HMHaoyu Meng

Haoyu Meng

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Haoyu Meng has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Multipath Ghost Recognition and Suppression Method Based on Template Matching for Indoor Human Detection and Location

    by Xiaopeng Yang, Haoyu Meng, Xiaodong Qu, Weicheng Gao, Feiyang Liu

    Indoor human detection and location is a prominent research area within the Internet of Things, which can be effectively realized using radar technology. However, the electromagnetic waves will be reflected by the wall, leading to multipath ghosts in radar image, resulting in increased false alarm rates and degraded target location accuracy. In order to address this challenge, a multipath ghost recognition and suppression method based on template matching is proposed in this article. It is proved that the shape can be modeled as ellipse and the major axis and rotation angle of ghost is different from that of target. Two distinct features are calculated and used to achieve ghost recognition, and ghost mask is generated further. The effectiveness and robustness of the proposed method are validated through simulations and experimental results. Particularly, the proposed method does not depend on the information of building layout and is geometry-layout-free.


  • Azimuth Sidelobe Suppression Method for Through-the-Wall Radar Based on Phase Nonuniform Quantized Coherence Factor

    by Xiaopeng Yang, Haoyu Meng, Zeyu Ma, Xiaodong Qu, Weicheng Gao, Yi Zhao

    In through-the-wall radar systems, sparse arrays are frequently utilized to optimize the trade-off between system cost and array aperture. Nevertheless, the radar image will suffer from high azimuth sidelobes, resulting in fake targets in detection. To solve this problem, an azimuth sidelobe suppression method for through-the-wall radar based on phase nonuniform quantized coherence factor is proposed in this paper. Firstly, based on the positional relationship among the transceivers, target, and imaging grid, the phase at the azimuth sidelobe position in radar image can be determined, which is only relevant to radar parameters. Secondly, the quantized intervals are divided by the calculated phase. Additionally, the phase at each imaging grid is quantized to guarantee the maximum phase difference at the azimuth sidelobe position. Ultimately, the weight image is computed using the phase standard deviation. By applying weights to the original radar image, the azimuth sidelobes are effectively suppressed. Both numerical simulations and experimental results are analyzed to demonstrate the superiority and robustness of the proposed method.


  • Generalizable Indoor Human Activity Recognition Method Based on Micro-Doppler Corner Point Cloud and Dynamic Graph Learning

    by Xiaopeng Yang, Weicheng Gao, Xiaodong Qu, Haoyu Meng

    Through-the-wall radar (TWR) human activity recognition can be achieved by fusing micro-Doppler signature extraction and intelligent decision-making algorithms. However, limited by the insufficient priori of tester in practical indoor scenarios, the trained models on one tester are commonly difficult to inference well on other testers, which causes poor generalization ability. To solve this problem, this paper proposes a generalizable indoor human activity recognition method based on micro-Doppler corner point cloud and dynamic graph learning. In the proposed method, DoG-μD-CornerDet is used for micro-Doppler corner extraction on two types of radar profiles. Then, a micro-Doppler corner filtering method based on polynomial fitting smoothing is proposed to maximize the feature distance under the constraints of the kinematic model. The extracted corners from the two types of radar profiles are concatenated together into three-dimensional point cloud. Finally, the paper proposes a dynamic graph neural network (DGNN)-based recognition method for data-to-activity label mapping. Visualization, comparison and ablation experiments are carried out to verify the effectiveness of the proposed method. The results prove that the proposed method has strong generalization ability on radar data collected from different testers.


