Yanxi Lu

Yanxi Lu


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
1 March 2019 in IET Radar, Sonar & Navigation
Verified
Journal Article
Open access
PDF file
YLYanxi Lu
Yanxi Lu
CHChunlin Han
Chunlin Han
ZHZishu He
Zishu He
SLShuangli Liu
Shuangli Liu
YWYikai Wang
Yikai Wang
In this study, the authors present a distributed resource‐awareness colocated multiple‐input–multiple‐output radar network for multiple targets tracking. Specifically, taking posterior Cramér–Rao lower bound as the performance metric, they propose a joint scheduling and power allocation (JSPA) scheme as a sparse optimisation problem. The sparsity of the solution enables the JSPA scheme to jointly optimise the schedule and corresponding transmit power of radars by the non‐zero entries with associated amplitudes. The JSPA scheme has the robustness of feasibility even if there is not enough resource to achieve the prescribed performance requirements of targets. In this case, the JSPA scheme will automatically relax the performance bounds for individual targets at the lowest price and decide the number of targets to be tracked according to the priorities. They also propose a global optimal fusion rule that builds the connection between resource allocation and distributed tracking. Simulation results demonstrate the effectiveness of the proposed methods. The JSPA scheme can dynamically adjust the resource utilisation of the tracking of individual targets according to the accuracy demands. The performance of important targets is favoured to be satisfied, whereas a target with low priority may be dropped by the JSPA scheme if necessary.

21 January 2020 in IET Radar, Sonar & Navigation
Verified
Journal Article
Open access
PDF file
YLYanxi Lu
Yanxi Lu
ZHZishu He
Zishu He
SLShuangli Liu
Shuangli Liu
GSGuoHao Sun
GuoHao Sun
The coexistence of radar and communication system is a crucial task owing to the shortage of spectrum resources. In this study, the authors consider a multiple manoeuvring targets tracking problem via a radar network in the presence of several non‐cooperative, spatially random, and spectral overlapped communication areas (CAs). Instead of costly inner pattern optimisation, a communication awareness joint beam and power allocation (CJBPA) scheme of radar network is proposed to achieve high flexibility in coexistence. In CJBPA, radars and CAs treat the signals from each other as interference, which are formulated and discussed from the perspective of spectrum and space. The CJBPA optimises the overall tracking performance, which is characterised by the posterior Cramer‐Rao lower bound under the consideration of coexistence. The resultant non‐convex problem is relaxed and decoupled as an integrated two‐staged optimisation. To accelerate the numerical procedures of the optimisations, custom‐built primal dual interior point methods are derived by the structure information of the problems. The effectiveness of the proposed CJBPA scheme is assessed through simulations, showing that by using spatial and spectral information of undesired signals, the tracking performance can be optimised while the impacts of interference on both radars and CAs are restricted.

13 August 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YLYanxi Lu
Yanxi Lu
ASAnna Song
Anna Song
GLGaozheng Liu
Gaozheng Liu
LTLonglong Tan
Longlong Tan
YXYushi Xu
Yushi Xu
LYLei Yang
Lei Yang
Airborne aircrafts are dependent on the Global Navigation Satellite System (GNSS), which is susceptible to interference due to the satellite base-station and cooperative communication. Synthetic aperture radar altimeter (SARAL) provides the ability to measure the topographic terrain for matching with Digital Elevation Model (DEM) to achieve positioning without relying on GNSS. However, due to the near-vertical coupling in the delay-Doppler map (DDM), the similarity of DDMs of adjacent apertures is high, and the probability of successful matching is low. To this end, a novel neural network of terrain matching and aircraft positioning is proposed based on the airborne SARAL imagery. The model-driven terrain matching and aircraft positioning network (TMP-Net) is capable of realizing aircraft positioning by utilizing the real-time DDMs to match with the DEM-based DDM references, which are generated by a point-by-point coupling mechanism between the airborne routine and ground terrain DEM. Specifically, the training dataset is established by a numerical simulation method based on a semi-analytical model. Therefore, DEM-based DDM references can be generated by forward deduction when only regional DEM can be obtained. In addition to the model-based DDM generation, feature extraction, and similarity measurement, an aircraft positioning module is added. Three different positioning methods are designed to achieve the aircraft positioning, where three-point weighting exhibits the best performance in terms of positioning accuracy. Due to the fact that both the weighted triplet loss and softmax loss are employed in a cooperative manner, the matching accuracy can be improved and the positioning error can be reduced. Finally, both simulated and measured airborne datasets are used to validate the effectiveness of the proposed algorithm. Quantitative and qualitative evaluations show the superiority.

17 November 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
MDMengmeng Duan
Mengmeng Duan
YLYanxi Lu
Yanxi Lu
YWYao Wang
Yao Wang
GLGaozheng Liu
Gaozheng Liu
LTLonglong Tan
Longlong Tan
GJGe Jiang
Ge Jiang
Due to the lack of accurate labels for the airborne synthetic aperture radar altimeter (SARAL), the use of deep learning methods is limited for estimating the above ground level (AGL) of complicated landforms. In addition, the inherent additive and speckle noise definitely influences the intended delay/Doppler map (DDM); accurate AGL estimation becomes more challenging when using the feature extraction approach. In this paper, a generalized AGL estimation algorithm is proposed, based on a fully supervised altimetry enhancement network (FuSAE-net), where accurate labels are generated by a novel semi-analytical model. In such a case, there is no need to have a fully analytical DDM model, and accurate labels are achieved without additive noises and speckles. Therefore, deep learning supervision is easy and accurate. Next, to further decrease the computational complexity for various landforms on the airborne platform, the network architecture is designed in a lightweight manner. Knowledge distillation has proven to be an effective and intuitive lightweight paradigm. To significantly improve the performance of the compact student network, both the encoder and decoder of the teacher network are utilized during knowledge distillation under the supervision of labels. In the experiments, airborne raw radar altimeter data were applied to examine the performance of the proposed algorithm. Comparisons with conventional methods in terms of both qualitative and quantitative aspects demonstrate the superiority of the proposed algorithm.

18 March 2026 in Sensors
Verified
Journal Article
Open access
PDF file
DXDong Xia
Dong Xia
LLLiming Lv
Liming Lv
YZYoujian Zhang
Youjian Zhang
YLYanxi Lu
Yanxi Lu
FLFang Li
Fang Li
ZGZhan Ge
Zhan Ge
Rapid and accurate recognition of radar active jamming is a prerequisite for cognitive electronic countermeasures. However, under complex electromagnetic environments with scarce training samples, existing deep learning models are prone to capturing spurious correlations induced by environmental confounders, resulting in notable performance degradation. To address this causal confounding issue, we propose a physics-guided variational causal intervention network (PG-VCIN). First, we reconstruct a structured causal model of jamming signal generation, decoupling observations into robust physical statistical features and sensitive time–frequency image representations. Physical priors are then leveraged to perform dynamic precision-weighted modulation of visual feature extraction, enforcing physical consistency at the representation learning stage. Second, we formulate deconfounding within an active inference framework and introduce a variational information bottleneck to optimize mutual information, thereby filtering out high-complexity redundant information attributable to confounders while preserving the essential causal semantics. Finally, we numerically approximate the causal effect by imposing dual intervention constraints in the latent space, including intra-class invariance and confounder invariance. Experiments on a semi-physical simulation dataset demonstrate that the proposed method achieves substantially higher recognition accuracy than several representative few-shot baselines in extremely low-sample regimes, validating the effectiveness of integrating physical mechanisms with causal inference.