Extraction of training samples from time-series MODIS imagery and its utility for land cover classification

Abstract. Advanced Land Observation Satellite (ALOS) is a Japanese satellite equipped with 3 sensors i.e., PRISM, AVNIR, and PALSAR. The Advanced Visible and Near Infrared Radiometer (AVNIR) provides multi spectral sensors ranging from Visible to Near Infrared to observe land and coastal zones. It has 10 meter spatial resolution, which can be used to map land cover with a scale of 1:25000. The purpose of this research was to determineclassification for land cover mapping using ALOS AVNIR data. Training samples were collected for 11 land cover classes from Bromo volcano by visually referring to very high resolution data of IKONOS panchromatic data. The training samples were divided into samples for classification input and samples for accuracy evaluation. Principal component analysis (PCA) was conducted for AVNIR data, and the generated PCA bands were classified using Maximum Likehood Enhanced Neighbor method. The classification result was filtered and re-classed into 8 classes. Misclassifications were evaluated and corrected in the post processing stage. The accuracy of classifications results, before and after post processing, were evaluated using confusion matrix method. The result showed that Maximum Likelihood Enhanced Neighbor classifier with post processing can produce land cover classification result of AVNIR data with good accuracy (total accuracy 94% and kappa statistic 0.92). ALOS AVNIR has been proven as a potential satellite data to map land cover in the study area with good accuracy.

Download Full-text

Channel-Based Attention for Land Cover Classification using Sentinel-2 Time Series

10.1109/igarss47720.2021.9554205 ◽

2021 ◽

Author(s):

H. Courteille ◽

A. Benoit ◽

N. Meger ◽

A. Atto ◽

D. Ienco

Keyword(s):

Time Series ◽

Land Cover ◽

Land Cover Classification ◽

Sentinel 2

Download Full-text

Time-Series Model-Adjusted Percentile Features: Improved Percentile Features for Land-Cover Classification Based on Landsat Data

Remote Sensing ◽

10.3390/rs12183091 ◽

2020 ◽

Vol 12 (18) ◽

pp. 3091

Author(s):

Shuai Xie ◽

Liangyun Liu ◽

Jiangning Yang

Keyword(s):

Time Series ◽

Land Cover ◽

Time Series Data ◽

Land Cover Classification ◽

Time Series Model ◽

Training Data ◽

Series Data ◽

Landsat Data ◽

Data Sampling ◽

Continuous Change

Percentile features derived from Landsat time-series data are widely adopted in land-cover classification. However, the temporal distribution of Landsat valid observations is highly uneven across different pixels due to the gaps resulting from clouds, cloud shadows, snow, and the scan line corrector (SLC)-off problem. In addition, when applying percentile features, land-cover change in time-series data is usually not considered. In this paper, an improved percentile called the time-series model (TSM)-adjusted percentile is proposed for land-cover classification based on Landsat data. The Landsat data were first modeled using three different time-series models, and the land-cover changes were continuously monitored using the continuous change detection (CCD) algorithm. The TSM-adjusted percentiles for stable pixels were then derived from the synthetic time-series data without gaps. Finally, the TSM-adjusted percentiles were used for generating supervised random forest classifications. The proposed methods were implemented on Landsat time-series data of three study areas. The classification results were compared with those obtained using the original percentiles derived from the original time-series data with gaps. The results show that the land-cover classifications obtained using the proposed TSM-adjusted percentiles have significantly higher overall accuracies than those obtained using the original percentiles. The proposed method was more effective for forest types with obvious phenological characteristics and with fewer valid observations. In addition, it was also robust to the training data sampling strategy. Overall, the methods proposed in this work can provide accurate characterization of land cover and improve the overall classification accuracy based on such metrics. The findings are promising for percentile-based land cover classification using Landsat time series data, especially in the areas with frequent cloud coverage.

Download Full-text

Automatic Land-Cover Mapping using Landsat Time-Series Data based on Google Earth Engine

Remote Sensing ◽

10.3390/rs11243023 ◽

2019 ◽

Vol 11 (24) ◽

pp. 3023 ◽

Cited By ~ 9

Author(s):

Shuai Xie ◽

Liangyun Liu ◽

Xiao Zhang ◽

Jiangning Yang ◽

Xidong Chen ◽

...

