Chentao Zhang

Xiamen University | XMU · Department of Instrumental and Electrical Engineering

Depth estimation is an essential component of computer vision applications for environment perception, 3D reconstruction and scene understanding. Among the available methods, self-supervised monocular depth estimation is noteworthy for its cost-effectiveness, ease of installation and data accessibility. However, there are two challenges with curren...

High sensitivity is crucial for anisotropic magnetoresistive (AMR) sensors in industrial applications. In this paper, a high- sensitive AMR sensor based on magnetoresistive thin films with Ta/NiFe/Ta/Al four-layer structure is proposed and fabricated. Firstly, the structural parameters were optimized by finite element analysis. Secondly, thin film...

Epidermal electronics that can monitor physiological signals such as surface electromyogram (sEMG) signals attract widespread attentions in personalized healthcare, human–machine interfaces (HMI) and virtual/augmented reality (AR/VR). However, conventional electromyographic electrodes suffer from skin discomfort, susceptibility to motion artifact i...

We present a camera‐based human body parameters measurement approach and develop a human postural assessment system. The approach combines the conventional contact measurement method and the non‐contact measurement method to overcome some shortcomings in terms of time, expense, and professionalism in early methods. The entire measurement system con...

Aiming at solving the issue of blurred images and difficult recognition of digital meters encountered by inspection robots in the inspection process, this paper proposes a deep-learning-based method for blurred image restoration and LED digital identification. Firstly, fast Fourier transform (FFT) is used to perform blur detection on the acquired i...

In the recognition of distracted driving behaviour, traditional manual feature extraction is subjective and complex; single deep convolutional network also has problems such as insufficient generalisation performance and stability. To solve the above problems, this paper proposes a distracted driving behaviour recognition method based on transfer l...

Conventional reconnaissance camera systems have been flown on manned aircraft, where the weight, size, and power requirements are not stringent. However, today, these parameters are important for unmanned aerial vehicles (UAVs). This article provides a solution to the design of airborne large aperture infrared optical systems, based on a monocentri...

The photocatalytic degradation, as an environmental-friendly technology, has great significance for cost-effective and efficient catalysis processes, wherein piezo-photocatalysis can significantly increase the catalytic degradation rate using both solar and mechanical energy. Here, a ternary heterostructure PVDF/ZnO/Au (PZA) nanobrush photocatalyst...

Supervoxels have a widespread application of instance segmentation on account of the merit of providing a highly approximate representation with fewer data. However, low accuracy, mainly caused by point cloud adhesion in the localization of industrial robots, is a crucial issue. An improved bottom-up clustering method based on supervoxels was propo...

To solve the problem of inflexibility of offline hand–eye calibration in “eye-in-hand” modes, an online hand–eye calibration method based on the ChArUco board is proposed in this paper. Firstly, a hand–eye calibration model based on the ChArUco board is established, by analyzing the mathematical model of hand–eye calibration, and the image features...

For the task of obstacle detection in a complex traffic environment, this paper proposes a road-free space extraction and obstacle detection method based on stereo vision. The proposed method combines the advantages of the V-disparity image and the Stixel method. Firstly, the depth information and the V-disparity image are calculated according to t...

In this latest work, the Newly Modified Robust Tensor Principal Component Analysis (New RTPCA) using affine transformation and L 2,1 norms is proposed to remove the outliers and heavy sparse noises in signal processing. This process is done by decomposing the original data matrix as the low-rank heavy sparse noises. The determination of the potenti...

In this work, we propose a novel method for head pose estimation and face recovery, particularly to solve the potential impacts of noises in signal processing to get an efficient and effective model that is more resilient with annoying effects through adding affine transformation with the low-rank robust subspace regression. Consequently, the corru...

Currently, pointer meters in substations are read manually, which causes a waste of human resources. To realize automatic reading of such meters, an accurate method for recognizing and reading of pointer meters was proposed for the inspection robot in substation. The new method consists of three steps. Step 1: the image is preprocessed with graysca...

