scholarly journals Improving the Accuracy of Land Cover Mapping by Distributing Training Samples

2021 ◽  
Vol 13 (22) ◽  
pp. 4594
Author(s):  
Chenxi Li ◽  
Zaiying Ma ◽  
Liuyue Wang ◽  
Weijian Yu ◽  
Donglin Tan ◽  
...  
Keyword(s):  
Land Cover ◽  
Object Oriented ◽  
Land Cover Classification ◽  
Training Sample ◽  
Stratified Sampling ◽  
Systematic Sampling ◽  
Sampling Strategies ◽  
Sample Distribution ◽  
Training Samples ◽  
Sampling Approach

High-quality training samples are essential for accurate land cover classification. Due to the difficulties in collecting a large number of training samples, it is of great significance to collect a high-quality sample dataset with a limited sample size but effective sample distribution. In this paper, we proposed an object-oriented sampling approach by segmenting image blocks expanded from systematically distributed seeds (object-oriented sampling approach) and carried out a rigorous comparison of seven sampling strategies, including random sampling, systematic sampling, stratified sampling (stratified sampling with the strata of land cover classes based on classification product, Latin hypercube sampling, and spatial Latin hypercube sampling), object-oriented sampling, and manual sampling, to explore the impact of training sample distribution on the accuracy of land cover classification when the samples are limited. Five study areas from different climate zones were selected along the China–Mongolia border. Our research identified the proposed object-oriented sampling approach as the first-choice sampling strategy in collecting training samples. This approach improved the diversity and completeness of the training sample set. Stratified sampling with strata defined by the combination of different attributes and stratified sampling with the strata of land cover classes had their limitations, and they performed well in specific situations when we have enough prior knowledge or high-accuracy product. Manual sampling was greatly influenced by the experience of interpreters. All these sampling strategies mentioned above outperformed random sampling and systematic sampling in this study. The results indicate that the sampling strategies of training datasets do have great impacts on the land cover classification accuracies when the sample size is limited. This paper will provide guidance for efficient training sample collection to increase classification accuracies.

Impact of Training Set Size on Object-Based Land Cover Classification

2014 ◽  
Vol 5 (3) ◽  
pp. 49-67 ◽  
Author(s):  
Gerhard Myburgh ◽  
Adriaan van Niekerk
Keyword(s):  
Land Cover ◽  
Classification Tree ◽  
Land Cover Classification ◽  
Training Sample ◽  
Support Vector ◽  
Training Set ◽  
Training Sample Size ◽  
Set Size ◽  
Object Based ◽  
Training Samples

Supervised classifiers are commonly employed in remote sensing to extract land cover information, but various factors affect their accuracy. The number of available training samples, in particular, is known to have a significant impact on classification accuracies. Obtaining a sufficient number of samples is, however, not always practical. The support vector machine (SVM) is a supervised classifier known to perform well with limited training samples and has been compared favourably to other classifiers for various problems in pixel-based land cover classification. Very little research on training-sample size and classifier performance has been done in a geographical object-based image analysis (GEOBIA) environment. This paper compares the performance of SVM, nearest neighbour (NN) and maximum likelihood (ML) classifiers in a GEOBIA environment, with a focus on the influence of training-set size. Training-set sizes ranging from 4-20 per land cover class were tested. Classification tree analysis (CTA) was used for feature selection. The results indicate that the performance of all the classifiers improved significantly as the size of the training set increased. The ML classifier performed poorly when few (<10 per class) training samples were used and the NN classifier performed poorly compared to SVM throughout the experiment. SVM was the superior classifier for all training-set sizes although ML achieved competitive results for sets of 12 or more training areas per class.

scholarly journals LAND COVER CLASSIFICATION ALOS AVNIR DATA USING IKONOS AS REFERENCE

2012 ◽  
Vol 9 (1) ◽  
Author(s):  
Bambang Trisakti ◽  
Dini Oktaviana Ambarwati
Keyword(s):  
Land Cover ◽  
Near Infrared ◽  
Good Accuracy ◽  
Confusion Matrix ◽  
Principal Component ◽  
Land Cover Classification ◽  
Accuracy Evaluation ◽  
Post Processing ◽  
Classification Result ◽  
Training Samples

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.

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

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.

scholarly journals Domain Adversarial Neural Networks for Large-Scale Land Cover Classification

2019 ◽  
Vol 11 (10) ◽  
pp. 1153 ◽  
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%.

Knowledge-Based Object Oriented Land Cover Classification Using SPOT5 Imagery in Forest-Agriculture Ecotones

2010 ◽  
Vol 8 (1) ◽  
pp. 22-31 ◽  
Author(s):  
Su Wei ◽  
Zhang Chao ◽  
Yang Jianyu ◽  
Wu Honggan ◽  
Chen Minjie ◽  
...  
Keyword(s):  
Land Cover ◽  
Object Oriented ◽  
Land Cover Classification ◽  
Knowledge Based
Sign in / Sign up

Export Citation Format

Share Document