Article
Geochemistry & Geophysics
Bin Xiong, Xinhan Huang, Min Wang
Summary: In order to overcome the drawbacks of conventional methods for detecting infrared small targets, a novel approach based on local gradient field feature contrast measure (LGFFCM) is proposed. The experimental results indicate that this approach outperforms other advanced methods in reducing false alarm probability and enhancing detection rate effectively and stably.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Geochemistry & Geophysics
In Ho Lee, Chan Gook Park
Summary: In this paper, a fast and robust single-frame infrared small target detection algorithm is proposed. It enhances the detection accuracy and speed by augmenting the infrared intensity map and employing density-based clustering.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Yifan He, Chunmin Zhang, Tingkui Mu, Tingyu Yan, Yanqiang Wang, Zeyu Chen
Summary: The study introduces a multiscale local gray dynamic range (MLGDR) method to enhance target and suppress background clutter. Experimental results demonstrate that the method achieves a high signal-to-noise ratio, high detection rate, and low false-alarm rate in various scenes compared to baseline methods.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Optics
Long Ren, Zhibin Pan, Yue Ni
Summary: This paper proposes a small target detection algorithm based on weighted double layer local contrast and multi-directional gradient map, which effectively reduces the false alarm rate in complex scenes, improves computational efficiency, and demonstrates good robustness.
Article
Geochemistry & Geophysics
Zhaobing Qiu, Yong Ma, Fan Fan, Jun Huang, Lang Wu
Summary: In this study, a novel method for infrared small target detection called Global Sparsity-Weighted Local Contrast Measure (GSWLCM) is proposed. This method combines global and local features, effectively suppressing high-contrast background interference and achieving better detection performance compared to existing methods.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Environmental Sciences
Yahui Wang, Yan Tian, Jijun Liu, Yiping Xu
Summary: This paper proposes a multi-stage, multi-scale local feature fusion method for the detection of small infrared targets. The experimental results demonstrate that this method effectively improves the performance of infrared small target detection.
Article
Environmental Sciences
Siying Cao, Jiakun Deng, Junhai Luo, Zhi Li, Junsong Hu, Zhenming Peng
Summary: This study proposes a robust scheme for automatically detecting infrared small targets, which improves the accuracy of detecting dim and small targets in complex scenes. It has competitive performance with state-of-the-art algorithms and low time consumption, making it beneficial for practical applications.
Article
Geochemistry & Geophysics
Jinhui Han, Qiuyue Xu, Saed Moradi, Houzhang Fang, Xuye Yuan, Zhimeng Qi, Jinyao Wan
Summary: This letter proposes a ratio-difference local feature contrast (LFC) method for effective infrared small target detection. The method utilizes a new nested window design and selects local gray contrast as the features to investigate the characteristics of a local area. The proposed algorithm achieves better performance in terms of detection rate and false alarm rate and has good robustness against noise.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Erwei Zhao, Wei Zheng, Mingtao Li, Haibin Sun, Jianfeng Wang
Summary: This study proposes a new method for detecting small targets in complex backgrounds using local uncertainty measurements. The method uses a multilayer nested sliding window and a local component uncertainty measure algorithm to suppress complex backgrounds and enhances the target signal through energy weighting. Experimental results demonstrate that the method performs well in detecting small targets in complex backgrounds.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Environmental Sciences
Jiping Yao, Shanzhu Xiao, Qiuqun Deng, Gongjian Wen, Huamin Tao, Jinming Du
Summary: This study proposes a multidimensional information fusion network (MIFNet) for infrared small target detection. By calculating semantic information and fusing it with detailed information and edge information, the network achieves more accurate target position detection, improving the accuracy and reliability of detection.
