arXiv subjects

Xiaoguang Zhao

Publications and source records attributed to Xiaoguang Zhao.

32 records · Page 2Linked to original sources

arXiv2023

DALNet: A Rail Detection Network Based on Dynamic Anchor Line

Rail detection is one of the key factors for intelligent train. In the paper, motivated by the anchor line-based lane detection methods, we propose a rail detection network called DALNet based on dynamic anchor line. Aiming to solve the problem that the predefined anchor line is image agnostic, we design a novel dynamic anchor line mechanism. It utilizes a dynamic anchor line generator to dynamically generate an appropriate anchor line for each rail instance based on the position and shape of the rails in the input image. These dynamically generated anchor lines can be considered as better position references to accurately localize the rails than the predefined anchor lines. In addition, we present a challenging urban rail detection dataset DL-Rail with high-quality annotations and scenario diversity. DL-Rail contains 7000 pairs of images and annotations along with scene tags, and it is expected to encourage the development of rail detection. We extensively compare DALNet with many competitive lane methods. The results show that our DALNet achieves state-of-the-art performance on our DL-Rail rail detection dataset and the popular Tusimple and LLAMAS lane detection benchmarks. The code will be released at https://github.com/Yzichen/mmLaneDet.

cs.CV↗

arXiv2022

Complementary Vanadium Dioxide Metamaterials with Enhanced Modulation Amplitude at Terahertz Frequencies

One route to create tunable metamaterials is through integration with "on-demand" dynamic quantum materials, such as vanadium dioxide (VO2). This enables new modalities to create high performance devices for historically challenging applications. Indeed, dynamic materials have often been integrated with metamaterials to imbue artificial structures with some degree of tunability. Conversely, metamaterials can be used to enhance and extend the natural tuning range of dynamic materials. Utilizing a complementary split ring resonator array deposited on a VO2 film, we demonstrate enhanced terahertz transmission modulation upon traversing the insulator-to-metal transition (IMT) at ~340 K. Our complementary metamaterial increases the modulation amplitude of the original VO2 film from 42% to 68.3% at 0.47 THz upon crossing the IMT, corresponding to an enhancement of 62.4%. Moreover, temperature dependent transmission measurements reveal a redshift of the resonant frequency arising from a giant increase of the permittivity of the VO2 film. Maxwell-Garnett effective medium theory was employed to explain the permittivity change upon transitioning through the IMT. Our results highlight that symbiotic integration of metamaterial arrays with quantum materials provides a powerful approach to engineer emergent functionality.

physics.app-ph↗

arXiv2021

Auxetics-Inspired Tunable Metamaterials for Magnetic Resonance Imaging

Auxetics refers to structures or materials with a negative Poisson's ratio, thereby capable of exhibiting counter-intuitive behaviors. Herein, auxetic structures are exploited to design mechanically tunable metamaterials in both planar and hemispherical configurations operating at megahertz (MHz) frequencies, optimized for their application to magnetic resonance imaging (MRI). Specially, the reported tunable metamaterials are composed of arrays of inter-jointed unit cells featuring metallic helices, enabling auxetic patterns with a negative Poisson's ratio. The deployable deformation of the metamaterials yields an added degree of freedom with respect to frequency tunability through the resultant modification of the electromagnetic interactions between unit cells. The metamaterials are fabricated using 3D printing technology and a ~20 MHz frequency shift of the resonance mode is enabled during deformation. Experimental validation is performed in a clinical (3.0 Tesla) MRI, demonstrating that the metamaterials enable a marked boost in radiofrequency (RF) field strength under resonance matched conditions, ultimately yielding a dramatic increase in the signal-to-noise ratio (SNR) (~ 4.5X) of MRI. The tunable metamaterials presented herein offer a novel pathway towards the practical utilization of metamaterials in MRI, as well as a range of other emerging applications.

physics.med-ph↗

arXiv2020

TB-Net: A Three-Stream Boundary-Aware Network for Fine-Grained Pavement Disease Segmentation

Regular pavement inspection plays a significant role in road maintenance for safety assurance. Existing methods mainly address the tasks of crack detection and segmentation that are only tailored for long-thin crack disease. However, there are many other types of diseases with a wider variety of sizes and patterns that are also essential to segment in practice, bringing more challenges towards fine-grained pavement inspection. In this paper, our goal is not only to automatically segment cracks, but also to segment other complex pavement diseases as well as typical landmarks (markings, runway lights, etc.) and commonly seen water/oil stains in a single model. To this end, we propose a three-stream boundary-aware network (TB-Net). It consists of three streams fusing the low-level spatial and the high-level contextual representations as well as the detailed boundary information. Specifically, the spatial stream captures rich spatial features. The context stream, where an attention mechanism is utilized, models the contextual relationships over local features. The boundary stream learns detailed boundaries using a global-gated convolution to further refine the segmentation outputs. The network is trained using a dual-task loss in an end-to-end manner, and experiments on a newly collected fine-grained pavement disease dataset show the effectiveness of our TB-Net.

