Jianwei Wan

Jianwei Wan

Auto-generated profile, based on publicly available information

Jianwei Wan

National University of Defense Technology Changsha Hunan China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 February 2019 in Remote Sensing
Verified
Journal Article
Open access
PDF file
WWWei Wang
Wei Wang
DXDeliang Xiang
Deliang Xiang
Yifang BanYifang Ban
Yifang Ban
JZJun Zhang
Jun Zhang
JWJianwei Wan
Jianwei Wan
Image segmentation plays a fundamental role in image understanding and region-based applications. This paper presents a superpixel-based segmentation method for Polarimetric SAR (PolSAR) data, in which a two-stage merging strategy is proposed. First, based on the initial superpixel partition, the Wishart-merging stage (WMS) simultaneously merges the regions in homogeneous areas. The edge penalty is combined with the Wishart energy loss to ensure that the superpixels to be merged are from the same land cover. The second stage follows the iterative merging procedure, and applies the doubly flexible KummerU distribution to better characterize the resultant regions from WMS, which are usually located in heterogeneous areas. Moreover, the edge penalty and the proposed homogeneity penalty are adopted in the KummerU-merging stage (KUMS) to further improve the segmentation accuracy. The two-stage merging strategy applies the general statistical model for the superpixels without ambiguity, and more advanced model for the regions with ambiguity. Therefore, the implementing efficiency can be improved based on the WMS, and the accuracy can be increased through the KUMS. Experimental results on two real PolSAR datasets show that the proposed method can effectively improve the computation efficiency and segmentation accuracy compared with the classical merging-based methods.

8 February 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
FWFang Wang
Fang Wang
YCYong Chen
Yong Chen
JWJianwei Wan
Jianwei Wan
In the ocean environment, the minimum variance distortionless response beamformer usually has the problem of signal self-cancellation, that is, the acoustic signal of interest is erroneously suppressed as interference. By exploring the useful information behind the signal self-cancellation phenomenon, a high-precision direction estimation method for underwater acoustic sources is proposed. First, a pseudo spatial power spectrum is obtained by performing unit circle mapping on the beam response in the direction interval. Second, the online calculation process is given for reducing the computational complexity. The computer simulation results show that the proposed algorithm can obtain satisfactory direction estimation accuracy under the conditions of low intensity of acoustic source, strong interference and noise, and less array snapshot data.

26 February 2023 in Entropy
Verified
Journal Article
Open access
PDF file
CZCong Zhang
Cong Zhang
XKXu Ke
Xu Ke
YMYanxin Ma
Yanxin Ma
JWJianwei Wan
Jianwei Wan
Monocular depth estimation techniques are used to recover the distance from the target to the camera plane in an image scene. However, there are still several problems, such as insufficient estimation accuracy, the inaccurate localization of details, and depth discontinuity in planes parallel to the camera plane. To solve these problems, we propose the Global Feature Interaction Network (GFI-Net), which aims to utilize geometric features, such as object locations and vanishing points, on a global scale. In order to capture the interactive information of the width, height, and channel of the feature graph and expand the global information in the network, we designed a global interactive attention mechanism. The global interactive attention mechanism reduces the loss of pixel information and improves the performance of depth estimation. Furthermore, the encoder uses the Transformer to reduce coding losses and improve the accuracy of depth estimation. Finally, a local–global feature fusion module is designed to improve the depth map’s representation of detailed areas. The experimental results on the NYU-Depth-v2 dataset and the KITTI dataset showed that our model achieved state-of-the-art performance with full detail recovery and depth continuation on the same plane.

17 July 2022 in arXiv
Verified
Preprint
Open access
PDF file
GXGuoquan Xu
Guoquan Xu
HCHezhi Cao
Hezhi Cao
YZYifan Zhang
Yifan Zhang
YMYanxin Ma
Yanxin Ma
JWJianwei Wan
Jianwei Wan
XKXu Ke
Xu Ke
Transformer plays an increasingly important role in various computer vision areas and remarkable achievements have also been made in point cloud analysis. Since they mainly focus on point-wise transformer, an adaptive channel encoding transformer is proposed in this paper. Specifically, a channel convolution called Transformer-Conv is designed to encode the channel. It can encode feature channels by capturing the potential relationship between coordinates and features. Compared with simply assigning attention weight to each channel, our method aims to encode the channel adaptively. In addition, our network adopts the neighborhood search method of low-level and high-level dual semantic receptive fields to improve the performance. Extensive experiments show that our method is superior to state-of-the-art point cloud classification and segmentation methods on three benchmark datasets.

29 January 2021 in Shock and Vibration
Verified
Journal Article
Open access
PDF file
JZJianghao Zhuo
Jianghao Zhuo
LWLing Wang
Ling Wang
XKXu Ke
Xu Ke
JWJianwei Wan
Jianwei Wan
Rapid execution is required in operation‐oriented applications in underwater acoustic modelling. In this paper, the GPU graphic pipeline is used to accelerate the calculation of high‐resolution sound field image in the normal mode model of underwater acoustic propagation. The computer times of the proposed graphic pipeline method, the MATLAB code, and the C# code are compared for a stratified shallow water waveguide using the KRAKEN model at different frequencies. The research validates that the graphic pipeline method outperforms the classic CPU‐based methods in terms of execution speed at the frequencies where the eigenvalue equation in normal mode models can be solved.

5 May 2022 in arXiv
Verified
Preprint
Open access
PDF file
GXGuoquan Xu
Guoquan Xu
HCHezhi Cao
Hezhi Cao
YZYifan Zhang
Yifan Zhang
JWJianwei Wan
Jianwei Wan
XKXu Ke
Xu Ke
YMYanxin Ma
Yanxin Ma
Recently, deep neural networks have made remarkable achievements in 3D point cloud classification. However, existing classification methods are mainly implemented on idealized point clouds and suffer heavy degradation of per-formance on non-idealized scenarios. To handle this prob-lem, a feature representation learning method, named Dual-Neighborhood Deep Fusion Network (DNDFN), is proposed to serve as an improved point cloud encoder for the task of non-idealized point cloud classification. DNDFN utilizes a trainable neighborhood learning method called TN-Learning to capture the global key neighborhood. Then, the global neighborhood is fused with the local neighbor-hood to help the network achieve more powerful reasoning ability. Besides, an Information Transfer Convolution (IT-Conv) is proposed for DNDFN to learn the edge infor-mation between point-pairs and benefits the feature transfer procedure. The transmission of information in IT-Conv is similar to the propagation of information in the graph which makes DNDFN closer to the human reasoning mode. Extensive experiments on existing benchmarks especially non-idealized datasets verify the effectiveness of DNDFN and DNDFN achieves the state of the arts.