Huang Jianjun

Huang Jianjun
Shenzhen University · College of Information Engineering

PhD

About

86
Publications
6,647
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
498
Citations

Publications

Publications (86)
Article
Full-text available
The low-rank matrix completion problem has aroused notable attention in various fields, such as engineering and applied sciences. The classical methods approximate the rank minimization problem by minimizing the nuclear norm, therefore obtaining unsatisfactory results, which may deviate from the true solution. In addition, most methods minimize the...
Article
Full-text available
Autism spectrum disorders (ASD) is a neurodevelopmental disorder that causes repetitive stereotyped behavior and social difficulties, early diagnosis and intervention are beneficial to improve treatment effect. Although multi-site data expand sample size, they suffer from inter-site heterogeneitys, which degrades the performance of identitying ASD...
Article
Renal tumor is one of the common tumors with high incidence, and accurate segmentation of renal tumors is helpful for preoperative evaluation. Computed Tomography (CT) plays an important role in the treatment of renal tumors and accurate segmentation of tumors in CT images may provide critical information for surgery. In this paper, a segmentation...
Article
High-Resolution (HR) Magnetic Resonance Images (MRI) can help physician diagnosis lesion more effectively. However, in practice, it is difficult to obtain HR-MRI due to equipment limitations, scanning time or patient comfort. Fortunately, with the development of information technology, HR-MRI could be obtained by some image post-processing approach...
Article
Full-text available
Introduction Epilepsy is a serious hazard to human health. Minimally invasive surgery is an extremely effective treatment to refractory epilepsy currently if the location of epileptic foci is given. However, it is challenging to locate the epileptic foci since a multitude of patients are MRI-negative. It is well known that DKI (diffusion kurtosis i...
Article
Electricity theft has significant impact on the power grids in terms of generating non-technical losses, which eventually degrading the power quality and minimizing the outfitted profit. In this paper, we proposed a hybrid approach based on deep learning and support vector machine for the detection of energy theft to facilitate and assess energy su...
Article
Full-text available
Deep learning (DL) models are highly research-oriented field in image compressive sensing in the recent studies. In compressive sensing theory, a signal is efficiently reconstructed from very small and limited number of measurements. Block-based compressive sensing is most promising and lenient compressive sensing (CS) approach mostly used to proce...
Article
Full-text available
Power transmission lines are the key network that transmits energy from the generation side to load. The complexity and uncertainty in the power system increase continuously due to the evolution of the smart grid, which needs an effective and accurate protection system. The faults in transmission lines affect the whole power system and also the con...
Article
Full-text available
Space‐time adaptive processing (STAP) for sparse arrays such as coprime and nested arrays is shown to have improved performance for clutter suppression in airborne radar as compared with uniform linear arrays with the same size. However, most of the existing STAP algorithms are derived based on the assumption that the array manifold is exactly know...
Article
Full-text available
Epilepsy is a serious hazard to human health. Minimally invasive surgery is currently an extremely effective treatment to refractory epilepsy. However, it is challenging to localize the lesion for most patients because they are MRI negative. The identification of epileptic foci in local brain region will be helpful to the localization of epileptic...
Article
Full-text available
Human detection and tracking is a key aspect in surveillance system due to its importance in timely identification of person, recognition of human activity and scene analysis. Convolutional neural networks have been widely used approach in detection and tracking related tasks. In this paper, a robust framework is presented for the human detection a...
Article
As one of the most important physical phenomena of underwater acoustics, ocean reverberation is a common and strong interference which significantly degrades the performance of target bearing estimation. Meanwhile, sensor failure is inevitable in actual sonar deployment as the underwater scene is complicated. Therefore, it is a challenge for acoust...
Article
Detection and classification methods have a vital and important role in identifying brain diseases. Timely detection and classification of brain diseases enable an accurate identification and effective management of brain impairment. Brain disorders are commonly most spreadable diseases and the diagnosing process is time-consuming and highly expens...
Article
Full-text available
Mild cognitive impairment (MCI) is a clinical state with a high risk of conversion to Alzheimer's Disease (AD). Since there is no effective treatment for AD, it is extremely important to diagnose MCI as early as possible, as this makes it possible to delay its progression toward AD. However, it's challenging to identify early MCI (EMCI) because the...