Article
Geochemistry & Geophysics
Lang Wu, Yong Ma, Fan Fan, Minghui Wu, Jun Huang
Summary: The letter introduces a double-neighborhood gradient method (DNGM) for effective and efficient infrared small target detection, which utilizes a tri-layer sliding window technique to measure double-neighborhood gradient. Experimental results show that the proposed method can accurately detect multiple targets close to each other and is more robust and real-time compared to traditional methods.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Engineering, Electrical & Electronic
Yongsong Li, Zhengzhou Li, Weite Li, Yuchuan Liu
Summary: This article presents a robust target detection algorithm based on gradient-intensity, joint saliency measure (GISM) to gradually eliminate complex background clutter. The proposed method effectively identifies real target signals and eliminates false alarms by integrating gradient and intensity properties.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Yimian Dai, Yiquan Wu, Fei Zhou, Kobus Barnard
Summary: In this paper, a novel model-driven deep network is proposed for infrared small target detection, which combines discriminative networks and conventional model-driven methods. By designing a feature map cyclic shift scheme and incorporating bottom-up attentional modulation, the network is able to encode long-range contextual interactions and preserve small target features effectively. Experimental results demonstrate that the proposed network outperforms other model-driven methods and deep networks, showing a performance boost in small target detection.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Geochemistry & Geophysics
Won Young Chung, In Ho Lee, Chan Gook Park
Summary: To improve detection performance in a U-net-based IR small target detection algorithm, feature fusion of low- and high-level features is crucial. Unlike conventional algorithms that add a convolution layer to the skip pathway of the U-net, we propose a UNet3+-based full-scale skip connection U-net that lowers computational cost by fusing features with fewer parameters. An effective encoder and decoder structure, along with residual attention blocks, are used for improved feature extraction and fusion. The proposed algorithm, AMFU-net, guarantees effective target detection performance and a lightweight structure (mIoU: 0.7512, FPS: 86.1). The Pytorch implementation is available at github.com/cwon789/AMFU-net.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Geochemistry & Geophysics
Tianlei Ma, Zhen Yang, Benxue Liu, Siyuan Sun
Summary: In order to address the slow detection speed and poor robustness of existing infrared small target detection methods in complex environments, this letter proposes a lightweight detection model called MiniIR-net. The proposed MiniIR-net model improves the feature expression of the target by introducing a multiscale target context feature extraction (TCVE) module and enhances the feature mapping capability by designing a feature mapping upsampling network. Experimental results show that the MiniIR-net network outperforms existing detection methods in terms of detection speed, accuracy, and robustness in complex environments. The model size of MiniIR-net is at least 1/260 of the current detection model, and the detection accuracy is improved by at least 5%. The source code of this article can be obtained at https://github.com/yangzhen1252/MiniIR-net.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Computer Science, Artificial Intelligence
Zhuliang Le, Jun Huang, Han Xu, Fan Fan, Yong Ma, Xiaoguang Mei, Jiayi Ma
Summary: This paper introduces a novel unsupervised continual-learning generative adversarial network (UIFGAN) for unified image fusion, by training a single model through adversarial learning rather than multiple independent models. Experimental results demonstrate the superiority of this method over existing techniques.
INFORMATION FUSION
(2022)
Article
Automation & Control Systems
Jiayi Ma, Linfeng Tang, Fan Fan, Jun Huang, Xiaoguang Mei, Yong Ma
Summary: This study proposes a novel image fusion framework called SwinFusion, which combines cross-domain long-range learning and Swin Transformer. The framework integrates complementary information and achieves global interaction through attention-guided cross-domain modules. It also addresses multi-scene image fusion problems by preserving structure, detail, and intensity. Extensive experiments prove the superiority of SwinFusion compared to other state-of-the-art fusion algorithms. The implementation code and pre-trained weights are available at https://github.com/Linfeng-Tang/SwinFusion.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2022)
Article
Automation & Control Systems
Jiayi Ma, Wenjing Gao, Yong Ma, Jun Huang, Fan Fan
Summary: In this article, an array thermal camera equipment is developed to capture multiple infrared images with spatial and parallax information. Based on these images, a spatial-parallax prior network (SPPN) method is proposed, which effectively integrates spatial and parallax features using a channel attention mechanism. The experimental results demonstrate that SPPN outperforms current state-of-the-art methods, providing a highly effective and scalable solution for improving infrared image quality.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Environmental Sciences
Yujie Zhang, Xiaoguang Mei, Yong Ma, Xingyu Jiang, Zongyi Peng, Jun Huang
Summary: In this study, a new stitching strategy is proposed for hyperspectral image stitching. By selecting a reference band, enhancing the reliability of feature correspondences, performing adaptive bundle adjustment, and implementing spectral correction, high-precision hyperspectral panoramas with less distortion are generated.
Letter
Automation & Control Systems
Erting Pan, Yong Ma, Xiaoguang Mei, Jun Huang, Fan Fan, Jiayi Ma
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2023)
Article
Computer Science, Artificial Intelligence
Mingfan Chu, Yong Ma, Xiaoguang Mei, Jun Huang, Fan Fan
Summary: This paper proposes a novel framework called SAH-Net, which uses an end-to-end network to remove outliers and recover camera pose. SAH-Net has a hierarchical multi-scale structure that utilizes correspondence and clustering to learn the structural information of the scene. Extensive experiments demonstrate the excellence of SAH-Net in mismatch removal and relative pose estimation.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Qiwen Jin, Yong Ma, Fan Fan, Jun Huang, Xiaoguang Mei, Jiayi Ma
Summary: This article proposes an unsupervised unmixing technique based on the adversarial autoencoder network (AAENet) for hyperspectral image analysis. By partitioning the image into homogeneous regions and considering the spatial correlation between local pixels, the proposed method improves the performance and robustness of unmixing, and experiments show that it outperforms other state-of-the-art methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Erting Pan, Yong Ma, Xiaoguang Mei, Jun Huang, Qihai Chen, Jiayi Ma
Summary: In this article, a novel approach for denoising and destriping HSI is proposed. By decomposing the task into auxiliary sub-tasks, the shortcomings of the generalized mathematical model are addressed, leading to accurate destriping and high-fidelity restoration.
