Bokun Tian

Dr. Bokun Tian

orcid

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
6 August 2020 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
MWMou Wang
Mou Wang
WWweishunjun Wei
weishunjun Wei
JSJun Shi
Jun Shi
YWYue Wu
Yue Wu
QQQizhe Qu
Qizhe Qu
BTBokun Tian
Bokun Tian
Since the Compressed Sensing (CS) theory broke through the limitation of the traditional Nyquist sampling theory, it has attracted extensive attention in the field of microwave imaging. However, in three dimensional (3-D) microwave sparse reconstruction application, conventional CS-based algorithms always suffer from huge computational cost. In this paper, a novel 3-D microwave sparse reconstruction method based on a complex-valued sparse reconstruction network (CSR-Net) is proposed, which converts complex number operations into matrix operations for real and imaginary parts. Using the “unfolding + network approximate” scheme, each iteration process of CS-based iterative threshold optimization is designed as a block of CSR-Net, and a modified shrinkage term is introduced to improve the convergence performance of the approach. In addition, CSR-Net adopts a convolutional neural network module to replace a nonlinear sparse representation process, which dramatically reduces computational complexity and improves reconstruction performance over conventional CS-based iterative threshold optimization algorithms. Then, we divide the 3-D scene into a series of 2-D slices, and a phase correction scheme is adopted to ensure that the whole 3-D scene can be reconstructed with measurement matrix of a slice. Moreover, an efficient Position-Amplitude-Random (PAR) training method without additional real-measured data is employed for the proposed network, which effectively train the CSR-Net without enough real-measured data. Extensive experiment results demonstrate that CSR-Net outperforms both conventional iterative threshold optimization methods and deep network-based ISTA-NET-plus large margins. Its speed and reconstruction accuracy in 3-D imaging can achieve a state-of-the-art level.

30 April 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
BTBokun Tian
Bokun Tian
Xiaoling ZhangXiaoling Zhang
Xiaoling Zhang
LLLiang Li
Liang Li
LPLing Pu
Ling Pu
Liming PuLiming Pu
Liming Pu
WWweishunjun Wei
weishunjun Wei
Because of the three-dimensional (3D) imaging scene’s sparsity, compressed sensing (CS) algorithms can be used for linear array synthetic aperture radar (LASAR) 3D sparse imaging. CS algorithms usually achieve high-quality sparse imaging at the expense of computational efficiency. To solve this problem, a fast Bayesian compressed sensing algorithm via relevance vector machine (FBCS–RVM) is proposed in this paper. The proposed method calculates the maximum marginal likelihood function under the framework of the RVM to obtain the optimal hyper-parameters; the scattering units corresponding to the non-zero optimal hyper-parameters are extracted as the target-areas in the imaging scene. Then, based on the target-areas, we simplify the measurement matrix and conduct sparse imaging. In addition, under low signal to noise ratio (SNR), low sampling rate, or high sparsity, the target-areas cannot always be extracted accurately, which probably contain several elements whose scattering coefficients are too small and closer to 0 compared to other elements. Those elements probably make the diagonal matrix singular and irreversible; the scattering coefficients cannot be estimated correctly. To solve this problem, the inverse matrix of the singular matrix is replaced with the generalized inverse matrix obtained by the truncated singular value decomposition (TSVD) algorithm to estimate the scattering coefficients correctly. Based on the rank of the singular matrix, those elements with small scattering coefficients are extracted and eliminated to obtain more accurate target-areas. Both simulation and experimental results show that the proposed method can improve the computational efficiency and imaging quality of LASAR 3D imaging compared with the state-of-the-art CS-based methods.

