scholarly journals Joint Learning of the Center Points and Deep Metrics for Land-Use Classification in Remote Sensing

2019 ◽  
Vol 11 (1) ◽  
pp. 76 ◽  
Author(s):  
Zhiqiang Gong ◽  
Ping Zhong ◽  
Weidong Hu ◽  
Yuming Hua
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Metric Learning ◽  
Land Use Classification ◽  
Training Process ◽  
Pairwise Correlation ◽  
Deep Model ◽  
Training Samples ◽  
Deep Metric Learning ◽  
Learned Features

Deep learning methods, especially convolutional neural networks (CNNs), have shown remarkable ability for remote sensing scene classification. However, the traditional training process of standard CNNs only takes the point-wise penalization of the training samples into consideration, which usually makes the learned CNNs sub-optimal especially for remote sensing scenes with large intra-class variance and low inter-class variance. To address this problem, deep metric learning, which incorporates the metric learning into the deep model, is used to maximize the inter-class variance and minimize the intra-class variance for better representation. This work introduces structured metric learning for remote sensing scene representation, a special deep metric learning which can take full advantage of the training batch. However, the deep metrics only consider the pairwise correlation between the training samples, and ignores the classwise correlation from the class view. To take the classwise penalization into consideration, this work defines the center points of the learned features of each class in the training process to represent the class. Through increasing the variance between different center points and decreasing the variance between the learned features from each class and the corresponding center point, the representational ability can be further improved. Therefore, this work develops a novel center-based structured metric learning to take advantage of both the deep metrics and the center points. Finally, joint supervision of the cross-entropy loss and the center-based structured metric learning is developed for the land-use classification in remote sensing. It can joint learn the center points and the deep metrics to take advantage of the point-wise, the pairwise, and the classwise correlation. Experiments are conducted over three real-world remote sensing scene datasets, namely UC Merced Land-Use dataset, Brazilian Coffee Scene dataset, and Google dataset. The classification performance can achieve 97.30%, 91.24%, and 92.04% with the proposed method over the three datasets which are better than other state-of-the-art methods under the same experimental setups. The results demonstrate that the proposed method can improve the representational ability for the remote sensing scenes.

scholarly journals The Mapping of Land Use Using Object-Based Image Analysis (OBIA) in Klaten Regency

2020 ◽  
Vol 202 ◽  
pp. 06036
Author(s):  
Nurhadi Bashit ◽  
Novia Sari Ristianti ◽  
Yudi Eko Windarto ◽  
Desyta Ulfiana
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Image Analysis ◽  
Satellite Imagery ◽  
Agricultural Land ◽  
Scale Parameter ◽  
Land Use Classification ◽  
Object Based Image Analysis ◽  
Object Based ◽  
Sentinel 2

Klaten Regency is one of the regencies in Central Java Province that has an increasing population every year. This can cause an increase in built-up land for human activities. The built-up land needs to be monitored so that the construction is in accordance with the regional development plan so that it does not cause problems such as the occurrence of critical land. Therefore, it is necessary to monitor land use regularly. One method for monitoring land use is the remote sensing method. The remote sensing method is much more efficient in mapping land use because without having to survey the field. The remote sensing method utilizes satellite imagery data that can be processed for land use classification. This study uses the sentinel 2 satellite image data with the Object-Based Image Analysis (OBIA) algorithm to obtain land use classification. Sentinel 2 satellite imagery is a medium resolution image category with a spatial resolution of 10 meters. The land use classification can be used to see the distribution of built-up land in Klaten Regency without having to conduct a field survey. The results of the study obtained a segmentation scale parameter value of 60 and a merge scale parameter value of 85. The classification results obtained by 5 types of land use with OBIA. Agricultural land use dominates with an area of 50% of the total area.

scholarly journals Similarity Retention Loss (SRL) Based on Deep Metric Learning for Remote Sensing Image Retrieval

2020 ◽  
Vol 9 (2) ◽  
pp. 61
Author(s):  
Hongwei Zhao ◽  
Lin Yuan ◽  
Haoyu Zhao
Keyword(s):  
Remote Sensing ◽  
Spatial Distribution ◽  
Image Retrieval ◽  
Learning Strategy ◽  
Metric Learning ◽  
Remote Sensing Image ◽  
Fine Tuning ◽  
Retention Loss ◽  
Deep Metric Learning ◽  
Hard Samples

