Liwu Wen

Dr. Liwu Wen

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
24 March 2020 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
JDJinshan Ding
Jinshan Ding
LWLiwu Wen
Liwu Wen
CZChao Zhong
Chao Zhong
OLOtmar Loffeld
Otmar Loffeld
Video synthetic aperture radar (SAR) has been found to be very valuable for detection and tracking of slow moving targets and for observing changes over short time periods. Shadows produced by target motion in sequential radar images can be used to detect targets themselves. This article presents a framework for shadow-aided moving target detection using deep neural networks (DNNs) in video SAR. The faster region-based convolutional neural network (Faster-RCNN) is first used to detect shadows in a single frame, and then all the detections in each frame are filtered by the improved density-based clustering algorithm to mitigate false alarms. The missing alarm in detection can be suppressed by using the designed bi-directional long-short-term memory (Bi-LSTM) network. The proposed approaches have been tested by both the simulated and the real data, and a comparison to classical processing is given. This article reveals that the DNN techniques are very suitable for video SAR moving target detection.

25 February 2021 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
LWLiwu Wen
Liwu Wen
JDJinshan Ding
Jinshan Ding
OLOtmar Loffeld
Otmar Loffeld
Video synthetic aperture radar (SAR) has shown great potentials in detection and tracking of slow ground moving targets. The classical shadow-aided detection was applied in video SAR, and most recently, the deep learning approach has been developed for shadow-aided moving target detection. This article presents a joint moving target detection approach for video SAR using a dual faster region-based convolutional neural network (Faster R-CNN), which algorithmically combines the shadow detection in the SAR image and the Doppler energy detection in the range-Doppler (RD) spectrum domain, and this new approach can suppress false alarm sufficiently. Video SAR image and its corresponding low resolution RD spectrum are fed into the developed dual Faster R-CNN. A correct detection can be achieved if the shadow of a moving target and its Doppler energy are simultaneously detected by paired region proposals, which are obtained by sharing the region proposals of two independent region proposal networks (RPNs). Therefore, the performance of moving target detection can be significantly improved by using diverse features in different domains. This proposed approach has been verified by both the simulated and real video SAR data. Compared to other classical methods, our approach exhibits a great detection performance in terms of fewer false alarms and acceptable missing alarms.

25 October 2021 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
LWLiwu Wen
Liwu Wen
JDJinshan Ding
Jinshan Ding
ZXZhong Xu
Zhong Xu
Sea-surface small target detection is challenging for maritime radar. Unfortunately, conventional detection methods are often limited to complex marine environment and low signal-to-clutter ratio (SCR). This article presents a multiframe detection approach for sea-surface small target by using deep convolutional neural network. The moving targets can be reconstructed and detected from the sequential range–Doppler (RD) spectra. A two-step detection framework is proposed, where the intraframe and interframe detections are achieved using the differences in features and interframe correlations between the moving target and sea clutter, respectively. The proposed approach has been verified on both the simulated and real sea-surface small targets, which shows better detection performance than the conventional multiframe detection algorithms. Additionally, this approach exhibits acceptable generalization ability.

28 February 2020 in IEEE Sensors Journal
Verified
Journal Article
Closed access
XHXuejun Huang
Xuejun Huang
JDJinshan Ding
Jinshan Ding
DLDongxing Liang
Dongxing Liang
LWLiwu Wen
Liwu Wen
It is challenging to recognize individuals when they move in the radar field of view due to the superimposition of micro-Doppler signatures. This paper presents a multi-person recognition approach by separating micro-Doppler signatures of multiple persons into their individual components. The preliminary separation can be obtained by their range difference in a high resolution radar. A multi-task learning network is designed for both the fine separation of micro-Doppler signatures and the personnel recognition. A frequency modulated continuous waveform (FMCW) radar that operates at 77 GHz for automotive applications is used in experiments. The proposed deep-neural-network-based approach gives a convincing result in the test.

13 August 2021 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
SQSiqi Qin
Siqi Qin
JDJinshan Ding
Jinshan Ding
LWLiwu Wen
Liwu Wen
MJMing Jiang
Ming Jiang
Moving target shadows continuously appear in the sequential images produced by video synthetic aperture radar (SAR), which conducts research on shadow-based detection and tracking of moving targets. This article addresses a typical shadow-based detection and tracking problem of dim high-maneuvering targets in the complex background. Building upon the dynamic programming-based track-before-detect (DP-TBD) algorithm, this article proposes a joint-processing-strategy-based DP-TBD (JP-DP-TBD) algorithm to detect and track multiple high-maneuvering targets in video SAR. Benefiting from both of the location and radial velocity information of the targets in the video SAR image and range-Doppler (RD) spectrum, the JP-DP-TBD algorithm can screen the state candidate region and retain more states that conform to the motion law of the target. Meanwhile, we adopt a dual-frame close-range matching mechanism to complete the automatic initialization of the candidate target state, whose validity has been verified on the real video SAR data. Experimental results on simulated data demonstrate that the proposed algorithm has better detection ability and fewer false alarms in comparison with other TBD algorithms.

27 May 2022 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
LWLiwu Wen
Liwu Wen
JDJinshan Ding
Jinshan Ding
YCYu Cheng
Yu Cheng
ZXZhong Xu
Zhong Xu
Track-Before-Detect (TBD) algorithm has been used to track weak moving target shadow in video synthetic aperture radar (SAR), where strong maneuverability may deteriorate tracking performance. Fortunately, the Doppler characteristic of target can additionally provide velocity guidance for tracking. This article presents ground moving target indication (GMTI) results of the multi-channel video SAR raw data, and a tracking approach is proposed based on the Doppler supervision in an improved dynamic programming-based TBD (DP-TBD) framework that uses a dual-domain merit function. Both the sequential high-resolution SAR images and low-resolution Range-Doppler (RD) spectra are used, and the clutter in RD spectrum is suppressed by using an adaptive displaced phase center antenna (ADPCA) technique. Fine states can be searched in dual-domain through resampling from random expansion in state initialization and transition. The inverse shadow amplitude and Doppler energy of the same potential target are simultaneously integrated to determine whether the target exists. The proposed Dual-DP-TBD can deal with the tracking of a time-varying number of targets in successive measurements. Compared to other TBD algorithms, this approach has fewer missing alarms and false alarms thanks to precise velocity estimation constrained from diverse features both in SAR image and RD spectrum.