Article
Mild cognitive impairment (MCI) is an early sign of Alzheimer's disease (AD) which is the fourth leading disease mostly found in the aged population. Early intervention of MCI will possibly delay the progress towards AD, and this makes it very important to diagnose early MCI(EMCI). However, it is very difficult since the subtle difference between E...
Article
Full-text available
Capacitive proximity sensors (CPSs) are ubiquitous because of their simple design, low cost and low consumption. Capacitive displacement sensing, as one of the three sensing modalities, works for long distance and can be unitized to measure more physical quantities compared with capacitive volume and deformation sensing. In this paper, we firstly i...
Article
Full-text available
Compressive sampling (CS) is an attractive method to implement analog-to-information conversion (AIC) for sub-Nyquist radar, where random demodulation (RD) is the most successful AIC. However, RD only considers the sparse characteristic of one single radar pulse, and its mixing circuit still works at the Nyquist sampling rate. To exploit the strong...
Preprint
Full-text available
Space-time adaptive processing (STAP) algorithms with coprime arrays can provide good clutter suppression potential with low cost in airborne radar systems as compared with their uniform linear arrays counterparts. However, the performance of these algorithms is limited by the training samples support in practical applications. To address this issu...
Article
Space-time adaptive processing (STAP) algorithms with coprime arrays can provide good clutter suppression potential with low cost in airborne radar systems as compared with their uniform linear arrays counterparts. However, the performance of these algorithms is limited by the training samples support in practical applications. To address this issu...
Article
Full-text available
Space-time adaptive processing (STAP) for airborne radar with co-prime arrays is shown to have excellent superiority compared to traditional STAP with uniform linear array radar. However, high arithmetic computational complexity and large amount of training data are required in this approach. This motivates the authors to present a new approach whi...
Article
Full-text available
In this paper, we consider the problem of joint target detection and tracking in compressive sampling and processing (CSP-JDT). CSP can process the compressive samples of sparse signals directly without signal reconstruction, which is suitable for handling high-resolution radar signals. However, in CSP, the radar target detection and tracking probl...
Article
In this brief, a high sensitivity measuring system for capacitive sensor to detect moving target is presented. It mainly consists of a capacitance measuring circuit and a DC-blocking circuit. The capacitance measuring circuit is used to convert a capacitance to a DC voltage and the DC-blocking circuit is employed to extract the voltage variation. T...
Article
Full-text available
Coprime arrays and coprime time samplers have been receiving attractive attention recently due to their advantages of large apertures and achievable degrees of freedom (DoFs) with low cost. In this paper, different from traditional airborne radar with uniform transmitting pulses, the considered radar is configured with a coprime array in receiver a...
Article
This paper investigates the problem of direction-of-arrival (DOA) estimation of rectilinear or strictly second-order noncircular signals with a partly calibrated uniform linear array (ULA). Consider that the uncalibrated portion of the array suffers from unknown gains and phases, an extended data model corresponding to a virtual (extended) array is...
Article
In this paper, a new linear array configuration based on the concept of two-level nested array is proposed. Specifically, the proposed array configuration consists of two uniform linear arrays (ULAs) plus a separate sensor with appropriate spacing apart. Compared with the original two-level nested array, the degrees of freedom (DOF) of our proposed...
Conference Paper
In this paper, we focus on sparsity-based space-time adaptive processing (STAP) in airborne radar with compressive sampling both in Doppler and spatial domains. Compared with the uniform pluses repetition Frequency (UPRF) and uniform arrays (UA) radar, the designed radar transmits random pulse repetition interval pulses and receives the returns wit...
Conference Paper
Infrared (IR) image sequences are sparse in nature. This feature has been widely applied to IR image compression. In order to improve the recovery accuracy of IR small target image, a novel scheme is presented in this paper. Firstly, IR small target image is represented as a signal with characteristic of block-sparsity. Then, Bayesian framework is...
Article
Full-text available
This paper investigates the compression detection problem using sub-Nyquist radars, which is well suited to the scenario of high bandwidths in real-time processing because it would significantly reduce the computational burden and save power consumption and computation time. A compressive generalized likelihood ratio test (GLRT) detector for sparse...
