Learning High-level Features for Satellite Image Classification With Limited Labeled Samples

Yang, Wen; Yin, Xiaoshuang; Xia, Gui-Song

doi:10.1109/tgrs.2015.2400449

Cited by 128 publications

(62 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The first dataset is an object-based scene: the 21-class UC Merced dataset [55], which was manually generated from large images from the USGS National Map Urban Area Imagery collection for various urban areas around the United States. The pixel resolution of this public domain imagery is approximately 0.30 m. The second dataset contains two large HRS scenes: a large scene of Tongzhou (Scene-TZ) [56] and a large scene near the Tucson airport (Scene-AT) [57], which were both captured by the GeoEye-1 satellite sensor. The GeoEye-1 satellite includes a high-resolution CCD camera, which acquires images with a spatial resolution up to 0.41 m in the panchromatic band and of up to 1.65 m in the multi-spectral band.…”

Section: Resultsmentioning

confidence: 99%

A Color-Texture-Structure Descriptor for High-Resolution Satellite Image Classification

Yang

Xia

et al. 2016

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Scene classification plays an important role in understanding high-resolution satellite (HRS) remotely sensed imagery. For remotely sensed scenes, both color information and texture information provide the discriminative ability in classification tasks. In recent years, substantial performance gains in HRS image classification have been reported in the literature. One branch of research combines multiple complementary features based on various aspects such as texture, color and structure. Two methods are commonly used to combine these features: early fusion and late fusion. In this paper, we propose combining the two methods under a tree of regions and present a new descriptor to encode color, texture and structure features using a hierarchical structure-Color Binary Partition Tree (CBPT), which we call the CTS descriptor. Specifically, we first build the hierarchical representation of HRS imagery using the CBPT. Then we quantize the texture and color features of dense regions. Next, we analyze and extract the co-occurrence patterns of regions based on the hierarchical structure. Finally, we encode local descriptors to obtain the final CTS descriptor and test its discriminative capability using object categorization and scene classification with HRS images. The proposed descriptor contains the spectral, textural and structural information of the HRS imagery and is also robust to changes in illuminant color, scale, orientation and contrast. The experimental results demonstrate that the proposed CTS descriptor achieves competitive classification results compared with state-of-the-art algorithms.

show abstract

Section: Resultsmentioning

confidence: 99%

A Color-Texture-Structure Descriptor for High-Resolution Satellite Image Classification

Yang

Xia

et al. 2016

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Similar to the process of forming , another graph ℎ can be constructed based on activation map , but the weight assigned to the edges is defined as Equation (3). Again, a Markov chain on ℎ is obtained to help obtain the normalization map namely the final saliency map .…”

Section: Saliency Mapmentioning

confidence: 99%

“…The interpretation of such huge amount of RS imagery is a challenging task of significant sense for disaster monitoring, urban planning, traffic controlling and so on [1][2][3][4][5]. RS scene classification, which aims at automatically classifying extracted sub-regions of the scenes into a set of semantic categories, is an effective method for RS image interpreting [6,7].…”

Section: Introductionmentioning

confidence: 99%

Deep Salient Feature Based Anti-Noise Transfer Network for Scene Classification of Remote Sensing Imagery

et al. 2018

View full text Add to dashboard Cite

Abstract:Remote sensing (RS) scene classification is important for RS imagery semantic interpretation. Although tremendous strides have been made in RS scene classification, one of the remaining open challenges is recognizing RS scenes in low quality variance (e.g., various scales and noises). This paper proposes a deep salient feature based anti-noise transfer network (DSFATN) method that effectively enhances and explores the high-level features for RS scene classification in different scales and noise conditions. In DSFATN, a novel discriminative deep salient feature (DSF) is introduced by saliency-guided DSF extraction, which conducts a patch-based visual saliency (PBVS) algorithm using "visual attention" mechanisms to guide pre-trained CNNs for producing the discriminative high-level features. Then, an anti-noise network is proposed to learn and enhance the robust and anti-noise structure information of RS scene by directly propagating the label information to fully-connected layers. A joint loss is used to minimize the anti-noise network by integrating anti-noise constraint and a softmax classification loss. The proposed network architecture can be easily trained with a limited amount of training data. The experiments conducted on three different scale RS scene datasets show that the DSFATN method has achieved excellent performance and great robustness in different scales and noise conditions. It obtains classification accuracy of 98.25%, 98.46%, and 98.80%, respectively, on the UC Merced Land Use Dataset (UCM), the Google image dataset of SIRI-WHU, and the SAT-6 dataset, advancing the state-of-the-art substantially.

show abstract

“…Remote sensing image processing achieves great advances in recent years, from low-level tasks, such as segmentation, to high-level ones, such as classification [1][2][3][4][5][6][7]. However, the task becomes incrementally more difficult as the level of abstraction increases, going from pixels, to objects, and then scenes.…”

Section: Introductionmentioning

confidence: 99%

“…However, the task becomes incrementally more difficult as the level of abstraction increases, going from pixels, to objects, and then scenes. Classifying remote sensing images according to a set of semantic categories is a very challenging problem, because of high intra-class variability and low inter-class distance [5][6][7][8][9]. Different objects may appear at different scales and orientations in a given class, and the same objects may be found in images belonging to different classes.…”

Section: Introductionmentioning

confidence: 99%

Transferring Pre-Trained Deep CNNs for Remote Scene Classification with General Features Learned from Linear PCA Network

et al. 2017

View full text Add to dashboard Cite

Abstract:Deep convolutional neural networks (CNNs) have been widely used to obtain high-level representation in various computer vision tasks. However, in the field of remote sensing, there are not sufficient images to train a useful deep CNN. Instead, we tend to transfer successful pre-trained deep CNNs to remote sensing tasks. In the transferring process, generalization power of features in pre-trained deep CNNs plays the key role. In this paper, we propose two promising architectures to extract general features from pre-trained deep CNNs for remote scene classification. These two architectures suggest two directions for improvement. First, before the pre-trained deep CNNs, we design a linear PCA network (LPCANet) to synthesize spatial information of remote sensing images in each spectral channel. This design shortens the spatial "distance" of target and source datasets for pre-trained deep CNNs. Second, we introduce quaternion algebra to LPCANet, which further shortens the spectral "distance" between remote sensing images and images used to pre-train deep CNNs. With five well-known pre-trained deep CNNs, experimental results on three independent remote sensing datasets demonstrate that our proposed framework obtains state-of-the-art results without fine-tuning and feature fusing. This paper also provides baseline for transferring fresh pre-trained deep CNNs to other remote sensing tasks.

show abstract

Learning High-level Features for Satellite Image Classification With Limited Labeled Samples

Cited by 128 publications

References 36 publications

A Color-Texture-Structure Descriptor for High-Resolution Satellite Image Classification

A Color-Texture-Structure Descriptor for High-Resolution Satellite Image Classification

Deep Salient Feature Based Anti-Noise Transfer Network for Scene Classification of Remote Sensing Imagery

Transferring Pre-Trained Deep CNNs for Remote Scene Classification with General Features Learned from Linear PCA Network

Contact Info

Product

Resources

About