High-resolution satellite scene classification using a sparse coding based multiple feature combination

Sheng, Guofeng; Yang, Wen; Xu, Tao; Sun, Hui

doi:10.1080/01431161.2011.608740

Cited by 274 publications

(173 citation statements)

References 25 publications

Supporting

Mentioning

166

Contrasting

Unclassified

Order By: Relevance

“…We randomly select samples of each class for training the SVM classifier and the rest for testing, following the same sampling setting as [5,54] for the two datasets, respectively: 80 training samples per class for the UCM dataset and 30 training samples per class for the WHU-RS dataset. The classification accuracy is measured by A = N c /N t , where N c denotes the number of correctly classified samples in the testing samples and N t denotes the total number of testing samples.…”

Section: Airportmentioning

confidence: 99%

Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery

et al. 2015

View full text Add to dashboard Cite

Abstract:Learning efficient image representations is at the core of the scene classification task of remote sensing imagery. The existing methods for solving the scene classification task, based on either feature coding approaches with low-level hand-engineered features or unsupervised feature learning, can only generate mid-level image features with limited representative ability, which essentially prevents them from achieving better performance. Recently, the deep convolutional neural networks (CNNs), which are hierarchical architectures trained on large-scale datasets, have shown astounding performance in object recognition and detection. However, it is still not clear how to use these deep convolutional neural networks for high-resolution remote sensing (HRRS) scene classification. In this paper, we investigate how to transfer features from these successfully pre-trained CNNs for HRRS scene classification. We propose two scenarios for generating image features via extracting CNN features from different layers. In the first scenario, the activation vectors extracted from fully-connected layers are regarded as the final image features; in the second scenario, we extract dense features from the last convolutional layer at multiple scales and then encode the dense features into global image features through commonly used feature coding approaches. Extensive experiments on two public scene classification datasets demonstrate that the image features obtained by the two proposed scenarios, even with a simple linear classifier, can result in remarkable performance and improve the state-of-the-art by a significant margin. The results reveal that the features Remote Sens. 2015, 7 14681 from pre-trained CNNs generalize well to HRRS datasets and are more expressive than the low-and mid-level features. Moreover, we tentatively combine features extracted from different CNN models for better performance.

show abstract

Section: Airportmentioning

confidence: 99%

Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Bag of SIFT [58] 85.5 ± 1.2 LTP-HF [59] 77.6 MS-CLBP [59] 93.4 ± 1.1 Multi-feature Concatenation [58] 90.8 ± 0.7 MTJSLRC [55] 91.74 ± 1.14 SIFT + LTP-HF + Color Histogram [48] 93.6 MS-CLBP + FV [56] 94.32 ± 1.2…”

Section: Methods Accuracy (Mean ± Std)mentioning

confidence: 99%

“…The pre-trained CNN We randomly selected samples of each class for training the linear SVM classifier and the rest for testing. The sampling setting as in [48] are: 80 training samples per class for the UCM dataset and 30 training samples per class for the WHU-RS dataset. These two datasets were divided 50 times, each run with randomly selected training and testing samples, to obtain reliable results.…”

Section: Methodsmentioning

confidence: 99%

A Multiscale Deeply Described Correlatons-Based Model for Land-Use Scene Classification

Yang

Guan

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

Abstract:Research efforts in land-use scene classification is growing alongside the popular use of High-Resolution Satellite (HRS) images. The complex background and multiple land-cover classes or objects, however, make the classification tasks difficult and challenging. This article presents a Multiscale Deeply Described Correlatons (MDDC)-based algorithm which incorporates appearance and spatial information jointly at multiple scales for land-use scene classification to tackle these problems. Specifically, we introduce a convolutional neural network to learn and characterize the dense convolutional descriptors at different scales. The resulting multiscale descriptors are used to generate visual words by a general mapping strategy and produce multiscale correlograms of visual words. Then, an adaptive vector quantization of multiscale correlograms, termed multiscale correlatons, are applied to encode the spatial arrangement of visual words at different scales. Experiments with two publicly available land-use scene datasets demonstrate that our MDDC model is discriminative for efficient representation of land-use scene images, and achieves competitive classification results with state-of-the-art methods.

show abstract

“…An example of each class is shown in Figure 8. The same experimental setup in [30] was used. Here, 30 images are randomly selected per class as training data and the remaining images as testing data.…”

Section: Experimental Data and Setupmentioning

confidence: 99%

Remote Sensing Image Scene Classification Using Multi-Scale Completed Local Binary Patterns and Fisher Vectors

et al. 2016

View full text Add to dashboard Cite

An effective remote sensing image scene classification approach using patch-based multi-scale completed local binary pattern (MS-CLBP) features and a Fisher vector (FV) is proposed. The approach extracts a set of local patch descriptors by partitioning an image and its multi-scale versions into dense patches and using the CLBP descriptor to characterize local rotation invariant texture information. Then, Fisher vector encoding is used to encode the local patch descriptors (i.e., patch-based CLBP features) into a discriminative representation. To improve the discriminative power of feature representation, multiple sets of parameters are used for CLBP to generate multiple FVs that are concatenated as the final representation for an image. A kernel-based extreme learning machine (KELM) is then employed for classification. The proposed method is extensively evaluated on two public benchmark remote sensing image datasets (i.e., the 21-class land-use dataset and the 19-class satellite scene dataset) and leads to superior classification performance (93.00% for the 21-class dataset with an improvement of approximately 3% when compared with the state-of-the-art MS-CLBP and 94.32% for the 19-class dataset with an improvement of approximately 1%).

show abstract

High-resolution satellite scene classification using a sparse coding based multiple feature combination

Cited by 274 publications

References 25 publications

Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery

Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery

A Multiscale Deeply Described Correlatons-Based Model for Land-Use Scene Classification

Remote Sensing Image Scene Classification Using Multi-Scale Completed Local Binary Patterns and Fisher Vectors

Contact Info

Product

Resources

About