $3μ>λ$. Here, the initial velocity and initial temperature could be large. The assumption on the initial density do not exclude that the initial density may vanish in a subset of $\mathbb{R}^3$ and that it can be of a nontrivially compact support. Our result is an extension of the works of Fan and Yu \cite{FY09} and Li et al. \cite{LXZ13}, where the local strong solutions in three dimensions and the global strong solutions for isentropic case were obtained, respectively. The analysis is based on some new mathematical techniques and some new useful energy estimates. This paper can be viewed as the first result concerning the global existence of strong solutions with vacuum at infinity in some classes of large data in higher dimension.

math.AP↗