Integration of heterogeneous features for remote sensing scene classification

Wang, Xin; Xiong, Xingnan; Chen, Ning; Shi, Aiye; Lv, Guofang

doi:10.1117/1.jrs.12.015023

Cited by 15 publications

(18 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SPM [14], LDA [17], PLSA [61], S-UFL [62], SIFT+BoVW [63], and RF [64] are all high-resolution remote sensing scene classification methods based on middle-level visual features, and their accuracy is mostly lower than that of deep learning methods, let alone the methods of low-level visual features. The method of features integration [65] fuses low-level visual features with middle-level visual features to improve the accuracy of scene classification, but the accuracy is still lower than the method proposed in this paper. Because there is a semantic gap between low-level visual features and scene semantic categories, the scene classification methods based on low-level visual features often fail to achieve good results.…”

Section: The Analysis Of Test Results On the Siri-whu Datasetmentioning

confidence: 89%

See 1 more Smart Citation

Research on Scene Classification Method of High-Resolution Remote Sensing Images Based on RFPNet

et al. 2019

View full text Add to dashboard Cite

One of the challenges in the field of remote sensing is how to automatically identify and classify high-resolution remote sensing images. A number of approaches have been proposed. Among them, the methods based on low-level visual features and middle-level visual features have limitations. Therefore, this paper adopts the method of deep learning to classify scenes of high-resolution remote sensing images to learn semantic information. Most of the existing methods of convolutional neural networks are based on the existing model using transfer learning, while there are relatively few articles about designing of new convolutional neural networks based on the existing high-resolution remote sensing image datasets. In this context, this paper proposes a multi-view scaling strategy, a new convolutional neural network based on residual blocks and fusing strategy of pooling layer maps, and uses optimization methods to make the convolutional neural network named RFPNet more robust. Experiments on two benchmark remote sensing image datasets have been conducted. On the UC Merced dataset, the test accuracy, precision, recall, and F1-score all exceed 93%. On the SIRI-WHU dataset, the test accuracy, precision, recall, and F1-score all exceed 91%. Compared with the existing methods, such as the most traditional methods and some deep learning methods for scene classification of high-resolution remote sensing images, the proposed method has higher accuracy and robustness.

show abstract

Section: The Analysis Of Test Results On the Siri-whu Datasetmentioning

confidence: 89%

“…Traditional methods SPM [14] 77.69±1.01 LDA [17] 60.32±1.20 PLSA [61] 89.60±0.89 S-UFL [62] 74.84 SIFT+BoVW [63] 75.63 RF [64] 89.29 Features integration [65] 88…”

Section: Methods Accuracy (%)mentioning

confidence: 99%

Research on Scene Classification Method of High-Resolution Remote Sensing Images Based on RFPNet

et al. 2019

View full text Add to dashboard Cite

show abstract

“…i κ and i α reveal respectively the -th i basic kernel function and its weight coefficient. A popular kernel, called Gaussian radial basic function (RBF), is employed as the basic kernels in this paper, for it can handle the non-linear mapping between the class labels and features robustly [28]. A RBF is defined as:…”

Section: Multi-kernel Learningmentioning

confidence: 99%

Infrared Target Recognition using Heterogeneous Features with Multi-kernel Transfer Learning

2020

KSII TIIS

View full text Add to dashboard Cite

Infrared pedestrian target recognition is a vital problem of significant interest in computer vision. In this work, a novel infrared pedestrian target recognition method that uses heterogeneous features with multi-kernel transfer learning is proposed. Firstly, to exploit the characteristics of infrared pedestrian targets fully, a novel multi-scale monogenic filtering-based completed local binary pattern descriptor, referred to as MSMF-CLBP, is designed to extract the texture information, and then an improved histogram of oriented gradient-fisher vector descriptor, referred to as HOG-FV, is proposed to extract the shape information. Second, to enrich the semantic content of feature expression, these two heterogeneous features are integrated to get more complete representation for infrared pedestrian targets. Third, to overcome the defects, such as poor generalization, scarcity of tagged infrared samples, distributional and semantic deviations between the training and testing samples, of the state-of-the-art classifiers, an effective multi-kernel transfer learning classifier called MK-TrAdaBoost is designed. Experimental results show that the proposed method outperforms many state-of-the-art recognition approaches for infrared pedestrian targets.

show abstract

“…Good features that have good discriminability for different categories of image scenes can maximize inter-class differences and at the same time, minimize intra-class variations [6]. Many methods have been proposed to extract various features for RS images.…”

Section: Introductionmentioning

confidence: 99%

“…However, how to properly select those features is still one of the main research topics in the areas of pattern recognition and machine learning. As pointed out in [5,6,8,17], rather than adding features with similar attributes, one should combine those with complementary information in order to achieve better classification performance. In addition, the heterogeneous features fusion strategy is another key step to construct the final informative representation for RS image scenes.…”

Section: Introductionmentioning

confidence: 99%

Remote Sensing Scene Classification Using Heterogeneous Feature Extraction and Multi-Level Fusion

Wang

Xiong

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Integration of heterogeneous features for remote sensing scene classification

Cited by 15 publications

References 46 publications

Research on Scene Classification Method of High-Resolution Remote Sensing Images Based on RFPNet

Research on Scene Classification Method of High-Resolution Remote Sensing Images Based on RFPNet

Infrared Target Recognition using Heterogeneous Features with Multi-kernel Transfer Learning

Remote Sensing Scene Classification Using Heterogeneous Feature Extraction and Multi-Level Fusion

Contact Info

Product

Resources

About