Keyword(s):

Time Series ◽

Land Cover ◽

Vegetation Index ◽

Time Series Data ◽

Land Cover Classification ◽

Google Earth ◽

Thematic Mapper ◽

Series Data ◽

Land Cover Mapping ◽

Google Earth Engine

The Google Earth Engine (GEE) has emerged as an essential cloud-based platform for land-cover classification as it provides massive amounts of multi-source satellite data and high-performance computation service. This paper proposed an automatic land-cover classification method using time-series Landsat data on the GEE cloud-based platform. The Moderate Resolution Imaging Spectroradiometer (MODIS) land-cover products (MCD12Q1.006) with the International Geosphere–Biosphere Program (IGBP) classification scheme were used to provide accurate training samples using the rules of pixel filtering and spectral filtering, which resulted in an overall accuracy (OA) of 99.2%. Two types of spectral–temporal features (percentile composited features and median composited monthly features) generated from all available Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper Plus (ETM+) data from the year 2010 ± 1 were used as input features to a Random Forest (RF) classifier for land-cover classification. The results showed that the monthly features outperformed the percentile features, giving an average OA of 80% against 77%. In addition, the monthly features composited using the median outperformed those composited using the maximum Normalized Difference Vegetation Index (NDVI) with an average OA of 80% against 78%. Therefore, the proposed method is able to generate accurate land-cover mapping automatically based on the GEE cloud-based platform, which is promising for regional and global land-cover mapping.

Download Full-text

Land Cover Classification using Google Earth Engine and Random Forest Classifier—The Role of Image Composition

Remote Sensing ◽

10.3390/rs12152411 ◽

2020 ◽

Vol 12 (15) ◽

pp. 2411 ◽

Cited By ~ 2

Author(s):

Thanh Noi Phan ◽

Verena Kuch ◽

Lukas W. Lehnert

Keyword(s):

Time Series ◽

Random Forest ◽

Land Cover ◽

Land Cover Classification ◽

High Accuracy ◽

Google Earth ◽

Temporal Aggregation ◽

Google Earth Engine ◽

Time Series Images ◽

Land Cover Maps

Land cover information plays a vital role in many aspects of life, from scientific and economic to political. Accurate information about land cover affects the accuracy of all subsequent applications, therefore accurate and timely land cover information is in high demand. In land cover classification studies over the past decade, higher accuracies were produced when using time series satellite images than when using single date images. Recently, the availability of the Google Earth Engine (GEE), a cloud-based computing platform, has gained the attention of remote sensing based applications where temporal aggregation methods derived from time series images are widely applied (i.e., the use the metrics such as mean or median), instead of time series images. In GEE, many studies simply select as many images as possible to fill gaps without concerning how different year/season images might affect the classification accuracy. This study aims to analyze the effect of different composition methods, as well as different input images, on the classification results. We use Landsat 8 surface reflectance (L8sr) data with eight different combination strategies to produce and evaluate land cover maps for a study area in Mongolia. We implemented the experiment on the GEE platform with a widely applied algorithm, the Random Forest (RF) classifier. Our results show that all the eight datasets produced moderately to highly accurate land cover maps, with overall accuracy over 84.31%. Among the eight datasets, two time series datasets of summer scenes (images from 1 June to 30 September) produced the highest accuracy (89.80% and 89.70%), followed by the median composite of the same input images (88.74%). The difference between these three classifications was not significant based on the McNemar test (p > 0.05). However, significant difference (p < 0.05) was observed for all other pairs involving one of these three datasets. The results indicate that temporal aggregation (e.g., median) is a promising method, which not only significantly reduces data volume (resulting in an easier and faster analysis) but also produces an equally high accuracy as time series data. The spatial consistency among the classification results was relatively low compared to the general high accuracy, showing that the selection of the dataset used in any classification on GEE is an important and crucial step, because the input images for the composition play an essential role in land cover classification, particularly with snowy, cloudy and expansive areas like Mongolia.