Recently, with the rapid growth of the number of datasets with remote sensing images, it is urgent to propose an effective image retrieval method to manage and use such image data. In this paper, we propose a deep metric learning strategy based on Similarity Retention Loss (SRL) for content-based remote sensing image retrieval. We have improved the current metric learning methods from the following aspects—sample mining, network model structure and metric loss function. On the basis of redefining the hard samples and easy samples, we mine the positive and negative samples according to the size and spatial distribution of the dataset classes. At the same time, Similarity Retention Loss is proposed and the ratio of easy samples to hard samples in the class is used to assign dynamic weights to the hard samples selected in the experiment to learn the sample structure characteristics within the class. For negative samples, different weights are set based on the spatial distribution of the surrounding samples to maintain the consistency of similar structures among classes. Finally, we conduct a large number of comprehensive experiments on two remote sensing datasets with the fine-tuning network. The experiment results show that the method used in this paper achieves the state-of-the-art performance.

scholarly journals Enhancing remote sensing image retrieval using a triplet deep metric learning network

2019 ◽  
Vol 41 (2) ◽  
pp. 740-751 ◽  
Author(s):  
Rui Cao ◽  
Qian Zhang ◽  
Jiasong Zhu ◽  
Qing Li ◽  
Qingquan Li ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Image Retrieval ◽  
Metric Learning ◽  
Remote Sensing Image ◽  
Learning Network ◽  
Deep Metric Learning

scholarly journals Deep Metric Learning by Online Soft Mining and Class-Aware Attention

2019 ◽  
Vol 33 ◽  
pp. 5361-5368 ◽  
Author(s):  
Xinshao Wang ◽  
Yang Hua ◽  
Elyor Kodirov ◽  
Guosheng Hu ◽  
Neil M. Robertson
Keyword(s):  
Large Fraction ◽  
Metric Learning ◽  
Improve Performance ◽  
Fine Grained ◽  
Training Samples ◽  
Deep Embedding ◽  
Data Points ◽  
Accelerate Convergence ◽  
Deep Metric Learning ◽  
Mining Methods

Deep metric learning aims to learn a deep embedding that can capture the semantic similarity of data points. Given the availability of massive training samples, deep metric learning is known to suffer from slow convergence due to a large fraction of trivial samples. Therefore, most existing methods generally resort to sample mining strategies for selecting nontrivial samples to accelerate convergence and improve performance. In this work, we identify two critical limitations of the sample mining methods, and provide solutions for both of them. First, previous mining methods assign one binary score to each sample, i.e., dropping or keeping it, so they only selects a subset of relevant samples in a mini-batch. Therefore, we propose a novel sample mining method, called Online Soft Mining (OSM), which assigns one continuous score to each sample to make use of all samples in the mini-batch. OSM learns extended manifolds that preserve useful intraclass variances by focusing on more similar positives. Second, the existing methods are easily influenced by outliers as they are generally included in the mined subset. To address this, we introduce Class-Aware Attention (CAA) that assigns little attention to abnormal data samples. Furthermore, by combining OSM and CAA, we propose a novel weighted contrastive loss to learn discriminative embeddings. Extensive experiments on two fine-grained visual categorisation datasets and two video-based person re-identification benchmarks show that our method significantly outperforms the state-of-the-art.

scholarly journals An Ensemble Learning Approach for Urban Land Use Mapping Based on Remote Sensing Imagery and Social Sensing Data

2020 ◽  
Vol 12 (19) ◽  
pp. 3254
Author(s):  
Zhou Huang ◽  
Houji Qi ◽  
Chaogui Kang ◽  
Yuelong Su ◽  
Yu Liu
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Land Cover ◽  
Ensemble Learning ◽  
Urban Land ◽  
Urban Land Use ◽  
Learning Approach ◽  
Land Use Classification ◽  
Remote Sensing Imagery ◽  
Sensing Data

Urban land use mapping is crucial for effective urban management and planning due to the rapid change of urban processes. State-of-the-art approaches rely heavily on the socioeconomic, topographical, infrastructural and land cover information of urban environments via feeding them into ad hoc classifiers for land use classification. Yet, the major challenge lies in the lack of a universal and reliable approach for the extraction and combination of physical and socioeconomic features derived from remote sensing imagery and social sensing data. This article proposes an ensemble-learning-approach-based solution of integrating a rich body of features derived from high resolution satellite images, street-view images, building footprints, points-of-interest (POIs) and social media check-ins for the urban land use mapping task. The proposed approach can statistically differentiate the importance of input feature variables and provides a good explanation for the relationships between land cover, socioeconomic activities and land use categories. We apply the proposed method to infer the land use distribution in fine-grained spatial granularity within the Fifth Ring Road of Beijing and achieve an average classification accuracy of 74.2% over nine typical land use types. The results also indicate that our model outperforms several alternative models that have been widely utilized as baselines for land use classification.

Sign in / Sign up

Export Citation Format

Share Document