Article
Full-text available
A fuzzy logic-based multi-factor aided multiple-model filter (FLMAMMF) for General aviation (GA) maneuvering target tracking (MTT) is presented. The target category and meteorological information are introduced into the interacting multiple model (IMM) filter to perform GA target tracking. Fuzzy logic inference is employed in the proposed algorithm...
Conference Paper
In this paper, a new approach based on Sub-sampled Inverse Fast Fourier Transform (SSIFFT) for efficiently acquiring compressive measurements is proposed, which is motivated by random filter based method and sub-sampled FFT. In our approach, to start with, we multiply the FFT of input signal and that of random-tap FIR filter in frequency domain and...
Article
Full-text available
A variational Bayesian approximation-based interacting multiple model (VB-IMM) filter for automatic dependent surveillance-broadcast (ADS-B) Data is proposed. ADS-B data is a type of measurements with unknown noise variances. The variational Bayesian adaptive Kalman filter (VB-AKF) is a recursively forming separable approximation to the joint distr...
Conference Paper
This paper investigates the compressive signal detection problem for radar system in the presence of compoundGaussian clutter. An effective random measurement matrix is designed for unknown signal detection problem in clutter-dominated environment. In order to not use reconstruction algorithm which would increase computational burden, we first repr...
Conference Paper
Full-text available
Aiming at the problem of incline alignment for vehicle-borne sensor system, a UKF-LM based incline alignment algorithm is presented. Two Unscented Kalman Filters (UKF) are used to estimate a calibration target's position in both sensor coordinate system and vehicle base-coordinate system, respectively. The nonlinear least-squares Levenberg-Marquard...
Conference Paper
Full-text available
In this paper, a top-hat transformation module is implemented for infrared small target detection. The top-hat algorithm uses two different structure elements in erosion and dilation. Erosion implements a 5×5 ring structure element process unit while dilation implements a 3×3 structure element one. The time delay of open operation is formulated and...
Article
Full-text available
A track iteration UKF based alignment algorithm for the estimation of a slowly time-varying spatial bias is presented. First, the spatial bias is estimated with a UKF filter. Second, the spatial alignment iteration is applied track to track according to the magnitude of the bias change. If the bias change is obvious, the alignment restarts and init...
Conference Paper
Full-text available
Spatial alignment is the prerequisite for the successful data fusion of multiple sensors. A CKF based spatial alignment algorithm for the estimation of bias between radar and infrared sensors on a same platform is presented. The system dynamics of this problem is established in a hybrid coordinate, i.e., the target position in the spherical coordin...
Article
Electron cyclotron resonance (ECR) plasma was applied to enhance the direct current magnetron sputtering to prepare hydrogenated diamond-like carbon (H-DLC) films. For different microwave powers, both argon and hydrogen gas are introduced separately as the ECR working gas to investigate the influence of microwave power on the microstructure and ele...
Article
For improving the performance of ACDA (Ant Colony Data Association) for data association in multi-target tracking, we propose the combined method of ACDA and FCM. Since FCM is a determinate algorithm, in nature based on NN (Nearest Neighbor), it could generate reasonable results in any case, which is a backup when ACDA becomes divergent. Experiment...
Article
A new UKF based for radar and infrared sensor registration method is provided. A so-called "hybrid states" concept is introduced to describe target's state, which consists of the target's range, bearing and elevation and its velocity in the Cartesian coordinate system. The dynamic function and the measurement function are deduced in hybrid states....
Article
In the view of the unfitness to the actual maneuver of targets that a fixed maneuvering frequency used in the current statistical model. Firstly, predicted measurements of special maneuvering frequency are clustered with the aid of maximum entropy fuzzy clustering. Then, the estimated means and covariance of the state are mixed by utilizing the fuz...
Conference Paper
Full-text available
Cyclic MUSIC is a high-resolution direction finding method that utilizes the cyclostationarity property of man-made signals to suppress noises and interferences with undesired cyclic frequency. However, its performance of direction finding can be severely degraded by sensor position errors of the sensor array. In this paper, a PSO based array shape...
Conference Paper
Full-text available
An adaptive alpha-beta filter based on cloud model inference is presented for maneuvering target tracking. The proposed tracker incorporates cloud model in a conventional alpha-beta filter by using the rule bank based on cloud model, which utilizes the residue error and the change of residue error in the last prediction to determine the values of a...