PATTERN RECOGNITION
(2023)
Article
Geochemistry & Geophysics
Erting Pan, Yong Ma, Xiaoguang Mei, Fan Fan, Jun Huang, Jiayi Ma
Summary: This study proposes a progressive hyperspectral destriping method with an adaptive frequency focus for accurate destriping and delicate restoration. The method encodes the degraded input to the frequency domain with smaller scales and separates noise and preserves details in the high-frequency domain. The experimental results demonstrate the superiority of the proposed method over the current state-of-the-art methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Wendi Liu, Xiaoguang Mei, Yong Ma, Jun Huang, Qihai Chen, Hao Li
Summary: In this letter, a new hyperspectral unmixing algorithm based on graph Laplacian regularization and l(1)-norm-Gaussian mixture model is proposed. The algorithm effectively addresses the issues of fixed endmembers and underutilized spatial characteristics of the hyperspectral image. Experimental results demonstrate its superiority over other state-of-the-art methods.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Geochemistry & Geophysics
Zhaobing Qiu, Yong Ma, Fan Fan, Jun Huang, Lang Wu, You Du
Summary: With the advancement of modern weapons, such as UAV swarms and multiwarhead missiles, the detection of infrared cluster small targets has become increasingly important. However, existing methods suffer from poor detection performance due to the difficulty in characterizing cluster multitargets. This letter proposes an improved DBSCAN (IDBSCAN) and an IDBSCAN-DM-based approach to accurately extract the features of cluster multitargets with unknown numbers and distribution, leading to better target enhancement and background suppression.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Geochemistry & Geophysics
Yucheng Sun, Han Xu, Yong Ma, Minghui Wu, Xiaoguang Mei, Jun Huang, Jiayi Ma
Summary: In this article, we present a network called DSPNet for fusing multispectral and hyperspectral images. DSPNet utilizes the spectral pyramid module and multiscale local spectral information fusion module to accurately extract spectral information. Additionally, the spatial pyramid module enables DSPNet to extract nonlocal spatial information at different scales. Experimental results demonstrate the superiority of our method over existing methods in terms of both qualitative and quantitative evaluations.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Remote Sensing
Yang Yu, Yong Ma, Xiaoguang Mei, Jun Huang, Hao Li, Fan Fan
Summary: Hyperspectral unmixing is a critical task in various hyperspectral image applications. The autoencoder unmixing network has shown superior performance in terms of data fitting and feature acquisition. However, it fails to consider the overall distribution and long-range dependencies of materials. In this study, we propose a multi-stage convolutional autoencoder network (MSNet) that can learn broad contextual information while preserving detailed features in the unmixing process.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2022)
Article
Geochemistry & Geophysics
Zhaobing Qiu, Yong Ma, Fan Fan, Jun Huang, Lang Wu
Summary: In this study, a novel method for infrared small target detection called Global Sparsity-Weighted Local Contrast Measure (GSWLCM) is proposed. This method combines global and local features, effectively suppressing high-contrast background interference and achieving better detection performance compared to existing methods.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Engineering, Multidisciplinary
Zhao-bing Qiu, Yong Ma, Fan Fan, Jun Huang, Ming-hui Wu, Xiao-guang Mei
Summary: In this paper, a pixel-level local contrast measure (PLLCM) method is proposed to subdivide small targets and backgrounds at pixel level simultaneously, which helps to improve detection performance. Experimental results show that the method has a higher detection rate and a lower false alarm rate.
DEFENCE TECHNOLOGY
(2022)
Article
Instruments & Instrumentation
Zengrun Wen, Xiulin Fan, Kaile Wang, Weiming Wang, Song Gao, Wenjing Hao, Yuanmei Gao, Yangjian Cai, Liren Zheng
Summary: This study presents a transition from Q-switched state to continuous wave state in an erbium-doped fiber laser, accompanied by irregular mode-hopping. The results showed that the transition between these two states can be achieved by adjusting the pump power. Modulation peaks were observed on both the Q-switched pulse train and the continuous wave background, and the central wavelength fluctuated.
INFRARED PHYSICS & TECHNOLOGY
(2024)