Download Full-text

Urban Land-Cover Classification Using Side-View Information from Oblique Images

Remote Sensing ◽

10.3390/rs12030390 ◽

2020 ◽

Vol 12 (3) ◽

pp. 390

Author(s):

Changlin Xiao ◽

Rongjun Qin ◽

Xiao Ling

Keyword(s):

Feature Extraction ◽

Land Cover ◽

Remote Sensing Data ◽

Land Cover Classification ◽

Side View ◽

High Resolution Data ◽

Training Samples ◽

Surface Models ◽

Extraction Algorithm ◽

Oblique Images

Land-cover classification on very high resolution data (decimetre-level) is a well-studied yet challenging problem in remote sensing data processing. Most of the existing works focus on using images with orthographic view or orthophotos with the associated digital surface models (DSMs). However, the use of the nowadays widely-available oblique images to support such a task is not sufficiently investigated. In the effort of identifying different land-cover classes, it is intuitive that information of side-views obtained from the oblique can be of great help, yet how this can be technically achieved is challenging due to the complex geometric association between the side and top views. We aim to address these challenges in this paper by proposing a framework with enhanced classification results, leveraging the use of orthophoto, digital surface models and oblique images. The proposed method contains a classic two-step of (1) feature extraction and (2) a classification approach, in which the key contribution is a feature extraction algorithm that performs simplified geometric association between top-view segments (from orthophoto) and side-view planes (from projected oblique images), and joint statistical feature extraction. Our experiment on five test sites showed that the side-view information could steadily improve the classification accuracy with both kinds of training samples (1.1% and 5.6% for evenly distributed and non-evenly distributed samples, separately). Additionally, by testing the classifier at a large and untrained site, adding side-view information showed a total of 26.2% accuracy improvement of the above-ground objects, which demonstrates the strong generalization ability of the side-view features.

Download Full-text

Uncertainty Analysis of Object-Based Land-Cover Classification Using Sentinel-2 Time-Series Data

Remote Sensing ◽

10.3390/rs12223798 ◽

2020 ◽

Vol 12 (22) ◽

pp. 3798

Author(s):

Lei Ma ◽

Michael Schmitt ◽

Xiaoxiang Zhu

Keyword(s):

Time Series ◽

Land Cover ◽

Time Series Data ◽

Land Cover Classification ◽

Series Data ◽

Spectral Bands ◽

Object Based ◽

Spatio Temporal ◽

Optical Satellite Images ◽

The Impact

Recently, time-series from optical satellite data have been frequently used in object-based land-cover classification. This poses a significant challenge to object-based image analysis (OBIA) owing to the presence of complex spatio-temporal information in the time-series data. This study evaluates object-based land-cover classification in the northern suburbs of Munich using time-series from optical Sentinel data. Using a random forest classifier as the backbone, experiments were designed to analyze the impact of the segmentation scale, features (including spectral and temporal features), categories, frequency, and acquisition timing of optical satellite images. Based on our analyses, the following findings are reported: (1) Optical Sentinel images acquired over four seasons can make a significant contribution to the classification of agricultural areas, even though this contribution varies between spectral bands for the same period. (2) The use of time-series data alleviates the issue of identifying the “optimal” segmentation scale. The finding of this study can provide a more comprehensive understanding of the effects of classification uncertainty on object-based dense multi-temporal image classification.

Download Full-text

Domain Adversarial Neural Networks for Large-Scale Land Cover Classification

Remote Sensing ◽

10.3390/rs11101153 ◽

2019 ◽

Vol 11 (10) ◽

pp. 1153 ◽

Cited By ~ 1

Author(s):

Mesay Belete Bejiga ◽

Farid Melgani ◽

Pietro Beraldini

Keyword(s):

Neural Networks ◽

Land Cover ◽

Transfer Learning ◽

Large Scale ◽

Domain Adaptation ◽

Land Cover Classification ◽

Target Domain ◽

Training Samples ◽

Latent Space ◽

Large Scale Land

Learning classification models require sufficiently labeled training samples, however, collecting labeled samples for every new problem is time-consuming and costly. An alternative approach is to transfer knowledge from one problem to another, which is called transfer learning. Domain adaptation (DA) is a type of transfer learning that aims to find a new latent space where the domain discrepancy between the source and the target domain is negligible. In this work, we propose an unsupervised DA technique called domain adversarial neural networks (DANNs), composed of a feature extractor, a class predictor, and domain classifier blocks, for large-scale land cover classification. Contrary to the traditional methods that perform representation and classifier learning in separate stages, DANNs combine them into a single stage, thereby learning a new representation of the input data that is both domain-invariant and discriminative. Once trained, the classifier of a DANN can be used to predict both source and target domain labels. Additionally, we also modify the domain classifier of a DANN to evaluate its suitability for multi-target domain adaptation problems. Experimental results obtained for both single and multiple target DA problems show that the proposed method provides a performance gain of up to 40%.

Download Full-text