Conference Paper
Full-text available
In this paper, the augmented forms of the quadrature Kalman filter (QKF) and cubature Kalman filter (CKF) are presented for estimating the nonlinear dynamic systems. The QKF and CKF are modified by forming an augmented state variable, which concatenates the state and noise components together, so that the effect of process and measurement noises ca...
Article
Particle filters can become quite inefficient when applied to a high-dimensional state space since a prohibitively large number of samples may be required to approximate the underlying density functions with desired accuracy. In this paper, a novel multiple model Rao-Blackwellized particle filter (MMRBPF)-based algorithm has been proposed for manoe...
Conference Paper
A novel approach based on multifold building features for the task of detecting buildings in aerial photograph is presented. Firstly, a coarse classification based on the texture features was used. Secondly, line adjacency and spectrum features detection are applied to select possible building regions. Thirdly, the fuzzy logic inference is applied...
Conference Paper
Full-text available
A cloud model based c-means clustering approach (CMCM) is presented in this paper. Each cluster in CMCM is modeled by a cloud model, which characterizes the fuzziness and randomness of cluster and makes the clustering process more applicable than FCM. In the meantime, the new approach can avoid a trivial solution of the object function in FCM by re...
Article
The 3-dimensional upper airspace coverage on the restriction of the terrain is the NP problem in the space analysis. Its solution needs a large amount of calculation. To solve the problem, a method based on attention cognition theory for upper airspace coverage is proposed. This method simulates the mechanism in which the human brain selectively pa...
Article
This paper proposes a method based on quantum measurement for spherical shell clustering. This method simulates the conscious cognition of the human brain using quantum measurement. It regards a sample set as an environment quantum ensemble which is measurable and the stimulus quantum system. In this thought, each sample is treated as a microcosmic...
Article
A new solid waste disposal technology setup with DC arc plasma is presented. Being different from conventional combustion or burning such as incineration, it is based on a process called controlled high-temperature pyrolysis, the thermal destruction and recovery process. The results of vitrification of the circuit board is presented. The properties...
Article
The diversity and complexity of high-rise building shapes make it very difficult to extract them by traditional modeling and matching algorithms. Starting from detection of vertical lines, a strategy for automatic extraction of high-rise building in monocular high-resolution aerial images is developed under the evidential reasoning methodology, whi...
Article
In urban aerial images, the poor visibility of features in shadowed regions created by buildings prevents recognition of objects. It is necessary to compensate and remove the shadowed region. In this paper, a fuzzy Retinex is proposed to overcome the limitation of the well known image enhancement technique-Retinex. The fuzzy Retinex restricts the c...
Conference Paper
Full-text available
Dynamic textures are sequences of images of moving scenes that exhibit certain stationarity properties in time, for example, sea-waves, smoke, foliage, whirlwind etc. This work proposed a novel characterization of dynamic textures that poses the problems of recognizing. A method by spatio-temporal multiresolution histogram based on velocity and acc...
Article
Based on line detection, we introduce a line snake algorithm with vertices of traditional snakes replaced by straight line exemplars. Through the preliminary organization and interpretation functions of middle-level image processing techniques (e.g., line detection) for the chaotic low-level image information, the proposed method reduces the comput...
Article
A new shape-based feature vector, symmetrical edge orientation histogram, for description of main roads in higher resolution aerial images is presented. Based on the topology of edge pixels in image, the proposed feature vector describes the major shape properties of images preferably, and performs invariant with respect to translation, rotation, s...
Article
To track multiple targets in multisensor array with severe measuring errors, a fuzzy operation based fusion method is proposed. The system is made up of several types of sensors, considering that a single sensor is characterized by small coverage, great measuring error and serious time delay of data propagation. A nonsingleton fuzzy logic system is...
Conference Paper
Full-text available
A new method for shadow detection in colored urban aerial images is proposed. First, a new imaging model of shadows is presented, which indicates that hue values of shadowed image areas are larger than those of these areas non-shadowed. Based on this model, a thresholding technique is employed to detect shadowed areas. After detection, the Retinex...
Conference Paper
The diversity and complexity of high-rise building shapes make it very difficult to extract them automatically with traditional modeling and matching algorithms. In this paper, starting from detection of vertical lines as the key evidences, a strategy for automatic extraction of high-rise buildings in monocular high-resolution aerial images was dev...