  • Moving Human Target Tracking Method Based on Rotation Kernelized Correlation Filter for Through-the-Wall Radar

    by Zeyu Ma, Xiaodong Qu, Hao Zhang, Haoyu Meng, Xiaopeng Yang

    Tracking the position of human targets behind obstacles is one of the core functions of through-the-wall radar. Due to the fixed viewing angle of the through-the-wall radar and the complex scattering properties of the human targets, the radar images of human targets will rotate with the human movement, resulting in tracking difficulties. Aiming at solving this problem, a moving human targets tracking method based on rotation kernelized correlation filter (RKCF) is proposed. In the proposed method, the angle of the target region is estimated and then a rotation is performed on the region image to obtain the candidate target region. Next, a filter is utilized to perform correlation operation with the candidate region to locate the target. Finally, the training samples are extracted and a rotational update operation is performed to train a new filter. Numerical simulation and experimental results verify the tracking performance of the proposed algorithm.


  • Wall Clutter Suppression Method Based on Amplitude Coherence Factor for MIMO Through-the-Wall Radar

    by Xiaopeng Yang, Ding Zhang, Yiming Wang, Haoyu Meng, Xiaodong Qu

    Multiple-input multiple-output (MIMO) throughthe-wall radar (TWR) is utilized for target detection under indoor environments. However, target signals are often overshadowed by wall clutter. Existed clutter suppression methods predominantly work effectively for TWR under synthetic aperture mode, with limited approaches for MIMO TWR. Therefore, this letter introduces amplitude coherence factor (ACF) to suppress the wall clutter. In the proposed method, the ACF is denoted by using the variance across all transmit-receive channels, which directly reflects the correlation of echo amplitudes in each pixel. Then, weights based on the ACF are assigned to the image of raw TWR image. The performance of ACF is validated by simulation and experimental results Index Terms


  • Through-the-Wall Radar Imaging Grating-Lobe and Sidelobe Suppression Method Based on Imaginary Sign Coherence Factor

    by Xiaopeng Yang, Haoyu Meng, Xiaodong Qu, Weicheng Gao

    In order to address the contradiction between azimuth resolution and system complexity, sparse array is employed in through-the-wall radar for the purpose of detecting moving targets in shadowed spaces. However, the radar images can be distorted due to azimuth grating-lobes and high sidelobes. To mitigate this issue, a through-the-wall radar imaging gratinglobe and sidelobe suppression method based on imaginary sign coherence factor is proposed in this letter. Theoretically, it is demonstrated that the phase across different channels is symmetrical at the azimuth grating-lobes and sidelobes in centrosymmetric radar. Then, the weight is calculated based on the positive and negative consistency of the imaginary part of the imaging results in each channel. The azimuth grating-lobes and sidelobes are suppressed by applying weight to the original image. Through simulations and experiments, the effectiveness and robustness of the proposed method are validated. The azimuth grating-lobes and sidelobes are suppressed efficiently without increasing the computation amount, demonstrating its practical feasibility.


  • Adaptive Micro-Doppler Corner Feature Extraction Method Based on Difference of Gaussian Filter and Deformable Convolution

    by Weicheng Gao, Xiaodong Qu, Haoyu Meng, Xiaolong Sun, Xiaopeng Yang

    Through-the-wall radar (TWR) utilizes range and Doppler information to achieve indoor human activity recognition. However, traditional recognition methods are developed based on range-time maps (RTM) and Doppler-time maps (DTM), resulting in low accuracy and poor robustness. In order to solve these problems, this letter proposes to use micro-Doppler corner feature to achieve activity recognition and gives an adaptive corner feature extraction method based on difference of Gaussian (DoG) filter and deformable convolution. Micro-Doppler corner feature is defined as the points on the radar squared-range and squared-Doppler images where the gray scale changes sharply in different directions, reflecting the inflection, stationing, intersection, and boundaries of the motion trajectory curves of the human limb nodes. The proposed corner feature extraction method utilizes the DoG filter to extract the micro-Doppler corner supervisory labels on simulated data. The labels are then used to train the $\boldsymbol{\mu }$ D-CornerDet, which is constructed based on deformable convolution network (DCN), task-adaptive deformable convolution network (TDCN), feature pyramid network (FPN) and learnable regression global attention module (LRGA). For predictions, only $\mu$ D-CornerDet is used on measured data to obatin the corner feature maps. Both numerical simulations and experiments are conducted to verify the effectiveness and robustness of the proposed method.


