Small Aerial Target Detection for Airborne Infrared Detection Systems Using LightGBM and Trajectory Constraints

Sun, Xiaoliang; Guo, Liangchao; Zhang, Wenlong; Wang, Zi; Yu, Qifeng

doi:10.1109/jstars.2021.3115637

Cited by 32 publications

(10 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to assess the effectiveness of the proposed algorithm, the study employed a variety of classification algorithms for comparison. The baseline algorithms included traditional machine learning techniques like SVM [35], RF [35], CRC, and ProCRC [36] , while more advanced ensemble methods, such as GBDT [37] and LightGBM [38], [39] ], were also considered. Additionally, the paper utilized the META-DES [40]- [42]algorithm as an advanced comparative approach.…”

Section: B Experiments Setupmentioning

confidence: 99%

A Novel Semi-Supervised Dynamic Classifier Selection Method for HSI Classification Based on SP Segmentation

Ge,

Yu,

Yang

2023

IEEE Access

View full text Add to dashboard Cite

This paper proposes a novel hyperspectral image classification method that combines dynamic semi-supervised multiple-kernel collaborative representation ensemble selection with superpixel (SP) consistency constraints. The method is based on the consistency principle of labels within SP blocks, where the hyperspectral image is divided into different SP blocks, and each block is treated as an independent classification task. It applies a dynamic ensemble selection strategy to select high-confidence samples from the unlabeled data and assigns pseudo-labels to expand the available training sample set. Additionally, it employs a multiple-kernel collaborative representation classifier as the base classifier to better capture sample similarities and correlations, thereby improving the classification performance. Experimental results demonstrate that the proposed method achieves superior classification accuracy on various datasets such as Indian Pines, Purdue, and KSC, outperforming the traditional Meta-DES method significantly.

show abstract

Section: B Experiments Setupmentioning

confidence: 99%

A Novel Semi-Supervised Dynamic Classifier Selection Method for HSI Classification Based on SP Segmentation

Ge,

Yu,

Yang

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The light gradient boosting machine (LGBM) [48] is widely used in the field of remote sensing, and research has proved that the LGBM has obvious advantages in computational speed and accuracy compared with other similar algorithms [49,50]. Given the advantages of machine learning in nonlinear mapping, we used the LGBM regression model to obtain the weights of each impact factor by nonlinearly fitting the bias pairs.…”

Section: Nonlinear Fitting Of Image Bias Pairsmentioning

confidence: 99%

A Sensor Bias Correction Method for Reducing the Uncertainty in the Spatiotemporal Fusion of Remote Sensing Images

Zhang¹,

Huang²,

Hong³

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

With the development of multisource satellite platforms and the deepening of remote sensing applications, the growing demand for high-spatial resolution and high-temporal resolution remote sensing images has aroused extensive interest in spatiotemporal fusion research. However, reducing the uncertainty of fusion results caused by sensor inconsistencies and input data preprocessing is one of the challenges in spatiotemporal fusion algorithms. Here, we propose a novel sensor bias correction method to correct the input data of the spatiotemporal fusion model through a machine learning technique learning the bias between different sensors. Taking the normalized difference vegetation index (NDVI) images with low-spatial resolution (MODIS) and high-spatial resolution (Landsat) as the basic data, we generated the neighborhood gray matrices from the MODIS image and established the image bias pairs of MODIS and Landsat. The light gradient boosting machine (LGBM) regression model was used for the nonlinear fitting of the bias pairs to correct MODIS NDVI images. For three different landscape areas with various spatial heterogeneities, the fusion of the bias-corrected MODIS NDVI and Landsat NDVI was conducted by using the spatiotemporal adaptive reflection fusion model (STARFM) and the flexible spatiotemporal data fusion method (FSDAF), respectively. The results show that the sensor bias correction method can enhance the spatially detailed information in the input data, significantly improve the accuracy and robustness of the spatiotemporal fusion technology, and extend the applicability of the spatiotemporal fusion models.

show abstract

“…For example, the classic machine learning algorithms support vector (SVM) random forest (RF) are the baselines. Moreover, the advanced ensemble algorithm GBDT, Catboost [50], LightGBM [51], and XGboost [52] are also used as a comparison algorithm. In addition, the two state-of-the-art DES algorithms, namely DES-MI and META-DES algorithm are used as comparative algorithms in the paper.…”

Section: A Experiments Setupmentioning

confidence: 99%

Weighted Residual Dynamic Ensemble Learning for Hyperspectral Image Classification

Lü

Pan

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Recently, collaborative representation classifiers have been extensively studied as an essential method for hyperspectral image. However, how to comprehensively utilize the classification advantages of multiple collaborative classifiers has not been well investigated. In this paper, two new dynamic ensemble learning methods using local weighted residual (LWR-DEL) and double-weighted residual (DWR-DEL) of multicollaborative representation classifiers are proposed. First, the dynamic ensemble learning method based on clustering is utilized to introduce prior knowledge for the collaborative representation classifier. Then, with prior knowledge, the local weights of each classifier for a different region of competence are obtained. To consider the global information of hyperspectral data, the Knearest neighbor (K-NN) algorithm is adopted to achieve validation samples with global information. The global weights for each classifier can be obtained and then used to constrain the locally weighted residuals. Similar to LWR-DEL, the global information is also used to constrain residual, and then doubleweighted constrained residual fusion obtains the final classifier result. The effectiveness of the proposed methods is validated using three hyperspectral data sets. The experimental results show that both LWR-DEL and DWR-DEL outperform their single-classifier counterparts. In particular, the proposed methods provide superior performance compared with the stateof-the-art methods.

show abstract

Small Aerial Target Detection for Airborne Infrared Detection Systems Using LightGBM and Trajectory Constraints

Cited by 32 publications

References 46 publications

A Novel Semi-Supervised Dynamic Classifier Selection Method for HSI Classification Based on SP Segmentation

A Novel Semi-Supervised Dynamic Classifier Selection Method for HSI Classification Based on SP Segmentation

A Sensor Bias Correction Method for Reducing the Uncertainty in the Spatiotemporal Fusion of Remote Sensing Images

Weighted Residual Dynamic Ensemble Learning for Hyperspectral Image Classification

Contact Info

Product

Resources

About