In order to improve industrial production efficiency, a hand–eye system based on 3D vision is proposed and the proposed system is applied to the assembly task of workpieces. First, a hand–eye calibration optimization algorithm based on data filtering is proposed in this paper. This method ensures the accuracy required for hand–eye calibration by fi...

In this paper, we developed a new robust part-based model for facial landmark localization and detection via affine transformation. In contrast to the existing works, the new algorithm incorporates affine transformations with the robust regression to tackle the potential effects of outliers and heavy sparse noises, occlusions and illuminations. As...

Optical Wireless Communications (OWCs) can play vital role in providing communication in healthcare infrastructure’s, where contagious patients are admitted or treated as well as other patients are coming without any side effects as of radio frequency communication. In this paper, we propose high-speed cost-efficient free space optical (FSO) system...

In this paper, we propose a novel robust algorithm for image recovery via affine transformations, the weighted nuclear, L∗,w, and the L2,1 norms. The new method considers the spatial weight matrix to account the correlated samples in the data, the L2,1 norm to tackle the dilemma of extreme values in the high-dimensional images, and the L∗,w norm ne...

The expansion of high-speed communication needs due to explosive growth of subscribers each year has led the researchers to design the next generation communication systems which can cope with the current growing demand. Millimeter waves, operated within the range of 30 GHz to 300 GHz, can become potential carrier for delivering large amount of dat...

Herein we design a fiber sensor able to simultaneously measure the temperature and the pressure under harsh conditions, such as strong electromagnetic interference and high pressure. It is built on the basis of the fiber-optic Fabry–Perot (F–P) interference and the temperature sensitive mechanism of fluorescent materials. Both halogen lamps and lig...

Laser-induced-plasma-assisted ablation (LIPAA) is a promising micro-machining method that can fabricate microstructure on hard and transparent double-polished single crystal sapphire (SCS). While ablating, a nanosecond pulse 1064 nm wavelength laser beam travels through the SCS substrate and bombards the copper target lined up behind the substrate,...

Surface-enhanced Raman scattering (SERS) has been extensively investigated as an effective approach for trace species detection. Silver nanostructures are high-sensitivity SERS substrates in common use, but their poor chemical stability impedes practical applications. Herein, a stable and sensitive SERS substrate based on the hybrid structures of g...

An automatic setup based on the laser-assisted chemical vapor deposition method has been developed for the rapid synthesis of graphene patterns. The key components of this setup include a laser beamcontrol and focusing unit, a laser spot monitoring unit, and a vacuum and flow control unit. A laser beam with precision control of laser power is focus...

Surface enhanced Raman scattering (SERS) is an efficient technique to detect low concentration molecules. In this work, periodical silicon nanowires (SiNWs) integrated with metal-insulator-metal (MIM) layers are employed as SERS substrates. Laser interference lithography (LIL) combined with reactive ion etching (RIE) is used to fabricate large-area...

Surface enhanced Raman spectroscopy (SERS) has drawn much research interest in the past decades as an efficient technique to detect low-concentration molecules. Among many technologies, which can be used to fabricate SERS substrates, laser ablation is a simple and high-speed method to produce large-area SERS substrates. This work investigates the a...

Lasers are frequently used to locally open dielectric layers for contacting the front or rear side of advanced silicon wafer solar cell architectures. For reasons of cost, laser processes are usually carried out in ambient environment, which inevitably leads to the oxidation of silicon. In order to achieve maximum solar cell efficiency, the laser p...

In recent decades, multispectral imaging (MSI) has been approved as an effective tool to detect and discriminate targets in industrial application. A narrowband micro-arrayed multispectral filter mosaic (MSFM) based on MSI technology is proposed to miniaturize MSI instrumentation. There are many reasons to believe that this innovation is going to r...

Electric vehicles is a new energy and environmentally friendly vehicles. But in the process of development and popularization of electric vehicles, China is facing many difficulties. By introducing a convenient rental system for electric vehicles based on internet of things for vehicle, electric vehicles can be applied in large-scale in Chinese cit...