  • Indoor Human Behavior Recognition Method Based on Wavelet Scattering Network and Conditional Random Field Model

    by Xiaodong Qu, Weicheng Gao, Haoyu Meng, Yi Zhao, Xiaopeng Yang

    Ultra-wideband (UWB) through-the-wall radar (TWR) can be utilized for indoor human behavior recognition via micro-Doppler information. However, faced with weak micro-Doppler features and low accuracy, conventional recognition method does not perform well in shielded environment. To address these problems, this paper proposes an indoor human behavior recognition method based on wavelet scattering network and conditional random field model (TWR-WSN-CRF). In the proposed method, wavelet scattering network, speckle reducing anisotropic diffution (SRAD) with weighted guided image filter (WGIF) are employed for feature enhancement and noise suppression, and the signal-to-noise ratio (SNR) is improved. Then, human behavior recognition network based on conditional random field model is developed to extract global and local features from wall, target, noise subspace obtained by singular value decomposition. Finally, multi-layer perceptron (MLP) model and weighted majority voting (WMVE) method are used for fusion decision. The effectiveness of the proposed method is verified by experiment. The results show that compared with other methods, the proposed human behavior recognition method achieves highest recognition accuracy with 96.25% on the validation data set.


  • Open Access

    Rectum Protection by Rectal Gel Injection in Cervical Cancer Brachytherapy: A Dosimetric Study via Deformable Surface Dose Accumulation and Machine-Learning-Based Discriminative Modeling

    by Xuetao Wang, Bailin Zhang, Qiang He, Yilin Kong, Zhenhui Dai, Haoyu Meng, Fangjun Huang, Shengfeng Zhang, Yuanhu Zhu, Xiang Tan, et al.

    Purpose: This retrospective study aimed to evaluate the dosimetric effects of a rectal insertion of Kushen Ningjiao on rectal protection using deformable dose accumulation and machine learning–based discriminative modelling.Materials and Methods: Sixty-two patients with cervical cancer enrolled in a clinical trial, who received a Kushen Ningjiao injection of 20 g into their rectum for rectal protection via high–dose rate brachytherapy (HDR-BT, 6 Gy/f), were studied. The cumulative equivalent 2-Gy fractional rectal surface dose was deformably summed using an in-house-developed topography-preserved point-matching deformable image registration method. The cumulative three-dimensional (3D) dose was flattened and mapped to a two-dimensional (2D) plane to obtain the rectal surface dose map (RSDM). For analysis, the rectal dose (RD) was further subdivided as follows: whole, anterior, and posterior 3D-RD and 2D-RSDM. The dose–volume parameters (DVPs) were extracted from the 3D-RD, while the dose geometric parameters (DGPs) and textures were extracted from the 2D-RSDM. These features were fed into 192 classification models (built with 8 classifiers and 24 feature selection methods) for discriminating the dose distributions between pre-Kushen Ningjiao and pro-Kushen Ningjiao.Results: The rectal insertion of Kushen Ningjiao dialated the rectum in the ambilateral direction, with the rectal column increased from pre-KN 15 cm3 to post-KN 18 cm3 (P < 0.001). The characteristics of DGPs accounted for the largest portions of the top-ranked features. The top-ranked dosimetric features extracted from the posterior rectum were more reliable indicators of the dosimetric effects/changes introduced by the rectal insertion of Kushen Ningjiao. A significant dosimetric impact was found on the dose–volume parameters D1.0cc–D2.5cc extracted on the posterior rectal wall.Conclusions: The rectal insertion of Kushen Ningjiao incurs significant dosimetric changes on the posterior rectal wall. Whether this effect is eventually translated into clinical gains requires further long-term follow-up and more clinical data for confirmation.