Lei Min

Lei Min


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
28 July 2023 in Sensors
Verified
Journal Article
Open access
PDF file
FXFan Xiangsuo
Fan Xiangsuo
WDWentao Ding
Wentao Ding
WQWenlin Qin
Wenlin Qin
DXDachuan Xiao
Dachuan Xiao
LMLei Min
Lei Min
HYHaohao Yuan
Haohao Yuan
Convolutional neural networks have achieved good results in target detection in many application scenarios, but convolutional neural networks still face great challenges when facing scenarios with small target sizes and complex background environments. To solve the problem of low accuracy of infrared weak target detection in complex scenes, and considering the real-time requirements of the detection task, we choose the YOLOv5s target detection algorithm for improvement. We add the Bottleneck Transformer structure and CoordConv to the network to optimize the model parameters and improve the performance of the detection network. Meanwhile, a two-dimensional Gaussian distribution is used to describe the importance of pixel points in the target frame, and the normalized Guassian Wasserstein distance (NWD) is used to measure the similarity between the prediction frame and the true frame to characterize the loss function of weak targets, which will help highlight the targets with flat positional deviation transformation and improve the detection accuracy. Finally, through experimental verification, compared with other mainstream detection algorithms, the improved algorithm in this paper significantly improves the target detection accuracy, with the mAP reaching 96.7 percent, which is 2.2 percentage points higher compared with Yolov5s.

1 April 2022 in IEEE Access
Verified
Journal Article
Open access
AWAnqing Wu
Anqing Wu
FXFan Xiangsuo
Fan Xiangsuo
HCHuajin Chen
Huajin Chen
LMLei Min
Lei Min
ZXZhiyong Xu
Zhiyong Xu
In complex non-smooth backgrounds, infrared dim and small target targets generally have lower energy and occupy fewer pixels, and are easily swamped by clutter. To improve the detection capability of dim and small targets in non-smooth scenes, this paper proposes a new dim and small target detection method combining multidirectional gradient difference regularization principal component decomposition model. The method first establishes a new gradient difference regularization to constrain the low-rank subspaces of different image components, then construct a gradient difference regularization-based principal component decomposition model (GDR-PCD), and finally decomposes the model using the overlapping directional multiplier method to obtain the background impedance. The experimental results show that the method performs better in all six sequential image scenes than the traditional algorithm. Furthermore, the detection results verify the algorithm’s effectiveness in this paper.

8 September 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
FXFan Xiangsuo
Fan Xiangsuo
JLJuliu Li
Juliu Li
HCHuajin Chen
Huajin Chen
LMLei Min
Lei Min
FLFeng Li
Feng Li
In order to effectively improve the dim and small target detection ability of photoelectric detection system to solve the high false rate issue under complex clouds scene in background modeling, a novelty Hessian matrix and F-norm collaborative filtering is proposed in this paper. Considering the influence of edge noise, we propose an improved Hessian matrix background modeling (IHMM) algorithm, where a local saliency function for adaptive representation of the local gradient difference between the target and background region is constructed to suppress the background and preserve the target. Because the target energy is still weak after the background modeling, a new local multi-scale gradient maximum (LMGM) energy-enhancement model is constructed to enhance the target signal, and with the help of LMGM, the target’s energy significant growth and the target’s recognition are clearer. Thus, based on the above preprocessing, using the motion correlation of the target between frames, this paper proposes an innovative collaborative filtering model combining F-norm and Pasteur coefficient (FNPC) to obtain the real target in sequence images. In this paper, we selected six scenes of the target size of 2 × 2 to 3 × 3 and with complex clouds and ground edge contour to finish experimental verification. By comparing with 10 algorithms, the background modeling indicators SSIM, SNR, and IC of the IHMM model are greater than 0.9999, 47.4750 dB, and 12.1008 dB, respectively. In addition, the target energy-enhancement effect of LMGM model reaches 17.9850 dB in six scenes, and when the false alarm rate is 0.01%, the detection rate of the FNPC model reaches 100% in all scenes. It shows that the algorithm proposed in this paper has excellent performance in dim and small target detection.