cs.CV↗

arXiv2020

A Generalized Zero-Shot Framework for Emotion Recognition from Body Gestures

Although automatic emotion recognition from facial expressions and speech has made remarkable progress, emotion recognition from body gestures has not been thoroughly explored. People often use a variety of body language to express emotions, and it is difficult to enumerate all emotional body gestures and collect enough samples for each category. Therefore, recognizing new emotional body gestures is critical for better understanding human emotions. However, the existing methods fail to accurately determine which emotional state a new body gesture belongs to. In order to solve this problem, we introduce a Generalized Zero-Shot Learning (GZSL) framework, which consists of three branches to infer the emotional state of the new body gestures with only their semantic descriptions. The first branch is a Prototype-Based Detector (PBD) which is used to determine whether an sample belongs to a seen body gesture category and obtain the prediction results of the samples from the seen categories. The second branch is a Stacked AutoEncoder (StAE) with manifold regularization, which utilizes semantic representations to predict samples from unseen categories. Note that both of the above branches are for body gesture recognition. We further add an emotion classifier with a softmax layer as the third branch in order to better learn the feature representations for this emotion classification task. The input features for these three branches are learned by a shared feature extraction network, i.e., a Bidirectional Long Short-Term Memory Networks (BLSTM) with a self-attention module. We treat these three branches as subtasks and use multi-task learning strategies for joint training. The performance of our framework on an emotion recognition dataset is significantly superior to the traditional method of emotion classification and state-of-the-art zero-shot learning methods.

cs.CV↗

arXiv2020

A Prototype-Based Generalized Zero-Shot Learning Framework for Hand Gesture Recognition

Hand gesture recognition plays a significant role in human-computer interaction for understanding various human gestures and their intent. However, most prior works can only recognize gestures of limited labeled classes and fail to adapt to new categories. The task of Generalized Zero-Shot Learning (GZSL) for hand gesture recognition aims to address the above issue by leveraging semantic representations and detecting both seen and unseen class samples. In this paper, we propose an end-to-end prototype-based GZSL framework for hand gesture recognition which consists of two branches. The first branch is a prototype-based detector that learns gesture representations and determines whether an input sample belongs to a seen or unseen category. The second branch is a zero-shot label predictor which takes the features of unseen classes as input and outputs predictions through a learned mapping mechanism between the feature and the semantic space. We further establish a hand gesture dataset that specifically targets this GZSL task, and comprehensive experiments on this dataset demonstrate the effectiveness of our proposed approach on recognizing both seen and unseen gestures.

cs.CV↗

arXiv2019

Real-Time Human-Robot Interaction for a Service Robot Based on 3D Human Activity Recognition and Human-mimicking Decision Mechanism

This paper describes the development of a real-time Human-Robot Interaction (HRI) system for a service robot based on 3D human activity recognition and human-like decision mechanism. The Human-Robot Interactive (HRI) system, which allows one person to interact with a service robot using natural body language, collects sequences of 3D skeleton joints comprising rich human movement information about the user via Microsoft Kinect. This information is used to train a three-layer Long-Short-Term Memory (LSTM) network for human action recognition. The robot understands user intent based on an online LSTM network test, and responds to the user via movements of the robotic arm or chassis. Furthermore, the human-like decision mechanism is also fused into this process, which allows the robot to instinctively decide whether to interrupt the current task according to task priority. The framework of the overall system is established on the Robot Operating System (ROS) platform. The real-life activity interaction between our service robot and the user was conducted to demonstrate the effectiveness of developed HRI system.

cs.HC↗

arXiv2018

Automatic Safety Helmet Wearing Detection

Surveillance is essential for the safety of power substation. The detection of whether wearing safety helmets or not for perambulatory workers is the key component of overall intelligent surveillance system in power substation. In this paper, a novel and practical safety helmet detection framework based on computer vision, machine learning and image processing is proposed. In order to ascertain motion objects in power substation, the ViBe background modelling algorithm is employed. Moreover, based on the result of motion objects segmentation, real-time human classification framework C4 is applied to locate pedestrian in power substation accurately and quickly. Finally, according to the result of pedestrian detection, the safety helmet wearing detection is implemented using the head location, the color space transformation and the color feature discrimination. Extensive compelling experimental results in power substation illustrate the efficiency and effectiveness of the proposed framework.

cs.HC↗

arXiv2017

Electromechanically Tunable Metasurface Transmission Waveplate at Terahertz Frequencies

Dynamic polarization control of light is essential for numerous applications ranging from enhanced imaging to materials characterization and identification. We present a reconfigurable terahertz metasurface quarter-waveplate consisting of electromechanically actuated micro-cantilever arrays. Our anisotropic metasurface enables tunable polarization conversion cantilever actuation. Specifically, voltage-based actuation provides mode selective control of the resonance frequency, enabling real-time tuning of the polarization state of the transmitted light. The polarization tunable metasurface has been fabricated using surface micromachining and characterized using terahertz time domain spectroscopy. We observe a ~230 GHz cantilever actuated frequency shift of the resonance mode, sufficient to modulate the transmitted wave from pure circular polarization to linear polarization. Our CMOS-compatible tunable quarter-waveplate enriches the library of terahertz optical components, thereby facilitating practical applications of terahertz technologies.

