Superpixel based land cover classification of VHR satellite image combining multi-scale CNN and scale parameter estimation

Chen, Yangyang; Ming, Dongping; Lv, Xianwei

doi:10.1007/s12145-019-00383-2

Cited by 63 publications

(55 citation statements)

References 92 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lv et al classified remote sensing images with SEEDS-CNN and scale effectiveness analysis [20]. Chen et al applied multi-scale CNN and scale parameter estimation in land cover classification [21]. Zhou et al proposed So-CNN for urban functional zone fine division with VHR remote sensing images [22].…”

Section: Introductionmentioning

confidence: 99%

BRRNet: A Fully Convolutional Neural Network for Automatic Building Extraction From High-Resolution Remote Sensing Images

et al. 2020

View full text Add to dashboard Cite

Building extraction from high-resolution remote sensing images is of great significance in urban planning, population statistics, and economic forecast. However, automatic building extraction from high-resolution remote sensing images remains challenging. On the one hand, the extraction results of buildings are partially missing and incomplete due to the variation of hue and texture within a building, especially when the building size is large. On the other hand, the building footprint extraction of buildings with complex shapes is often inaccurate. To this end, we propose a new deep learning network, termed Building Residual Refine Network (BRRNet), for accurate and complete building extraction. BRRNet consists of such two parts as the prediction module and the residual refinement module. The prediction module based on an encoder–decoder structure introduces atrous convolution of different dilation rates to extract more global features, by gradually increasing the receptive field during feature extraction. When the prediction module outputs the preliminary building extraction results of the input image, the residual refinement module takes the output of the prediction module as an input. It further refines the residual between the result of the prediction module and the real result, thus improving the accuracy of building extraction. In addition, we use Dice loss as the loss function during training, which effectively alleviates the problem of data imbalance and further improves the accuracy of building extraction. The experimental results on Massachusetts Building Dataset show that our method outperforms other five state-of-the-art methods in terms of the integrity of buildings and the accuracy of complex building footprints.

show abstract

Section: Introductionmentioning

confidence: 99%

BRRNet: A Fully Convolutional Neural Network for Automatic Building Extraction From High-Resolution Remote Sensing Images

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Moreover, the performance of convolutional neural networks (CNNs) in scene classification or object detection [17,18] has been practically established. A CNN is a multi-layer artificial neural network with convolutional kernels, where each layer is a non-linear feature detector performing local processing of contiguous features within each layer, and it is developed by eliciting the function of the human brain [19]. Presently, CNN-based land cover classification methods fall into three main categories: semantic segmentation using fully convolutional networks (FCNs) [20], pixel-based CNN classification, and superpixel-based CNN classification, with many different configurations.…”

Section: Image Classification-coastal Areamentioning

confidence: 99%

“…Pixel-based CNNs are used to classify single pixels, by using their features. Applied in a pixel-based approach, a square image patch containing adjacent pixels of the pixel to be classified feeds the CNN for features extraction [19]. During the training phase, training images are disaggregated into overlapping patches, and each patch is typically centered on a pixel which provides the class for the whole patch.…”

Section: Image Classification-coastal Areamentioning

confidence: 99%

Assessment of a Smartphone-Based Camera System for Coastal Image Segmentation and Sargassum monitoring

Valentini

Balouin

2020

JMSE

View full text Add to dashboard Cite

Coastal video monitoring has proven to be a valuable ground-based technique to investigate ocean processes. Presently, there is a growing need for automatic, technically efficient, and inexpensive solutions for image processing. Moreover, beach and coastal water quality problems are becoming significant and need attention. This study employs a methodological approach to exploit low-cost smartphone-based images for coastal image classification. The objective of this paper is to present a methodology useful for supervised classification for image semantic segmentation and its application for the development of an automatic warning system for Sargassum algae detection and monitoring.A pixel-wise convolutional neural network (CNN) has demonstrated optimal performance in the classification of natural images by using abstracted deep features. Conventional CNNs demand a great deal of resources in terms of processing time and disk space. Therefore, CNN classification with superpixels has recently become a field of interest. In this work, a CNN-based deep learning framework is proposed that combines sticky-edge adhesive superpixels. The results indicate that a cheap camera-based video monitoring system is a suitable data source for coastal image classification, with optimal accuracy in the range between 75% and 96%. Furthermore, an application of the method for an ongoing case study related to Sargassum monitoring in the French Antilles proved to be very effective for developing a warning system, aiming at evaluating floating algae and algae that had washed ashore, supporting municipalities in beach management.

show abstract

“…Internationally, the land-use changes of Dakaria in Egypt, a northern region in Rwanda, Nagadeh in Iran, metropolitan areas of Atlanta, Georgia, in the United States, and Hue City in Vietnam have been studied using remote sensing images obtained by satellites, such as Landsat (an Earth observation satellite commissioned by the U.S.) and SPOT (Satellite Pour l'Observation de la Terre, an Earth observation satellite initiated by France), [11], [12], [13], [14] , [15]. In China, the dynamic changes of land-use in Beijing, Shanghai, Guangzhou, Jiaozuo, Wuyishan, and Jining have been monitored, and the landuse evolvement procedures of the Dongjiang River Basin, Pearl River Estuary, and Yellow River Delta have been analyzed [16], [17], [18].…”

Section: Introductionmentioning

confidence: 99%

Dynamic Monitoring and Analysis of Land-Use and Land-Cover Change Using Landsat Multitemporal Data in the Zhoushan Archipelago, China

Chen

Liao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Rapid urbanization, marked by massive land-use and land-cover change (LUCC) and explosive population growth, has a significant impact on human activities. To provide a comprehensive understanding of the characteristics of LUCC in the Zhoushan Archipelago, dynamic monitoring and analysis of LUCC was performed using seven Landsat images from 1984 to 2016. The observations and results obtained in this study include the following: the forest of Zhoushan Island was well protected and had a slight increase in the area, yet the spatial distribution remained nearly unchanged; the construction land gradually expanded to all of the coastal plains and southern islands with a trend "first southward, then eastward and finally northward," and the area increased by 571.88%; the coastal cropland/grassland surrounding Zhoushan Island was observed to have been gradually occupied by construction land as noted by a 27.94% decrease in area and the spatial distribution becoming discrete; the mudflat decreased by 93.39% and was mainly converted into construction land; the total land area observed in this study increased by 8.87%, which was achieved primarily by sea reclamation and conversion to construction land and inland water body. These results provide a better understanding of the spatial and temporal evolvement features of LUCC in Zhoushan, China, and the LUCC characteristics that can be expected to significantly support urban management and sustainable development.

show abstract

Superpixel based land cover classification of VHR satellite image combining multi-scale CNN and scale parameter estimation

Cited by 63 publications

References 92 publications

BRRNet: A Fully Convolutional Neural Network for Automatic Building Extraction From High-Resolution Remote Sensing Images

BRRNet: A Fully Convolutional Neural Network for Automatic Building Extraction From High-Resolution Remote Sensing Images

Assessment of a Smartphone-Based Camera System for Coastal Image Segmentation and Sargassum monitoring

Dynamic Monitoring and Analysis of Land-Use and Land-Cover Change Using Landsat Multitemporal Data in the Zhoushan Archipelago, China

Contact Info

Product

Resources

About