17 July 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
QZQian Zhao
Qian Zhao
YGYouming Guo
Youming Guo
LMLei Min
Lei Min
CRChanghui Rao
Changhui Rao
Motion alignment is a critical task in satellite video super-resolution. Most existing methods rely on optical flow or deformable convolution for motion alignment. However, these methods perform poorly in handling complex satellite video scenes and diverse moving objects. To address this challenge, we propose an efficient super-resolution method based on a multitemporal difference and dynamic optimization framework. Specifically, we introduce a multilevel temporal difference analysis mechanism to rapidly capture comprehensive motion information. Based on the extracted temporal difference data, we further develop a temporal differences-guided dynamic routing optimization module (T-DROM) to extract multiscale motion information. In addition, we introduce a multiattention enhancement and correction module to refine the long-term temporal difference features from T-DROM and reduce accumulated errors. These enhancements help recover spatial details and improve spatio-temporal consistency. We conducted detailed ablation studies to validate our contributions and compared the proposed method with state-of-the-art video super-resolution approaches. Experimental results show that our method improves video reconstruction quality while achieving an effective balance between performance and efficiency.

25 June 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
FXFan Xiangsuo
Fan Xiangsuo
JLJuliu Li
Juliu Li
LMLei Min
Lei Min
LFLinping Feng
Linping Feng
LYLing Yu
Ling Yu
ZXZhiyong Xu
Zhiyong Xu
It is difficult for traditional algorithms to remove cloud edge contours in multi-cloud scenarios. In order to improve the detection ability of dim and small targets in complex edge contour scenes, this paper proposes a new dim and small target detection algorithm based on local multi-directional gradient information energy perception. Herein, based on the information difference between the target area and the background area in the four direction neighborhood blocks, an energy enhancement model for multi-directional gray aggregation (EMDGA) is constructed to preliminarily enhance the target signal. Subsequently, a local multi-directional gradient reciprocal background suppression model (LMDGR) was constructed to model the background of the image. Furthermore, this paper proposes a multi-directional gradient scale segmentation model (MDGSS) to obtain candidate target points and then combines the proposed multi-frame energy-sensing (MFESD) detection algorithm to extract the true targets from sequence images. Finally, in order to better illustrate the effect of the algorithm proposed in this paper in detecting small targets in a cloudy background, four sequence images are selected for detection. The experimental results show that the proposed algorithm can effectively suppress the edge contour of complex clouds compared with the traditional algorithm. When the false alarm rate Pf is 0.005%, the detection rate Pd is greater than 95%.

18 August 2023 in Sensors
Verified
Journal Article
Open access
PDF file
LMLei Min
Lei Min
AWAnqing Wu
Anqing Wu
FXFan Xiangsuo
Fan Xiangsuo
FLFeng Li
Feng Li
JLJuliu Li
Juliu Li
Methods for detecting small infrared targets in complex scenes are widely utilized across various domains. Traditional methods have drawbacks such as a poor clutter suppression ability and a high number of edge residuals in the detection results in complex scenes. To address these issues, we propose a method based on a joint new norm and self-attention mechanism of low-rank sparse inversion. Firstly, we propose a new tensor nuclear norm based on linear transformation, which globally constrains the low-rank characteristics of the image background and makes full use of the structural information among tensor slices to better approximate the rank of the non-convex tensor, thus achieving effective background suppression. Secondly, we construct a self-attention mechanism in order to constrain the sparse characteristics of the target, which further eliminates any edge residuals in the detection results by transforming the local feature information into a weight matrix to further constrain the target component. Finally, we use the alternating direction multiplier method to decompose the newly reconstructed objective function and introduce a reweighted strategy to accelerate the convergence speed of the model. The average values of the three evaluation metrics, SSIM, BSF, and SNR, for the algorithm proposed in this paper are 0.9997, 467.23, and 11.72, respectively. Meanwhile, the proposed detection method obtains a higher detection rate compared with other algorithms under the same false alarm rate.