physics.app-ph↗

arXiv2016

Terahertz-driven Luminescence and Colossal Stark Effect in CdSe:CdS Colloidal Quantum Dots

Unique optical properties of colloidal semiconductor quantum dots (QDs), arising from quantum mechanical confinement of charge within these structures, present a versatile testbed for the study of how high electric fields affect the electronic structure of nanostructured solids. Earlier studies of quasi-DC electric field modulation of QD properties have been limited by the electrostatic breakdown processes under the high externally applied electric fields, which have restricted the range of modulation of QD properties. In contrast, in the present work we drive CdSe:CdS core:shell QD films with high-field THz-frequency electromagnetic pulses whose duration is only a few picoseconds. Surprisingly, in response to the THz excitation we observe QD luminescence even in the absence of an external charge source. Our experiments show that QD luminescence is associated with a remarkably high and rapid modulation of the QD band-gap, which is changing by more than 0.5 eV (corresponding to 25% of the unperturbed bandgap energy) within the picosecond timeframe of THz field profile. We show that these colossal energy shifts can be consistently explained by the quantum confined Stark effect. Our work demonstrates a route to extreme modulation of material properties without configurational changes in material sets or geometries. Additionally, we expect that this platform can be adapted to a novel compact THz detection scheme where conversion of THz fields (with meV-scale photon energies) to the visible/near-IR band (with eV-scale photon energies) can be achieved at room temperature with high bandwidth and sensitivity.

physics.optics↗

arXiv2016

Terahertz Saturable Absorption in Superconducting Metamaterials

We present a superconducting metamaterial saturable absorber at terahertz frequencies. The absorber consists of an array of split ring resonators (SRRs) etched from a 100nm YBaCu3O7 (YBCO) film. A polyimide spacer layer and gold ground plane are deposited above the SRRs, creating a reflecting perfect absorber. Increasing either the temperature or incident electric field (E) decreases the superconducting condensate density and corresponding kinetic inductance of the SRRs. This alters the impedance matching in the metamaterial, reducing the peak absorption. At low electric fields, the absorption was optimized near 80% at T=10K and decreased to 20% at T=70K. For E=40kV/cm and T=10K, the peak absorption was 70% decreasing to 40% at 200kV/cm, corresponding to a modulation of 43%.

physics.optics↗

arXiv2015

Terahertz radiation-induced sub-cycle field electron emission across a split-gap dipole antenna

We use intense terahertz pulses to excite the resonant mode (0.6 THz) of a micro-fabricated dipole antenna with a vacuum gap. The dipole antenna structure enhances the peak amplitude of the in-gap THz electric field by a factor of ~170. Above an in-gap E-field threshold amplitude of ~10 MVcm-1, THz-induced field electron emission is observed (TIFEE) as indicated by the field-induced electric current across the dipole antenna gap. Field emission occurs within a fraction of the driving THz period. Our analysis of the current (I) and incident electric field (E) is in agreement with a Millikan-Lauritsen analysis where log (I) exhibits a linear dependence on 1/E. Numerical estimates indicate that the electrons are accelerated to a value of approximately one tenth of the speed of light.

physics.optics↗

arXiv2015

Nonlinear terahertz devices utilizing semiconducting plasmonic metamaterials

The development of responsive metamaterials has enabled the realization of compact tunable photonic devices capable of manipulating the amplitude, polarization, wave vector, and frequency of light. Integration of semiconductors into the active regions of metallic resonators is a proven approach for creating nonlinear metamaterials through optoelectronic control of the semiconductor carrier density. Metal-free subwavelength resonant semiconductor structures offer an alternative approach to create dynamic metamaterials. We present InAs plasmonic disk arrays as a viable resonant metamaterial at terahertz frequencies. Importantly, InAs plasmonic disks exhibit a strong nonlinear response arising from electric field induced intervalley scattering resulting in a reduced carrier mobility thereby damping the plasmonic response. We demonstrate nonlinear perfect absorbers configured as either optical limiters or saturable absorbers, including flexible nonlinear absorbers achieved by transferring the disks to polyimide films. Nonlinear plasmonic metamaterials show potential for use in ultrafast THz optics and for passive protection of sensitive electromagnetic devices.

physics.optics↗

arXiv2012

Nonlinear terahertz metamaterials via field-enhanced carrier dynamics in GaAs

We demonstrate nonlinear metamaterial split ring resonators (SRRs) on GaAs at terahertz frequencies. For SRRs on doped GaAs films, incident terahertz radiation with peak fields of ~20 - 160 kV/cm drives intervalley scattering. This reduces the carrier mobility and enhances the SRR LC response due to a conductivity decrease in the doped thin film. Above ~160 kV/cm, electric field enhancement within the SRR gaps leads to efficient impact ionization, increasing the carrier density and the conductivity which, in turn, suppresses the SRR resonance. We demonstrate an increase of up to 10 orders of magnitude in the carrier density in the SRR gaps on semi-insulating GaAs substrate. Furthermore, we show that the effective permittivity can be swept from negative to positive values with increasing terahertz field strength in the impact ionization regime, enabling new possibilities for nonlinear metamaterials.

physics.optics↗