A novel two-stage scene classification model based on feature variable significance in high-resolution remote sensing

Zhao, Feng’an; Mu, Xiaodong; Yang, Zhou; Yi, Zhaoxiang

doi:10.1080/10106049.2019.1583772

Cited by 16 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One category is unsupervised feature-learning-based methods. In [21], a variable-weighted multi-feature fusion (VWMF) classification method based on kernel collaborative representation-based classification (KCRC) and the support vector machine (SVM) was proposed to solve the problems of high within-class differences and between-class similarities of remote sensing scene images.…”

Section: Performance Comparison With the State-of-the-art Methodsmentioning

confidence: 99%

“…CNN is one of the most representative neural networks in deep learning technology. In the field of remote sensing, CNN is applied in many applications, especially in target detection [15][16], semantic annotation [65], high-resolution image classification [17][18], hyperspectral image classification [19][20]66], and remote sensing scene classification [21][22][23][24]. Various methods based on CNN have shown excellent performance in the field of remote sensing, mainly as a deep neural network can extract better image representation features, for example VGG16 [25], AlexNet [26], MobileNet [27], and other network models [41][42].…”

Section: Related Workmentioning

confidence: 99%

“…In Table V, compared with the methods in [58], [21], [63], and [48], the proposed method had better classification performance. In terms of the OA, the proposed method was 7.46%, 5.54%, 2.27%, 0.78%, and 0.74% higher than the methods in [61], [21], [63], and the two methods in reference [48], respectively. In terms of the weight parameters, the total parameters of the proposed method only accounted for 4.48% of the method in [61] and 26.09% of the two methods in [48].…”

mentioning

confidence: 96%

“…The results of the OA and parameters of the proposed method and the state-of-the-art methods are listed in Table V. In Table V, compared with the methods in [58], [21], [63], and [48], the proposed method had better classification performance. In terms of the OA, the proposed method was 7.46%, 5.54%, 2.27%, 0.78%, and 0.74% higher than the methods in [61], [21], [63], and the two methods in reference [48], respectively.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Branch Feature Fusion Convolution Network for Remote Sensing Scene Classification

Shi

Wang

2020

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

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have outstanding advantages in the classification of remote sensing scenes. Deep CNN models with better classification performance typically have high complexity, while shallow CNN models with low complexity rarely achieve good classification performance for remote sensing images with complex spatial structures. In this paper, we proposed a new lightweight CNN classification method based on branch feature fusion (LCNN-BFF) for remote sensing scene classification. In contrast to a conventional single linear convolution structure, the proposed model had a bilinear feature extraction structure. The branch feature fusion (BFF) method was utilized to fuse the feature information extracted from the two branches, which improved the classification accuracy. In addition, combining depthwise separable convolution (DSC) and conventional convolution (CConv) to extract image features greatly reduced the complexity of the model on the premise of ensuring the accuracy of classification. We tested the method on four standard data sets. The experimental results showed that, compared with recent classification methods, the number of weight parameters of the proposed method only accounted for less than 5% of the other methods; however, the classification accuracy was equivalent to or even superior to certain high-performance classification methods. The python code for the paper can be downloaded from here: https://github.com/scp19801980/Remote-sensing-scene-classificati on.

show abstract

Section: Performance Comparison With the State-of-the-art Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 96%

mentioning

confidence: 99%

See 2 more Smart Citations

Branch Feature Fusion Convolution Network for Remote Sensing Scene Classification

Shi

Wang

2020

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

View full text Add to dashboard Cite

show abstract

“…However, it is still not a good solution to the problem of large intra-class differences and high inter-class similarity of remote sensing scene images. Then, Chaib [18], G. Cheng [19], and F. Zhao [20] proposed the discriminant correlation analysis (DCA) feature fusion method, the discriminative CNNs (D-CNNs) model, and variable-weighted multi-feature fusing (VWMF) model to solve these problems. However, in the D-CNN method of VGG16, the parameters of this method reached 130MB, which not only consumes a lot of training time, but also requires a high performance of computing environment.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Branch Feature Fusion Strategy Based on an Attention Mechanism for Remote Sensing Image Scene Classification

2021

View full text Add to dashboard Cite

In recent years, with the rapid development of computer vision, increasing attention has been paid to remote sensing image scene classification. To improve the classification performance, many studies have increased the depth of convolutional neural networks (CNNs) and expanded the width of the network to extract more deep features, thereby increasing the complexity of the model. To solve this problem, in this paper, we propose a lightweight convolutional neural network based on attention-oriented multi-branch feature fusion (AMB-CNN) for remote sensing image scene classification. Firstly, we propose two convolution combination modules for feature extraction, through which the deep features of images can be fully extracted with multi convolution cooperation. Then, the weights of the feature are calculated, and the extracted deep features are sent to the attention mechanism for further feature extraction. Next, all of the extracted features are fused by multiple branches. Finally, depth separable convolution and asymmetric convolution are implemented to greatly reduce the number of parameters. The experimental results show that, compared with some state-of-the-art methods, the proposed method still has a great advantage in classification accuracy with very few parameters.

show abstract

Region-based adaptive association learning for robust image scene recognition

Dong

Zhang

et al. 2022

Vis Comput

View full text Add to dashboard Cite

A novel two-stage scene classification model based on feature variable significance in high-resolution remote sensing

Cited by 16 publications

References 20 publications

Branch Feature Fusion Convolution Network for Remote Sensing Scene Classification

Branch Feature Fusion Convolution Network for Remote Sensing Scene Classification

A Multi-Branch Feature Fusion Strategy Based on an Attention Mechanism for Remote Sensing Image Scene Classification

Region-based adaptive association learning for robust image scene recognition

Contact Info

Product

Resources

About