25 August 2019 in Sensors
Verified
Journal Article
Open access
PDF file
XTXinxin Tang
Xinxin Tang
Xiaoling ZhangXiaoling Zhang
Xiaoling Zhang
JSJun Shi
Jun Shi
WWweishunjun Wei
weishunjun Wei
BTBokun Tian
Bokun Tian
It is difficult for multichannel maneuvering synthetic aperture radar (SAR) to achieve ground moving target 2D velocity estimation and refocusing. In this paper, a novel method based on back projection (BP) and velocity SAR (VSAR) is proposed to cope with the issues. First, the static scene is reconstructed by BP to solve the imaging problem of multichannel maneuvering SAR. Then, the static clutter is suppressed, and the range velocity is estimated via VSAR processing. As for azimuth velocity estimation and refocusing, a velocity search method based on velocity-aided BP (VA-BP) and VSAR is proposed to accomplish them. First, each azimuth velocity in the search and the estimated range velocity are used to image the moving target in a small-sized subimage space by VA-BP, i.e., matching the range history and the Doppler phase of the moving target in the image processing. Then, multiple sets of multichannel SAR subimages corresponding to different azimuth velocities are generated, and the clutter of each set of multichannel SAR subimages is also suppressed by VSAR processing. After that, the azimuth velocity is estimated by searching the clutter-suppressed subimage of the first spatial receiving channel in each set of multichannel SAR subimages with the best refocusing quality measured by the minimum entropy. Simulation results show the proposed method can reach high accuracy in moving target 2D velocity estimation and refocusing with the absolute error of 2D velocity estimation smaller than 0.1 m/s.

23 January 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
CWChen Wang
Chen Wang
JSJun Shi
Jun Shi
CTChongben Tao
Chongben Tao
FXFenglei Xu
Fenglei Xu
XTXinxin Tang
Xinxin Tang
Xiaoling ZhangXiaoling Zhang
Xiaoling Zhang
Recently, plenty of millimeter-wave image concealed object detection models have achieved superior performance on benchmark datasets. The success of these models heavily depends on a large amount of fully-annotated data. However, noisy-label data often exist in a large-scale dataset, which deteriorate the performance of models. In this paper, we delve into the training of the concealed object detector with label noise, where we recognize divergent types of noisy annotations. To tackle the multi-type label noise problem, we propose a unified framework including two stages: the label noise modeling and the correction training. We design the region-level label noise modeling, which analyzes and models label noise via the classification branch loss curves. To correct the labels during training, we design the uncertainty-weighted loss for label correction. The experiments on a millimeter-wave security image dataset demonstrate the effectiveness of our proposed training framework, which can alleviate the negative influence of noisy annotations on network training. By introducing our framework, the object detection network can achieve a prominent performance improvement on mean average precision (0.176 on average) compared to the one trained with noisy labels.

23 June 2021 in IEEE Antennas and Wireless Propagation Letters
Verified
Journal Article
Closed access
LPLing Pu
Ling Pu
Xiaoling ZhangXiaoling Zhang
Xiaoling Zhang
JSJun Shi
Jun Shi
BTBokun Tian
Bokun Tian
WWweishunjun Wei
weishunjun Wei
Sparse Bayesian (SB) 3-D imaging resolution transcends classical radar cross section (RCS) imaging, providing a novel solution for low-RCS objects. To better resolve low-RCS objects, we propose an improved SB 3-D imaging algorithm via dyadic Green's function, i.e., 1) in the building of the radar observation model, a novel dyadic Green's function-form dictionary (DGFD) is designed to replace traditional scalar form, contributing to resolving low-RCS objects; 2) in the implementation of 3-D imaging, an improved SB algorithm using DGFD is proposed, further ensuring high precision. Electromagnetic simulation results show the precision of the proposed algorithm is less than 1 dB in mean absolute deviation and less than 1.5 dB in standard deviation, better than existing algorithms.

26 October 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
LLLiang Li
Liang Li
Xiaoling ZhangXiaoling Zhang
Xiaoling Zhang
BTBokun Tian
Bokun Tian
CWChen Wang
Chen Wang
Liming PuLiming Pu
Liming Pu
WWweishunjun Wei
weishunjun Wei
Most of the existing image segmentation methods have a strong anti-noise ability but are susceptible to the interference in the background, so they are not suitable for 3-D synthetic aperture radar (SAR) image target extraction. Region of interest (ROI) extraction can improve the anti-interference ability of the image segmentation methods. However, the existing ROI extraction method uses the same threshold to process all the images in the data set. This threshold is not optimal for each image. Designed for 3-D SAR image target extraction, we propose an ROI extraction algorithm with adaptive threshold (REAT) to enhance the anti-interference ability of the existing image segmentation methods. The required thresholds in the proposed algorithm are adaptively obtained by the mapping of the image features. Moreover, the proposed algorithm can easily be applied to existing image segmentation methods. The experiments demonstrate that the proposed algorithm significantly enhances the anti-interference ability and computational efficiency of the image segmentation methods. Compared with the existing ROI extraction algorithm, the proposed algorithm improves the dice similarity coefficient by 6.4%.